Royce  Reinger

Royce Reinger

1672160760

Deep Learning with Satellite & Aerial Imagery

This page lists resources on deep learning applied to satellite and aerial imagery. For regular updates 👇

🖥️ satellite-image-deep-learning.com

Are you looking for a remote sensing dataset, or want to know about training and deploying models?

📺 Video: the remote-sensing-datasets repository

How to use this repository: if you know exactly what you are looking for (e.g. a dataset name) you can Control+F to search for it in the page. Otherwise refer to the table of contents below, and search within the relevant section. Material that is suitable for getting started with a topic is tagged with BEGINNER, which can also be searched.

Techniques

This section explores the different deep and machine learning (ML) techniques applied to common problems in satellite imagery analysis. Good background reading is Deep learning in remote sensing applications: A meta-analysis and review

Classification

Classification is the task of assigning a label to an image, e.g. this is an image of a forest. The more complex case is applying multiple labels to an image. This approach of image level classification is not to be confused with pixel-level classification which is called semantic segmentation. Read more in my post A brief introduction to satellite image classification with neural networks

Segmentation

Segmentation will assign a class label to each pixel in an image. Single class models are often trained for road or building segmentation, with multi class for land use/crop type classification. Note that many articles which refer to 'hyperspectral land classification' are actually describing semantic segmentation. Note that cloud detection can be addressed with semantic segmentation and has its own section Cloud detection & removal. Read more about segmentation in my post A brief introduction to satellite image segmentation with neural networks

Segmentation - Land use & land cover

Segmentation - Vegetation, crops & crop boundaries

Segmentation - Water, coastlines & floods

Segmentation - Fire, smoke & burn areas

Segmentation - Landslides

Segmentation - Glaciers

  • HED-UNet -> a model for simultaneous semantic segmentation and edge detection, examples provided are glacier fronts and building footprints using the Inria Aerial Image Labeling dataset
  • glacier_mapping -> Mapping glaciers in the Hindu Kush Himalaya, Landsat 7 images, Shapefile labels of the glaciers, Unet with dropout
  • glacier-detect-ML -> a simple logistic regression model to identify a glacier in Landsat satellite imagery
  • GlacierSemanticSegmentation -> uses unet
  • Antarctic-fracture-detection -> uses UNet with the MODIS Mosaic of Antarctica to detect surface fractures (paper)

Segmentation - Other environmental

Segmentation - Roads

Extracting roads is challenging due to the occlusions caused by other objects and the complex traffic environment

Segmentation - Buildings & rooftops

Segmentation - Solar panels

Segmentation - Other manmade

Instance segmentation

In instance segmentation, each individual 'instance' of a segmented area is given a unique lable. For detection of very small objects this may a good approach, but it can struggle seperating individual objects that are closely spaced.

Panoptic segmentation

Object detection

Onject detection is the task of placing a box around the bounds of an object (i.e. creating a bounding box). Typical use cases are detecting vehicles, aircraft & ships. A good introduction to the challenge of performing object detection on aerial imagery is given in this paper. In summary, images are large and objects may comprise only a few pixels, easily confused with random features in background. For the same reason, object detection datasets are inherently imbalanced, since the area of background typically dominates over the area of the objects to be detected. In general object detection performs well on large objects, and gets increasingly difficult as the objects get smaller & more densely packed. Model accuracy falls off rapidly as image resolution degrades, so it is common for object detection to use very high resolution imagery, e.g. 30cm RGB. A particular characteristic of aerial images is that objects can be oriented in any direction, so using rotated bounding boxes which align with the object can be crucial for extracting measurements of the length and width of an object.

Object detection with rotated bounding boxes

Orinted bounding boxes (OBB) are polygons representing rotated rectangles

  • For datasets checkout DOTA & HRSC2016
  • mmrotate -> Rotated Object Detection Benchmark, with pretrained models and function for inferencing on very large images
  • OBBDetection -> an oriented object detection library, which is based on MMdetection
  • rotate-yolov3 -> Rotation object detection implemented with yolov3. Also see yolov3-polygon
  • DRBox -> for detection tasks where the objects are orientated arbitrarily, e.g. vehicles, ships and airplanes
  • s2anet -> Official code of the paper 'Align Deep Features for Oriented Object Detection'
  • CFC-Net -> Official implementation of "CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images"
  • ReDet -> Official code of the paper "ReDet: A Rotation-equivariant Detector for Aerial Object Detection"
  • BBAVectors-Oriented-Object-Detection -> Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors
  • CSL_RetinaNet_Tensorflow -> Code for ECCV 2020 paper: Arbitrary-Oriented Object Detection with Circular Smooth Label
  • r3det-on-mmdetection -> R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
  • R-DFPN_FPN_Tensorflow -> Rotation Dense Feature Pyramid Networks (Tensorflow)
  • R2CNN_Faster-RCNN_Tensorflow -> Rotational region detection based on Faster-RCNN
  • Rotated-RetinaNet -> implemented in pytorch, it supports the following datasets: DOTA, HRSC2016, ICDAR2013, ICDAR2015, UCAS-AOD, NWPU VHR-10, VOC2007
  • OBBDet_Swin -> The sixth place winning solution in 2021 Gaofen Challenge
  • CG-Net -> Learning Calibrated-Guidance for Object Detection in Aerial Images. With paper
  • OrientedRepPoints_DOTA -> Oriented RepPoints + Swin Transformer/ReResNet
  • yolov5_obb -> yolov5 + Oriented Object Detection
  • How to Train YOLOv5 OBB -> YOLOv5 OBB tutorial and YOLOv5 OBB noteboook
  • OHDet_Tensorflow -> can be applied to rotation detection and object heading detection
  • Seodore -> framework maintaining recent updates of mmdetection
  • Rotation-RetinaNet-PyTorch -> oriented detector Rotation-RetinaNet implementation on Optical and SAR ship dataset
  • AIDet -> an open source object detection in aerial image toolbox based on MMDetection
  • rotation-yolov5 -> rotation detection based on yolov5
  • ShipDetection -> Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box, based on Faster R-CNN and ORN, uses caffe
  • SLRDet -> project based on mmdetection to reimplement RRPN and use the model Faster R-CNN OBB
  • AxisLearning -> code for 2020 paper: Axis Learning for Orientated Objects Detection in Aerial Images
  • Detection_and_Recognition_in_Remote_Sensing_Image -> This work uses PaNet to realize Detection and Recognition in Remote Sensing Image by MXNet
  • DrBox-v2-tensorflow -> tensorflow implementation of DrBox-v2 which is an improved detector with rotatable boxes for target detection in remote sensing images
  • Rotation-EfficientDet-D0 -> A PyTorch Implementation Rotation Detector based EfficientDet Detector, applied to custom rotation vehicle datasets
  • DODet -> Dual alignment for oriented object detection, uses DOTA dataset. With paper
  • GF-CSL -> code for 2022 paper: Gaussian Focal Loss: Learning Distribution Polarized Angle Prediction for Rotated Object Detection in Aerial Images
  • simplified_rbox_cnn -> code for 2018 paper: RBox-CNN: rotated bounding box based CNN for ship detection in remote sensing image. Uses Tensorflow object detection API
  • Polar-Encodings -> code for 2021 [paper](Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images)
  • R-CenterNet -> detector for rotated-object based on CenterNet
  • piou -> Orientated Object Detection; IoU Loss, applied to DOTA dataset
  • DAFNe -> code for 2021 paper: DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection
  • AProNet -> code for 2021 paper: AProNet: Detecting objects with precise orientation from aerial images. Applied to datasets DOTA and HRSC2016
  • UCAS-AOD-benchmark -> A benchmark of UCAS-AOD dataset
  • RotateObjectDetection -> based on Ultralytics/yolov5, with adjustments to enable rotate prediction boxes. Also see PolygonObjectDetection
  • AD-Toolbox -> Aerial Detection Toolbox based on MMDetection and MMRotate, with support for more datasets
  • GGHL -> code for 2022 paper: A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
  • NPMMR-Det -> code for 2021 paper: A Novel Nonlocal-Aware Pyramid and Multiscale Multitask Refinement Detector for Object Detection in Remote Sensing Images
  • AOPG -> code for 2022 paper: Anchor-Free Oriented Proposal Generator for Object Detection
  • SE2-Det -> code for 2022 paper: Semantic-Edge-Supervised Single-Stage Detector for Oriented Object Detection in Remote Sensing Imagery
  • OrientedRepPoints -> code for 2021 paper: Oriented RepPoints for Aerial Object Detection
  • TS-Conv -> code for 2022 paper: Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
  • FCOSR -> A Simple Anchor-free Rotated Detector for Aerial Object Detection. This implement is modified from mmdetection. See also TensorRT_Inference

