\Neural Network for Oriented-Object-Detection in Aerial Images

\Neural Network for Oriented-Object-Detection in Aerial Images

Researchers at Rutgers University have proposed a network architecture that predicts the directional boundaries of objects in aerial images.

Description of the problem

Oriented object recognition in aerial images is an open task because objects in such images are densely packed and can be directed in any direction. Existing methods for oriented object recognition mainly rely on two-stage detectors, which are based on the idea of ​​anchors. The limitation of such detectors is the problem of imbalance of object boundaries for positive and negative anchors. To solve this problem, the researchers propose to extend the horizontal keypoints detector for the task of oriented object recognition.

Image for post

Oriented bounding box (OBB) descriptions for (a) baseline method, (b) the proposed method, (c) illustrates the corner cases where the vectors are very close to the XY-axes. Source: Arxiv

Model architecture

The architecture of the model is based on a U-shaped network. The model first recognizes the central key points of the objects. Based on these center points, directional vectors (BBAVectors) are then predicted that capture the oriented object boundaries. BBAVectors are distributed in four quadrants, as in the Cartesian coordinate system. To facilitate the task of training vectors for edge cases, oriented object boundaries are then classified as horizontal or rotating.

artificial-intelligence machine-learning data-science deep-learning ai deep learning

Bootstrap 5 Complete Course with Examples

Bootstrap 5 Tutorial - Bootstrap 5 Crash Course for Beginners

Nest.JS Tutorial for Beginners

Hello Vue 3: A First Look at Vue 3 and the Composition API

Building a simple Applications with Vue 3

Deno Crash Course: Explore Deno and Create a full REST API with Deno

How to Build a Real-time Chat App with Deno and WebSockets

Convert HTML to Markdown Online

HTML entity encoder decoder Online

Artificial Intelligence (AI) vs Machine Learning vs Deep Learning vs Data Science

Artificial Intelligence (AI) vs Machine Learning vs Deep Learning vs Data Science: Artificial intelligence is a field where set of techniques are used to make computers as smart as humans. Machine learning is a sub domain of artificial intelligence where set of statistical and neural network based algorithms are used for training a computer in doing a smart task. Deep learning is all about neural networks. Deep learning is considered to be a sub field of machine learning. Pytorch and Tensorflow are two popular frameworks that can be used in doing deep learning.

Artificial Intelligence vs. Machine Learning vs. Deep Learning

Simple explanations of Artificial Intelligence, Machine Learning, and Deep Learning and how they’re all different

Difference between Machine Learning, Data Science, AI, Deep Learning, and Statistics

In this article, I clarify the various roles of the data scientist, and how data science compares and overlaps with related fields such as machine learning, deep learning, AI, statistics, IoT, operations research, and applied mathematics.

Most popular Data Science and Machine Learning courses — July 2020

Most popular Data Science and Machine Learning courses — August 2020. This list was last updated in August 2020 — and will be updated regularly so as to keep it relevant

AI(Artificial Intelligence): The Business Benefits of Machine Learning

Enroll now at CETPA, the best Institute in India for Artificial Intelligence Online Training Course and Certification for students & working professionals & avail 50% instant discount.