Object detection enhanced by super resolution

Salient object detection

Detecting the most noticeable or important object in a scene

  • ACCoNet -> code for 2022 paper: Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images
  • MCCNet -> Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
  • CorrNet -> Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation. With paper
  • Reading list for deep learning based Salient Object Detection in Optical Remote Sensing Images
  • ORSSD-dataset -> salient object detection dataset
  • EORSSD-dataset -> Extended Optical Remote Sensing Saliency Detection (EORSSD) Dataset
  • DAFNet_TIP20 -> code for 2020 paper: Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
  • EMFINet -> code for 2021 paper: Edge-Aware Multiscale Feature Integration Network for Salient Object Detection in Optical Remote Sensing Images
  • ERPNet -> code for 2022 paper: Edge-guided Recurrent Positioning Network for Salient Object Detection in Optical Remote Sensing Images
  • FSMINet -> code for 2022 paper: Fully Squeezed Multi-Scale Inference Network for Fast and Accurate Saliency Detection in Optical Remote Sensing Images
  • AGNet -> code for 2022 paper: AGNet: Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images
  • MSCNet -> code for 2022 paper: A lightweight multi-scale context network for salient object detection in optical remote sensing images
  • GPnet -> code for 2022 paper: Global Perception Network for Salient Object Detection in Remote Sensing Images

Object detection - Buildings, rooftops & solar panels

Object detection - Ships & boats

Object detection - Cars, vehicles & trains

Object detection - Planes & aircraft

Object detection - Infrastructure & utilities

Object detection - Oil storage tank detection

Oil is stored in tanks at many points between extraction and sale, and the volume of oil in storage is an important economic indicator.

Object detection - Animals

A variety of techniques can be used to count animals, including object detection and instance segmentation. For convenience they are all listed here:

Object tracking in videos

Object counting

When the object count, but not its shape is required, U-net can be used to treat this as an image-to-image translation problem.

  • centroid-unet -> Centroid-UNet is deep neural network model to detect centroids from satellite images, with paper BEGINNER
  • cownter_strike -> counting cows, located with point-annotations, two models: CSRNet (a density-based method) & LCFCN (a detection-based method)
  • DO-U-Net -> an effective approach for when the size of an object needs to be known, as well as the number of objects in the image, initially created to segment and count Internally Displaced People (IDP) camps in Afghanistan
  • Cassava Crop Counting
  • Counting from Sky -> A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method
  • PSGCNet -> code for 2022 paper: PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing Images
  • psgcnet -> code for 2022 paper: PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote-Sensing Images

Regression

Cloud detection & removal

There are many algorithms that use band math to detect clouds, but the deep learning approach is to use semantic segmentation

Change detection

Generally speaking, change detection methods are applied to a pair of images to generate a mask of change, e.g. of buildings damaged in a disaster. Note, clouds & shadows change often too..!

  • awesome-remote-sensing-change-detection lists many datasets and publications
  • Change-Detection-Review -> A review of change detection methods, including code and open data sets for deep learning
  • Change Detection using Siamese Networks -> Medium article BEGINNER
  • STANet -> official implementation of the spatial-temporal attention neural network (STANet) for remote sensing image change detection BEGINNER
  • UNet-based-Unsupervised-Change-Detection -> A convolutional neural network (CNN) and semantic segmentation is implemented to detect the changes between the images, as well as classify the changes into the correct semantic class, with arxiv paper BEGINNER
  • BIT_CD -> Official Pytorch Implementation of Remote Sensing Image Change Detection with Transformers
  • Unstructured-change-detection-using-CNN
  • Siamese neural network to detect changes in aerial images -> uses Keras and VGG16 architecture
  • Change Detection in 3D: Generating Digital Elevation Models from Dove Imagery
  • QGIS plugin for applying change detection algorithms on high resolution satellite imagery
  • LamboiseNet -> Master thesis about change detection in satellite imagery using Deep Learning
  • Fully Convolutional Siamese Networks for Change Detection -> with paper
  • Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks -> with paper, used the Onera Satellite Change Detection (OSCD) dataset
  • IAug_CDNet -> Official Pytorch Implementation of Adversarial Instance Augmentation for Building Change Detection in Remote Sensing Images
  • dpm-rnn-public -> Code implementing a damage mapping method combining satellite data with deep learning
  • SenseEarth2020-ChangeDetection -> 1st place solution to the Satellite Image Change Detection Challenge hosted by SenseTime; predictions of five HRNet-based segmentation models are ensembled, serving as pseudo labels of unchanged areas
  • KPCAMNet -> Python implementation of the paper Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network
  • CDLab -> benchmarking deep learning-based change detection methods.
  • Siam-NestedUNet -> The pytorch implementation for "SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images"
  • SUNet-change_detection -> Implementation of paper SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network
  • Self-supervised Change Detection in Multi-view Remote Sensing Images
  • MFPNet -> Remote Sensing Change Detection Based on Multidirectional Adaptive Feature Fusion and Perceptual Similarity
  • GitHub for the DIUx xView Detection Challenge -> The xView2 Challenge focuses on automating the process of assessing building damage after a natural disaster
  • DASNet -> Dual attentive fully convolutional siamese networks for change detection of high-resolution satellite images
  • Self-Attention for Raw Optical Satellite Time Series Classification
  • planet-movement -> Find and process Planet image pairs to highlight object movement
  • temporal-cluster-matching -> detecting change in structure footprints from time series of remotely sensed imagery
  • autoRIFT -> fast and intelligent algorithm for finding the pixel displacement between two images
  • DSAMNet -> Code for “A Deeply Supervised Attention Metric-Based Network and an Open Aerial Image Dataset for Remote Sensing Change Detection”. The main types of changes in the dataset include: (a) newly built urban buildings; (b) suburban dilation; (c) groundwork before construction; (d) change of vegetation; (e) road expansion; (f) sea construction.
  • SRCDNet -> The pytorch implementation for "Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions ". SRCDNet is designed to learn and predict change maps from bi-temporal images with different resolutions
  • Land-Cover-Analysis -> Land Cover Change Detection using Satellite Image Segmentation
  • A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sening images
  • Satellite-Image-Alignment-Differencing-and-Segmentation -> thesis on change detection
  • Change Detection in Multi-temporal Satellite Images -> uses Principal Component Analysis (PCA) and K-means clustering
  • Unsupervised Change Detection Algorithm using PCA and K-Means Clustering -> in Matlab but has paper
  • ChangeFormer -> A Transformer-Based Siamese Network for Change Detection. Uses transformer architecture to address the limitations of CNN in handling multi-scale long-range details. Demonstrates that ChangeFormer captures much finer details compared to the other SOTA methods, achieving better performance on benchmark datasets
  • Heterogeneous_CD -> Heterogeneous Change Detection in Remote Sensing Images. Accompanies Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images
  • ChangeDetectionProject -> Trying out Active Learning in with deep CNNs for Change detection on remote sensing data
  • DSFANet -> Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
  • siamese-change-detection -> Targeted synthesis of multi-temporal remote sensing images for change detection using siamese neural networks
  • Bi-SRNet -> code for 2022 paper: Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
  • SiROC -> Implementation of the paper Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images. Applied to Sentinel-2 and high-resolution Planetscope imagery on four datasets
  • DSMSCN -> Tensorflow implementation for Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Neural Networks
  • RaVAEn -> a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment. It flags changed areas to prioritise for downlink, shortening the response time
  • SemiCD -> Code for paper: Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images. Achieves the performance of supervised CD even with access to as little as 10% of the annotated training data
  • FCCDN_pytorch -> code for paper: FCCDN: Feature Constraint Network for VHR Image Change Detection. Uses the LEVIR-CD building change detection dataset
  • INLPG_Python -> code for paper: Structure Consistency based Graph for Unsupervised Change Detection with Homogeneous and Heterogeneous Remote Sensing Images
  • NSPG_Python -> code for paper: Nonlocal patch similarity based heterogeneous remote sensing change detection
  • LGPNet-BCD -> code for 2021 paper: Building Change Detection for VHR Remote Sensing Images via Local-Global Pyramid Network and Cross-Task Transfer Learning Strategy
  • DS_UNet -> code for 2021 paper: Sentinel-1 and Sentinel-2 Data Fusion for Urban Change Detection using a Dual Stream U-Net, uses Onera Satellite Change Detection dataset
  • SiameseSSL -> code for 2022 paper: Urban change detection with a Dual-Task Siamese network and semi-supervised learning. Uses SpaceNet 7 dataset
  • CD-SOTA-methods -> Remote sensing change detection: State-of-the-art methods and available datasets
  • multimodalCD_ISPRS21 -> code for 2021 paper: Fusing Multi-modal Data for Supervised Change Detection
  • Unsupervised-CD-in-SITS-using-DL-and-Graphs -> code for article: Unsupervised Change Detection Analysis in Satellite Image Time Series using Deep Learning Combined with Graph-Based Approaches
  • LSNet -> code for 2022 paper: Extremely Light-Weight Siamese Network For Change Detection in Remote Sensing Image
  • Change-Detection-in-Remote-Sensing-Images -> using PCA & K-means
  • End-to-end-CD-for-VHR-satellite-image -> code for 2019 paper: End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++
  • Semantic-Change-Detection -> code for 2021 paper: SCDNET: A novel convolutional network for semantic change detection in high resolution optical remote sensing imagery
  • ERCNN-DRS_urban_change_monitoring -> code for 2021 paper: Neural Network-Based Urban Change Monitoring with Deep-Temporal Multispectral and SAR Remote Sensing Data
  • EGRCNN -> code for 2021 paper: Edge-guided Recurrent Convolutional Neural Network for Multi-temporal Remote Sensing Image Building Change Detection
  • Unsupervised-Remote-Sensing-Change-Detection -> code for 2021 paper: An Unsupervised Remote Sensing Change Detection Method Based on Multiscale Graph Convolutional Network and Metric Learning
  • CropLand-CD -> code for 2022 paper: A CNN-transformer Network with Multi-scale Context Aggregation for Fine-grained Cropland Change Detection
  • contrastive-surface-image-pretraining -> code for 2022 paper: Supervising Remote Sensing Change Detection Models with 3D Surface Semantics
  • dcvaVHROptical -> Deep Change Vector Analysis (DCVA) change detection. Code for 2019 paper: Unsupervised Deep Change Vector Analysis for Multiple-Change Detection in VHR Images
  • hyperdimensionalCD -> code for 2021 paper: Change Detection in Hyperdimensional Images Using Untrained Models
  • DSFANet -> code for 2018 paper: Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
  • FCD-GAN-pytorch -> Fully Convolutional Change Detection Framework with Generative Adversarial Network (FCD-GAN) is a framework for change detection in multi-temporal remote sensing images
  • DARNet-CD -> code for 2022 paper: A Densely Attentive Refinement Network for Change Detection Based on Very-High-Resolution Bitemporal Remote Sensing Images
  • xView2_Vulcan -> Damage assessment using pre and post orthoimagery. Modified + productionized model based off the first-place model from the xView2 challenge.
  • ESCNet -> code for 2021 paper: An End-to-End Superpixel-Enhanced Change Detection Network for Very-High-Resolution Remote Sensing Images
  • ForestCoverChange -> Detecting and Predicting Forest Cover Change in Pakistani Areas Using Remote Sensing Imagery
  • deforestation-detection -> code for 2020 paper: DEEP LEARNING FOR HIGH-FREQUENCY CHANGE DETECTION IN UKRAINIAN FOREST ECOSYSTEM WITH SENTINEL-2
  • forest_change_detection -> forest change segmentation with time-dependent models, including Siamese, UNet-LSTM, UNet-diff, UNet3D models. Code for 2021 paper: Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2
  • SentinelClearcutDetection -> Scripts for deforestation detection on the Sentinel-2 Level-A images
  • clearcut_detection -> research & web-service for clearcut detection
  • CDRL -> code for 2022 paper: Unsupervised Change Detection Based on Image Reconstruction Loss
  • ddpm-cd -> code for 2022 paper: Remote Sensing Change Detection (Segmentation) using Denoising Diffusion Probabilistic Models
  • Remote-sensing-time-series-change-detection -> code for 2022 paper: Graph-based block-level urban change detection using Sentinel-2 time series
  • austin-ml-change-detection-demo -> A change detection demo for the Austin area using a pre-trained PyTorch model scaled with Dask on Planet imagery
  • dfc2021-msd-baseline -> A baseline for the "Multitemporal Semantic Change Detection" track of the 2021 IEEE GRSS Data Fusion Competition
  • CorrFusionNet -> code for 2020 paper: Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion
  • ChangeDetectionPCAKmeans -> MATLAB implementation for Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and k-Means Clustering.
  • IRCNN -> code for 2022 paper: IRCNN: An Irregular-Time-Distanced Recurrent Convolutional Neural Network for Change Detection in Satellite Time Series
  • UTRNet -> An Unsupervised Time-Distance-Guided Convolutional Recurrent Network for Change Detection in Irregularly Collected Images
  • open-cd -> an open source change detection toolbox based on a series of open source general vision task tools
  • Tiny_model_4_CD -> code for 2022 paper: TINYCD: A (Not So) Deep Learning Model For Change Detection. Uses LEVIR-CD & WHU-CD datasets
  • FHD -> code for 2022 paper: Feature Hierarchical Differentiation for Remote Sensing Image Change Detection
  • Change detection with Raster Vision -> blog post with Colab notebook
  • building-expansion -> code for 2021 paper: Enhancing Environmental Enforcement with Near Real-Time Monitoring: Likelihood-Based Detection of Structural Expansion of Intensive Livestock Farms
  • SaDL_CD -> code for 2022 paper: Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection
  • EGCTNet_pytorch -> code for 2022 paper: Building Change Detection Based on an Edge-Guided Convolutional Neural Network Combined with a Transformer
  • S2-cGAN -> code for 2020 paper: S2-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images
  • A-loss-function-for-change-detection -> code for 2022 paper: UAL: Unchanged Area Loss-Function for Change Detection Networks

Time series

More general than change detection, time series observations can be used for applications including improving the accuracy of crop classification, or predicting future patterns & events. Crop yield is very typically application and has its own section below

  • CropDetectionDL -> using GRU-net, First place solution for Crop Detection from Satellite Imagery competition organized by CV4A workshop at ICLR 2020
  • LANDSAT Time Series Analysis for Multi-temporal Land Cover Classification using Random Forest
  • temporalCNN -> Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
  • pytorch-psetae -> PyTorch implementation of the model presented in Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention
  • satflow -> optical flow models for predicting future satellite images from current and past ones
  • esa-superresolution-forecasting -> Forecasting air pollution using ESA Sentinel-5p data, and an encoder-decoder convolutional LSTM neural network architecture, implemented in Pytorch
  • Radiant-Earth-Spot-the-Crop-Challenge -> The main objective of this challenge was to use time-series of Sentinel-2 multi-spectral data to classify crops in the Western Cape of South Africa. The challenge was to build a machine learning model to predict crop type classes for the test dataset
  • lightweight-temporal-attention-pytorch -> A PyTorch implementation of the Light Temporal Attention Encoder (L-TAE) for satellite image time series. classification
  • Crop-Classification -> crop classification using multi temporal satellite images
  • dtwSat -> Time-Weighted Dynamic Time Warping for satellite image time series analysis
  • DeepCropMapping -> A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping, uses LSTM
  • CropMappingInterpretation -> An interpretation pipeline towards understanding multi-temporal deep learning approaches for crop mapping
  • MTLCC -> code for paper: Multitemporal Land Cover Classification Network. A recurrent neural network approach to encode multi-temporal data for land cover classification
  • timematch -> code for 2022 paper: A method to perform unsupervised cross-region adaptation of crop classifiers trained with satellite image time series. We also introduce an open-access dataset for cross-region adaptation with SITS from four different regions in Europe
  • PWWB -> Code for the 2021 paper: Real-Time Spatiotemporal Air Pollution Prediction with Deep Convolutional LSTM through Satellite Image Analysis
  • Classification of Crop Fields through Satellite Image Time Series -> using a pytorch-psetae & Sentinel-2 data
  • spaceweather -> predicting geomagnetic storms from satellite measurements of the solar wind and solar corona, uses LSTMs
  • Forest_wildfire_spreading_convLSTM -> Modeling of the spreading of forest wildfire using a neural network with ConvLSTM cells. Prediction 3-days forward
  • ConvTimeLSTM -> Extension of ConvLSTM and Time-LSTM for irregularly spaced images, appropriate for Remote Sensing
  • dl-time-series -> Deep Learning algorithms applied to characterization of Remote Sensing time-series
  • tpe -> code for 2022 paper: Generalized Classification of Satellite Image Time Series With Thermal Positional Encoding
  • wildfire_forecasting -> code for 2021 paper: Deep Learning Methods for Daily Wildfire Danger Forecasting. Uses ConvLSTM
  • satellite_image_forecasting -> predict future satellite images from past ones using features such as precipitation and elevation maps. Entry for the EarthNet2021 challenge
  • Deep Learning for Cloud Gap-Filling on Normalized Difference Vegetation Index using Sentinel Time-Series -> A CNN-RNN based model that identifies correlations between optical and SAR data and exports dense Normalized Difference Vegetation Index (NDVI) time-series of a static 6-day time resolution and can be used for Events Detection tasks

Crop yield

Wealth and economic activity

The goal is to predict economic activity from satellite imagery rather than conducting labour intensive ground surveys

Disaster response

Also checkout the sections on change detection and water/fire/building segmentation

Super-resolution

Super-resolution attempts to enhance the resolution of an imaging system, and can be applied as a pre-processing step to improve the detection of small objects or boundaries. Its use is controversial since it can introduce artefacts at the same rate as real features. These techniques are generally grouped into single image super resolution (SISR) or a multi image super resolution (MISR)

Single image super-resolution (SISR)

Multi image super-resolution (MISR)

Note that nearly all the MISR publications resulted from the PROBA-V Super Resolution competition

  • deepsum -> Deep neural network for Super-resolution of Unregistered Multitemporal images (ESA PROBA-V challenge)
  • 3DWDSRNet -> code to reproduce Satellite Image Multi-Frame Super Resolution (MISR) Using 3D Wide-Activation Neural Networks
  • RAMS -> Official TensorFlow code for paper Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks
  • TR-MISR -> Transformer-based MISR framework for the the PROBA-V super-resolution challenge. With paper
  • HighRes-net -> Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin competition
  • ProbaVref -> Repurposing the Proba-V challenge for reference-aware super resolution
  • The missing ingredient in deep multi-temporal satellite image super-resolution -> Permutation invariance harnesses the power of ensembles in a single model, with repo piunet
  • MSTT-STVSR -> Space-time Super-resolution for Satellite Video: A Joint Framework Based on Multi-Scale Spatial-Temporal Transformer, JAG, 2022
  • Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites
  • DDRN -> Deep Distillation Recursive Network for Video Satellite Imagery Super-Resolution
  • worldstrat -> SISR and MISR implementations of SRCNN
  • MISR-GRU -> Pytorch implementation of MISR-GRU, a deep neural network for multi image super-resolution (MISR), for ProbaV Super Resolution Competition

Pansharpening

Image fusion of low res multispectral with high res pan band.

  • Several algorithms described in the ArcGIS docs, with the simplest being taking the mean of the pan and RGB pixel value.
  • For into to classical methods see this notebook and this kaggle kernel
  • rio-pansharpen -> pansharpening Landsat scenes
  • Simple-Pansharpening-Algorithms
  • Working-For-Pansharpening -> long list of pansharpening methods and update of Awesome-Pansharpening
  • PSGAN -> A Generative Adversarial Network for Remote Sensing Image Pan-sharpening, arxiv paper
  • Pansharpening-by-Convolutional-Neural-Network
  • PBR_filter -> {P}ansharpening by {B}ackground {R}emoval algorithm for sharpening RGB images
  • py_pansharpening -> multiple algorithms implemented in python
  • Deep-Learning-PanSharpening -> deep-learning based pan-sharpening code package, we reimplemented include PNN, MSDCNN, PanNet, TFNet, SRPPNN, and our purposed network DIPNet
  • HyperTransformer -> A Textural and Spectral Feature Fusion Transformer for Pansharpening
  • DIP-HyperKite -> Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
  • D2TNet -> code for 2022 paper: A ConvLSTM Network with Dual-direction Transfer for Pan-sharpening
  • PanColorGAN-VHR-Satellite-Images -> code for 2020 paper: Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANs
  • MTL_PAN_SEG -> code for 2019 paper: Multi-task deep learning for satellite image pansharpening and segmentation
  • Z-PNN -> code for 2022 paper: Pansharpening by convolutional neural networks in the full resolution framework
  • GTP-PNet -> code for 2021 paper: GTP-PNet: A residual learning network based on gradient transformation prior for pansharpening
  • UDL -> code for 2021 paper: Dynamic Cross Feature Fusion for Remote Sensing Pansharpening
  • PSData -> A Large-Scale General Pan-sharpening DataSet, which contains PSData3 (QB, GF-2, WV-3) and PSData4 (QB, GF-1, GF-2, WV-2).
  • AFPN -> Adaptive Detail Injection-Based Feature Pyramid Network For Pan-sharpening
  • pan-sharpening -> multiple methods demonstrated for multispectral and panchromatic images
  • PSGan-Family -> code for 2020 paper: PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
  • PanNet-Landsat -> code for 2017 paper: A Deep Network Architecture for Pan-Sharpening
  • DLPan-Toolbox -> code for 2022 paper: Machine Learning in Pansharpening: A Benchmark, from Shallow to Deep Networks
  • LPPN -> code for 2021 paper: Laplacian pyramid networks: A new approach for multispectral pansharpening
  • S2_SSC_CNN -> code for 2020 paper: Zero-shot Sentinel-2 Sharpening Using A Symmetric Skipped Connection Convolutional Neural Network
  • S2S_UCNN -> code for 2021 paper: Sentinel 2 sharpening using a single unsupervised convolutional neural network with MTF-Based degradation model
  • SSE-Net -> code for 2022 paper: Spatial and Spectral Extraction Network With Adaptive Feature Fusion for Pansharpening
  • UCGAN -> code for 2022 paper: Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening
  • GCPNet -> code for 2022 paper: When Pansharpening Meets Graph Convolution Network and Knowledge Distillation
  • PanFormer -> code for 2022 paper: PanFormer: a Transformer Based Model for Pan-sharpening
  • Pansharpening -> code for 2021 paper: Pansformers: Transformer-Based Self-Attention Network for Pansharpening

Image-to-image translation

Translate images e.g. from SAR to RGB.

GANS

GANS are famously used for generating synthetic data, see the section Synthetic data

Transformers

  • Transformer-in-Remote-Sensing -> code for 2022 paper: Transformers in Remote Sensing: A Survey
  • Remote-Sensing-RVSA -> code for 2022 paper: Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
  • SatViT -> self-supervised training of multispectral optical and SAR vision transformers
  • UDA_for_RS -> code for 2022 paper: Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation with Transformer

Adversarial ML

Efforts to detect falsified images & deepfakes. Also checkout Synthetic data

  • UAE-RS -> dataset that provides black-box adversarial samples in the remote sensing field
  • PSGAN -> code for paper: Perturbation Seeking Generative Adversarial Networks: A Defense Framework for Remote Sensing Image Scene Classification
  • SACNet -> code for 2021 paper: Self-Attention Context Network: Addressing the Threat of Adversarial Attacks for Hyperspectral Image Classification

Autoencoders, dimensionality reduction, image embeddings & similarity search

Image retreival

  • Demo_AHCL_for_TGRS2022 -> code for 2022 paper: Asymmetric Hash Code Learning (AHCL) for remote sensing image retreival
  • GaLR -> code for 2022 paper: Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
  • retrievalSystem -> cross-modal image retrieval system
  • AMFMN -> code for the 2021 paper: Exploring a Fine-grained Multiscale Method for Cross-modal Remote Sensing Image Retrieval
  • Active-Learning-for-Remote-Sensing-Image-Retrieval -> unofficial implementation of paper: A Novel Active Learning Method in Relevance Feedback for Content-Based Remote Sensing Image Retrieval
  • CMIR-NET -> code for 2020 paper: A deep learning based model for cross-modal retrieval in remote sensing
  • Deep-Hash-learning-for-Remote-Sensing-Image-Retrieval -> code for 2020 paper: Deep Hash Learning for Remote Sensing Image Retrieval
  • MHCLN -> code for 2018 paper: Deep Metric and Hash-Code Learning for Content-Based Retrieval of Remote Sensing Images
  • HydroViet_VOR -> Object Retrieval in satellite images with Triplet Network
  • AMFMN -> code for 2021 paper: Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval

Image Captioning & Visual Question Answering

Mixed data learning

These techniques combine multiple data types, e.g. imagery and text data.

Few-shot learning

This is a class of techniques which attempt to make predictions for classes with few, one or even zero examples provided during training. In zero shot learning (ZSL) the model is assisted by the provision of auxiliary information which typically consists of descriptions/semantic attributes/word embeddings for both the seen and unseen classes at train time (ref). These approaches are particularly relevant to remote sensing, where there may be many examples of common classes, but few or even zero examples for other classes of interest.

Self-supervised, unsupervised & contrastive learning

These techniques use unlabelled datasets. Yann LeCun has described self/unsupervised learning as the 'base of the cake': If we think of our brain as a cake, then the cake base is unsupervised learning. The machine predicts any part of its input for any observed part, all without the use of labelled data. Supervised learning forms the icing on the cake, and reinforcement learning is the cherry on top.

Weakly & semi-supervised learning

These techniques use a partially annotated dataset

  • MARE -> self-supervised Multi-Attention REsu-net for semantic segmentation in remote sensing
  • SSGF-for-HRRS-scene-classification -> code for 2018 paper: A semi-supervised generative framework with deep learning features for high-resolution remote sensing image scene classification
  • SFGAN -> code for 2018 paper: Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification
  • SSDAN -> code for 2021 paper: Multi-Source Semi-Supervised Domain Adaptation Network for Remote Sensing Scene Classification
  • HR-S2DML -> code for 2020 paper: High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery
  • Semantic Segmentation of Satellite Images Using Point Supervision
  • fcd -> code for 2021 paper: Fixed-Point GAN for Cloud Detection. A weakly-supervised approach, training with only image-level labels
  • weak-segmentation -> Weakly supervised semantic segmentation for aerial images in pytorch
  • TNNLS_2022_X-GPN -> Code for paper: Semisupervised Cross-scale Graph Prototypical Network for Hyperspectral Image Classification
  • weakly_supervised -> code for the paper Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery. Demonstrates that segmentation can be performed using small datasets comprised of pixel or image labels
  • wan -> Weakly-Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite Imagery, with arxiv paper
  • sourcerer -> A Bayesian-inspired deep learning method for semi-supervised domain adaptation designed for land cover mapping from satellite image time series (SITS). Paper
  • MSMatch -> Semi-Supervised Multispectral Scene Classification with Few Labels. Includes code to work with both the RGB and the multispectral (MS) versions of EuroSAT dataset and the UC Merced Land Use (UCM) dataset. Paper
  • Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning with arxiv paper
  • Semi-supervised learning in satellite image classification -> experimenting with MixMatch and the EuroSAT data set
  • ScRoadExtractor -> code for 2020 paper: Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images
  • ICSS -> code for 2022 paper: Weakly-supervised continual learning for class-incremental segmentation
  • es-CP -> code for 2022 paper: Semi-Supervised Hyperspectral Image Classification Using a Probabilistic Pseudo-Label Generation Framework

Active learning

Supervised deep learning techniques typically require a huge number of annotated/labelled examples to provide a training dataset. However labelling at scale take significant time, expertise and resources. Active learning techniques aim to reduce the total amount of annotation that needs to be performed by selecting the most useful images to label from a large pool of unlabelled images, thus reducing the time to generate useful training datasets. These processes may be referred to as Human-in-the-Loop Machine Learning

Federated learning

Federated learning is a process for training models in a distributed fashion without sharing of data

Image registration

Image registration is the process of registering one or more images onto another (typically well georeferenced) image. Traditionally this is performed manually by identifying control points (tie-points) in the images, for example using QGIS. This section lists approaches which mostly aim to automate this manual process. There is some overlap with the data fusion section but the distinction I make is that image registration is performed as a prerequisite to downstream processes which will use the registered data as an input.

Data fusion

Data fusion covers techniques which integrate multiple datasources, for example fusing SAR & optical to make predictions about crop type. It can also cover fusion with non imagery data such as IOT sensor data

  • Awesome-Data-Fusion-for-Remote-Sensing
  • UDALN_GRSL -> Deep Unsupervised Blind Hyperspectral and Multispectral Data Fusion
  • CropTypeMapping -> Crop type mapping from optical and radar (Sentinel-1&2) time series using attention-based deep learning
  • Multimodal-Remote-Sensing-Toolkit -> uses Hyperspectral and LiDAR Data
  • Aerial-Template-Matching -> development of an algorithm for template Matching on aerial imagery applied to UAV dataset
  • DS_UNet -> code for 2021 paper: Sentinel-1 and Sentinel-2 Data Fusion for Urban Change Detection using a Dual Stream U-Net, uses Onera Satellite Change Detection dataset
  • DDA_UrbanExtraction -> Unsupervised Domain Adaptation for Global Urban Extraction using Sentinel-1 and Sentinel-2 Data
  • swinstfm -> code for paper: Remote Sensing Spatiotemporal Fusion using Swin Transformer
  • LoveCS -> code for 2022 paper: Cross-sensor domain adaptation for high-spatial resolution urban land-cover mapping: from airborne to spaceborne imagery
  • comingdowntoearth -> code for 2021 paper: Implementation of 'Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization'
  • Matching between acoustic and satellite images
  • MapRepair -> Deep Cadastre Maps Alignment and Temporal Inconsistencies Fix in Satellite Images
  • Compressive-Sensing-and-Deep-Learning-Framework -> Compressive Sensing is used as an initial guess to combine data from multiple sources, with LSTM used to refine the result
  • DeepSim -> code for paper: DeepSIM: GPS Spoofing Detection on UAVs using Satellite Imagery Matching
  • MHF-net -> code for 2019 paper: Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
  • Remote_Sensing_Image_Fusion -> code for 2021 paper: Semi-Supervised Remote Sensing Image Fusion Using Multi-Scale Conditional Generative Adversarial network with Siamese Structure
  • CNNs for Multi-Source Remote Sensing Data Fusion -> code for 2021 paper: Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data
  • Deep Generative Reflectance Fusion -> Achieving Landsat-like reflectance at any date by fusing Landsat and MODIS surface reflectance with deep generative models
  • IEEE_TGRS_MDL-RS -> code for 2021 paper: More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification
  • SSRNET -> code for 2022 paper: SSR-NET: Spatial-Spectral Reconstruction Network for Hyperspectral and Multispectral Image Fusion
  • cross-view-image-matching -> code for 2019 paper: Bridging the Domain Gap for Ground-to-Aerial Image Matching
  • CoF-MSMG-PCNN -> code for 2020 paper: Remote Sensing Image Fusion via Boundary Measured Dual-Channel PCNN in Multi-Scale Morphological Gradient Domain
  • robust_matching_network_on_remote_sensing_imagery_pytorch -> code for 2019 paper: A Robust Matching Network for Gradually Estimating Geometric Transformation on Remote Sensing Imagery
  • edcstfn -> code for 2019 paper: An Enhanced Deep Convolutional Model for Spatiotemporal Image Fusion
  • ganstfm -> code for 2021 paper: A Flexible Reference-Insensitive Spatiotemporal Fusion Model for Remote Sensing Images Using Conditional Generative Adversarial Network
  • CMAFF -> code for 2021 paper: Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery
  • SOLC -> code for 2022 paper: MCANet: A joint semantic segmentation framework of optical and SAR images for land use classification. Uses WHU-OPT-SAR-dataset
  • MFT -> code for 2022 paper: Multimodal Fusion Transformer for Remote Sensing Image Classification
  • ISPRS_S2FL -> code for 2021 paper: Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model
  • HSHT-Satellite-Imagery-Synthesis -> code for thesis - Improving Flood Maps by Increasing the Temporal Resolution of Satellites Using Hybrid Sensor Fusion
  • MDC -> code for 2021 paper: Unsupervised Data Fusion With Deeper Perspective: A Novel Multisensor Deep Clustering Algorithm
  • FusAtNet -> code for 2020 paper: FusAtNet: Dual Attention based SpectroSpatial Multimodal Fusion Network for Hyperspectral and LiDAR Classification
  • AMM-FuseNet -> code for 2022 paper: AMM-FuseNet: Attention-Based Multi-Modal Image Fusion Network for Land Cover Mapping
  • S1-S2_Transformer -> Sentinel-1 SAR and Sentinel-2 optical timeseries based Transformer architecture for tropical dry forest disturbance mapping
  • MANet -> code for 2022 paper: MANet: A Network Architecture for Remote Sensing Spatiotemporal Fusion Based on Multiscale and Attention Mechanisms
  • DCSA-Net -> code for 2022 paper: Dynamic Convolution Self-Attention Network for Land-Cover Classification in VHR Remote-Sensing Images

Terrain mapping, Disparity Estimation, Lidar, DEMs & NeRF

Measure surface contours & locate 3D points in space from 2D images. NeRF stands for Neural Radiance Fields and is the term used in deep learning communities to describe a model that generates views of complex 3D scenes based on a partial set of 2D images

Thermal Infrared

SAR

NDVI - vegetation index

General image quality

  • Convolutional autoencoder network can be employed to image denoising, read about this on the Keras blog
  • jitter-compensation -> Remote Sensing Image Jitter Detection and Compensation Using CNN
  • DeblurGANv2 -> Deblurring (Orders-of-Magnitude) Faster and Better
  • image-quality-assessment -> CNN to predict the aesthetic and technical quality of images
  • Convolutional autoencoder for image denoising -> keras guide
  • piq -> a collection of measures and metrics for image quality assessment
  • FFA-Net -> Feature Fusion Attention Network for Single Image Dehazing
  • DeepCalib -> A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras
  • PerceptualSimilarity -> LPIPS is a perceptual metric which aims to overcome the limitations of traditional metrics such as PSNR & SSIM, to better represent the features the human eye picks up on
  • Optical-RemoteSensing-Image-Resolution -> code for 2018 paper: Deep Memory Connected Neural Network for Optical Remote Sensing Image Restoration. Two applications: Gaussian image denoising and single image super-resolution
  • Hyperspectral-Deblurring-and-Destriping
  • HyDe -> Hyperspectral Denoising algorithm toolbox in Python, with paper
  • HLF-DIP -> code for 2022 paper: Unsupervised Hyperspectral Denoising Based on Deep Image Prior and Least Favorable Distribution
  • RQUNetVAE -> code for 2022 paper: Riesz-Quincunx-UNet Variational Auto-Encoder for Satellite Image Denoising
  • deep-hs-prior -> code for 2019 paper: Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution
  • iquaflow -> from Satellogic, an image quality framework that aims at providing a set of tools to assess image quality by using the performance of AI models trained on the images as a proxy.

Synthetic data

Training data can be hard to acquire, particularly for rare events such as change detection after disasters, or imagery of rare classes of objects. In these situations, generating synthetic training data might be the only option. This has become quite sophisticated, with 3D models being use with open source games engines such as Unreal.

Deep learning projects & frameworks

  • TorchGeo -> a PyTorch domain library providing datasets, samplers, transforms, and pre-trained models specific to geospatial data, supported by Microsoft. Read Geospatial deep learning with TorchGeo
  • rastervision -> An open source Python framework for building computer vision models on aerial, satellite, and other large imagery sets
  • geotorch -> A Deep Learning and Scalable Data Processing Framework for Raster and Spatio-Temporal Datasets
  • torchrs -> PyTorch implementation of popular datasets and models in remote sensing tasksenhance) -> Enhance PyTorch vision for semantic segmentation, multi-channel images and TIF file
  • DeepHyperX -> A Python/pytorch tool to perform deep learning experiments on various hyperspectral datasets
  • DELTA -> Deep Earth Learning, Tools, and Analysis, by NASA is a framework for deep learning on satellite imagery, based on Tensorflow & using MLflow for tracking experiments
  • Lightly is a computer vision framework for training deep learning models using self-supervised learning
  • Icevision offers a curated collection of hundreds of high-quality pre-trained models within an easy to use framework
  • pytorch_eo -> aims to make Deep Learning for Earth Observation data easy and accessible to real-world cases and research alike
  • NGVEO -> applying convolutional neural networks (CNN) to Earth Observation (EO) data from Sentinel 1 and 2 using python and PyTorch
  • chip-n-scale-queue-arranger by developmentseed -> an orchestration pipeline for running machine learning inference at scale. Supports fastai models
  • http://spaceml.org/ -> A Machine Learning toolbox and developer community building the next generation AI applications for space science and exploration
  • TorchSat is an open-source deep learning framework for satellite imagery analysis based on PyTorch (no activity since June 2020)
  • DeepNetsForEO -> Uses SegNET for working on remote sensing images using deep learning (no activity since 2019)
  • RoboSat -> semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds (no longer maintained)
  • DeepOSM -> Train a deep learning net with OpenStreetMap features and satellite imagery (no activity since 2017)
  • mapwith.ai -> AI assisted mapping of roads with OpenStreetMap. Part of Open-Mapping-At-Facebook
  • SAHI -> Python library for slicing image datasets, performing sliced inference with MMDetection, Detectron2, YOLOv5, Torchvision detectors and generating error analysis plots. Read the arxiv paper and article SAHI: A vision library for large-scale object detection & instance segmentation
  • terragpu -> Python library to process and classify remote sensing imagery by means of GPUs and AI/ML
  • EOTorchLoader -> Pytorch dataloader and pytorch lightning datamodule for Earth Observation imagery
  • satellighte -> an image classification library that consist state-of-the-art deep learning methods, using PyTorch Lightning
  • aeronetlib -> Python library to work with geospatial raster and vector data for deep learning
  • rsi-semantic-segmentation -> A unified PyTorch framework for semantic segmentation from remote sensing imagery
  • AiTLAS -> implements state-of-the-art AI methods for exploratory and predictive analysis of satellite images
  • mmsegmentation -> Semantic Segmentation Toolbox with support for many remote sensing datasets including LoveDA , Potsdam, Vaihingen & iSAID
  • ODEON landcover -> a set of command-line tools performing semantic segmentation on remote sensing images (aerial and/or satellite) with as many layers as you wish
  • aitlas-arena -> An open-source benchmark framework for evaluating state-of-the-art deep learning approaches for image classification in Earth Observation (EO)
  • PaddleRS -> remote sensing image processing development kit
  • RocketML Deep Neural Networks -> read Satellite Image Classification using rmldnn and Sentinel 2 data
  • segmentation_gym -> A neural gym for training deep learning models to carry out geoscientific image segmentation
  • EarthNets -> includes a database of 400 baseline models, and tutorial examples of common deep learning tasks on satellite imagery. Accompanied by a paper: EarthNets: Empowering AI in Earth Observation
  • raster4ml -> A geospatial raster processing library for machine learning

Neural nets in space

Processing on board a satellite allows less data to be downlinked. e.g. super-resolution image might take 8 images to generate, then a single image is downlinked. Other applications include cloud detection and collision avoidance.

Courses

Podcasts

Newsletters

Books



Download Details:

Author: robmarkcole
Source Code: https://github.com/robmarkcole/satellite-image-deep-learning 
License: Apache-2.0 license

#machinelearning #python #deeplearning 

What is GEEK

Buddha Community

Deep Learning with Satellite & Aerial Imagery
Marget D

Marget D

1618317562

Top Deep Learning Development Services | Hire Deep Learning Developer

View more: https://www.inexture.com/services/deep-learning-development/

We at Inexture, strategically work on every project we are associated with. We propose a robust set of AI, ML, and DL consulting services. Our virtuoso team of data scientists and developers meticulously work on every project and add a personalized touch to it. Because we keep our clientele aware of everything being done associated with their project so there’s a sense of transparency being maintained. Leverage our services for your next AI project for end-to-end optimum services.

#deep learning development #deep learning framework #deep learning expert #deep learning ai #deep learning services

Mikel  Okuneva

Mikel Okuneva

1603735200

Top 10 Deep Learning Sessions To Look Forward To At DVDC 2020

The Deep Learning DevCon 2020, DLDC 2020, has exciting talks and sessions around the latest developments in the field of deep learning, that will not only be interesting for professionals of this field but also for the enthusiasts who are willing to make a career in the field of deep learning. The two-day conference scheduled for 29th and 30th October will host paper presentations, tech talks, workshops that will uncover some interesting developments as well as the latest research and advancement of this area. Further to this, with deep learning gaining massive traction, this conference will highlight some fascinating use cases across the world.

Here are ten interesting talks and sessions of DLDC 2020 that one should definitely attend:

Also Read: Why Deep Learning DevCon Comes At The Right Time


Adversarial Robustness in Deep Learning

By Dipanjan Sarkar

**About: **Adversarial Robustness in Deep Learning is a session presented by Dipanjan Sarkar, a Data Science Lead at Applied Materials, as well as a Google Developer Expert in Machine Learning. In this session, he will focus on the adversarial robustness in the field of deep learning, where he talks about its importance, different types of adversarial attacks, and will showcase some ways to train the neural networks with adversarial realisation. Considering abstract deep learning has brought us tremendous achievements in the fields of computer vision and natural language processing, this talk will be really interesting for people working in this area. With this session, the attendees will have a comprehensive understanding of adversarial perturbations in the field of deep learning and ways to deal with them with common recipes.

Read an interview with Dipanjan Sarkar.

Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER

By Divye Singh

**About: **Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER is a paper presentation by Divye Singh, who has a masters in technology degree in Mathematical Modeling and Simulation and has the interest to research in the field of artificial intelligence, learning-based systems, machine learning, etc. In this paper presentation, he will talk about the common problem of class imbalance in medical diagnosis and anomaly detection, and how the problem can be solved with a deep learning framework. The talk focuses on the paper, where he has proposed a synergistic over-sampling method generating informative synthetic minority class data by filtering the noise from the over-sampled examples. Further, he will also showcase the experimental results on several real-life imbalanced datasets to prove the effectiveness of the proposed method for binary classification problems.

Default Rate Prediction Models for Self-Employment in Korea using Ridge, Random Forest & Deep Neural Network

By Dongsuk Hong

About: This is a paper presentation given by Dongsuk Hong, who is a PhD in Computer Science, and works in the big data centre of Korea Credit Information Services. This talk will introduce the attendees with machine learning and deep learning models for predicting self-employment default rates using credit information. He will talk about the study, where the DNN model is implemented for two purposes — a sub-model for the selection of credit information variables; and works for cascading to the final model that predicts default rates. Hong’s main research area is data analysis of credit information, where she is particularly interested in evaluating the performance of prediction models based on machine learning and deep learning. This talk will be interesting for the deep learning practitioners who are willing to make a career in this field.


#opinions #attend dldc 2020 #deep learning #deep learning sessions #deep learning talks #dldc 2020 #top deep learning sessions at dldc 2020 #top deep learning talks at dldc 2020

Few Shot Learning — A Case Study (2)

In the previous blog, we looked into the fact why Few Shot Learning is essential and what are the applications of it. In this article, I will be explaining the Relation Network for Few-Shot Classification (especially for image classification) in the simplest way possible. Moreover, I will be analyzing the Relation Network in terms of:

  1. Effectiveness of different architectures such as Residual and Inception Networks
  2. Effects of transfer learning via using pre-trained classifier on ImageNet dataset

Moreover, effectiveness will be evaluated on the accuracy, time required for training, and the number of required training parameters.

Please watch the GitHub repository to check out the implementations and keep updated with further experiments.

Introduction to Few-Shot Classification

In few shot classification, our objective is to design a method which can identify any object images by analyzing few sample images of the same class. Let’s the take one example to understand this. Suppose Bob has a client project to design a 5 class classifier, where 5 classes can be anything and these 5 classes can even change with time. As discussed in previous blog, collecting the huge amount of data is very tedious task. Hence, in such cases, Bob will rely upon few shot classification methods where his client can give few set of example images for each classes and after that his system can perform classification young these examples with or without the need of additional training.

In general, in few shot classification four terminologies (N way, K shot, support set, and query set) are used.

  1. N way: It means that there will be total N classes which we will be using for training/testing, like 5 classes in above example.
  2. K shot: Here, K means we have only K example images available for each classes during training/testing.
  3. Support set: It represents a collection of all available K examples images from each classes. Therefore, in support set we have total N*K images.
  4. Query set: This set will have all the images for which we want to predict the respective classes.

At this point, someone new to this concept will have doubt regarding the need of support and query set. So, let’s understand it intuitively. Whenever humans sees any object for the first time, we get the rough idea about that object. Now, in future if we see the same object second time then we will compare it with the image stored in memory from the when we see it for the first time. This applied to all of our surroundings things whether we see, read, or hear. Similarly, to recognise new images from query set, we will provide our model a set of examples i.e., support set to compare.

And this is the basic concept behind Relation Network as well. In next sections, I will be giving the rough idea behind Relation Network and I will be performing different experiments on 102-flower dataset.

About Relation Network

The Core idea behind Relation Network is to learn the generalized image representations for each classes using support set such that we can compare lower dimensional representation of query images with each of the class representations. And based on this comparison decide the class of each query images. Relation Network has two modules which allows us to perform above two tasks:

  1. Embedding module: This module will extract the required underlying representations from each input images irrespective of the their classes.
  2. Relation Module: This module will score the relation of embedding of query image with each class embedding.

Training/Testing procedure:

We can define the whole procedure in just 5 steps.

  1. Use the support set and get underlying representations of each images using embedding module.
  2. Take the average of between each class images and get the single underlying representation for each class.
  3. Then get the embedding for each query images and concatenate them with each class’ embedding.
  4. Use the relation module to get the scores. And class with highest score will be the label of respective query image.
  5. [Only during training] Use MSE loss functions to train both (embedding + relation) modules.

Few things to know during the training is that we will use only images from the set of selective class, and during the testing, we will be using images from unseen classes. For example, from the 102-flower dataset, we will use 50% classes for training, and rest will be used for validation and testing. Moreover, in each episode, we will randomly select 5 classes to create the support and query set and follow the above 5 steps.

That is all need to know about the implementation point of view. Although the whole process is simple and easy to understand, I’ll recommend reading the published research paper, Learning to Compare: Relation Network for Few-Shot Learning, for better understanding.

#deep-learning #few-shot-learning #computer-vision #machine-learning #deep learning #deep learning

Tia  Gottlieb

Tia Gottlieb

1595573880

Deep Reinforcement Learning for Video Games Made Easy

In this post, we will investigate how easily we can train a Deep Q-Network (DQN) agent (Mnih et al., 2015) for Atari 2600 games using the Google reinforcement learning library Dopamine. While many RL libraries exist, this library is specifically designed with four essential features in mind:

  • Easy experimentation
  • Flexible development
  • Compact and reliable
  • Reproducible

_We believe these principles makes __Dopamine _one of the best RL learning environment available today. Additionally, we even got the library to work on Windows, which we think is quite a feat!

In my view, the visualization of any trained RL agent is an absolute must in reinforcement learning! Therefore, we will (of course) include this for our own trained agent at the very end!

We will go through all the pieces of code required (which is** minimal compared to other libraries**), but you can also find all scripts needed in the following Github repo.

1. Brief Introduction to Reinforcement Learning and Deep Q-Learning

The general premise of deep reinforcement learning is to

“derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations.”

  • Mnih et al. (2015)

As stated earlier, we will implement the DQN model by Deepmind, which only uses raw pixels and game score as input. The raw pixels are processed using convolutional neural networks similar to image classification. The primary difference lies in the objective function, which for the DQN agent is called the optimal action-value function

Image for post

where_ rₜ is the maximum sum of rewards at time t discounted by γ, obtained using a behavior policy π = P(a_∣_s)_ for each observation-action pair.

There are relatively many details to Deep Q-Learning, such as Experience Replay (Lin, 1993) and an _iterative update rule. _Thus, we refer the reader to the original paper for an excellent walk-through of the mathematical details.

One key benefit of DQN compared to previous approaches at the time (2015) was the ability to outperform existing methods for Atari 2600 games using the same set of hyperparameters and only pixel values and game score as input, clearly a tremendous achievement.

2. Installation

This post does not include instructions for installing Tensorflow, but we do want to stress that you can use both the CPU and GPU versions.

Nevertheless, assuming you are using Python 3.7.x, these are the libraries you need to install (which can all be installed via pip):

tensorflow-gpu=1.15   (or tensorflow==1.15  for CPU version)
cmake
dopamine-rl
atari-py
matplotlib
pygame
seaborn
pandas

#reinforcement-learning #q-learning #games #machine-learning #deep-learning #deep learning

Learn Transfer Learning for Deep Learning by implementing the project.

Project walkthrough on Convolution neural networks using transfer learning

From 2 years of my master’s degree, I found that the best way to learn concepts is by doing the projects. Let’s start implementing or in other words learning.

Problem Statement

Take an image as input and return a corresponding dog breed from 133 dog breed categories. If a dog is detected in the image, it will provide an estimate of the dog’s breed. If a human is detected, it will give an estimate of the dog breed that is most resembling the human face. If there’s no human or dog present in the image, we simply print an error.

Let’s break this problem into steps

  1. Detect Humans
  2. Detect Dogs
  3. Classify Dog breeds

For all these steps, we use pre-trained models.

Pre-trained models are saved models that were trained on a huge image-classification task such as Imagenet. If these datasets are huge and generalized enough, the saved weights can be used for multiple image detection task to get a high accuracy quickly.

Detect Humans

For detecting humans, OpenCV provides many pre-trained face detectors. We use OpenCV’s implementation of Haar feature-based cascade classifiers to detect human faces in images.

### returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0

Image for post

Detect Dogs

For detecting dogs, we use a pre-trained ResNet-50 model to detect dogs in images, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks.

from keras.applications.resnet50 import ResNet50

### define ResNet50 model
ResNet50_model_detector = ResNet50(weights='imagenet')
### returns "True" if a dog is detected
def dog_detector(img_path):
    prediction = ResNet50_predict_labels(img_path)
    return ((prediction <= 268) & (prediction >= 151))

Classify Dog Breeds

For classifying Dog breeds, we use transfer learning

Transfer learning involves taking a pre-trained neural network and adapting the neural network to a new, different data set.

To illustrate the power of transfer learning. Initially, we will train a simple CNN with the following architecture:

Image for post

Train it for 20 epochs, and it gives a test accuracy of just 3% which is better than a random guess from 133 categories. But with more epochs, we can increase accuracy, but it takes up a lot of training time.

To reduce training time without sacrificing accuracy, we will train the CNN model using transfer learning.

#data-science #transfer-learning #project-based-learning #cnn #deep-learning #deep learning