Underwater Trash Detection using Opensource Monk Toolkit

Underwater Trash Detection using Opensource Monk Toolkit: Train a machine vision engine that detects marine waste debris in videos captured by underwater autonomous robots.

Underwater Waste is a huge environmental problem affecting aquatic habitat drastically. Marine debris includes plastic, non-bio-degradable industrial waste, sewage sludge, radioactive material dumps, etc.

As per the statistics published at Condor Ferries

★ More than 100K marine animals die due to plastic waste

★ It is estimated that around 5.25 trillion plastic pieces exist in our oceans

★ 70 % of waste debris sinks in the ocean, around 15% floats, and the rest is washed ashore.

The great pacific garbage patch, also known as pacific trash vortex spans around 617K miles between Hawaii and California. And this is still a small part of the entire marine pollution.

To tackle this issue a lot of initiatives are being taken up like

▹ The OceanCleanUp Project

▹ Clean Ocean Project

▹ Seabin Project

… And many more!

A crucial part of these projects is the use of robots

★ to clean up the larger areas in a shorter period as compared to manual cleanup drives.

★ to access areas where human divers cannot reach

Robotic crab bot for plastic removal from ocean beds. Credits

A critical component for these robots is to identify different objects and take actions accordingly and this is where Deep Learning and Machine Vision enters the space!!!

About the Dataset and the Library

Let’s dive in and add a minimalistic contribution as deep learning engineers to make this world a better place

To create a detector we used Trash-ICRA19** Dataset**

• Contains 5K+ Training images and 1K+ Test Images

• Data was sourced from the_ J-EDI dataset of marine debris_

• The dataset is labeled with bounding box annotations over trash as well as marine life. (For simplicity we train only over trash data)

low-code trash object-detection computer-vision marine visual studio code

Explains how to find ulimit values of currently running process or given user account under Linux using the 'ulimit -a' builtin command.

Mit dem integrierten Debugger von Visual Studio Code lassen sich ASP.NET Core bzw. .NET Core Applikationen einfach und problemlos debuggen. Der Debugger unterstützt auch Remote Debugging, somit lassen sich zum Beispiel .NET Core Programme, die in einem Docker-Container laufen, debuggen.

Während der Entwicklung lassen sich Performanceprobleme bei ASP.NET Applikationen relativ einfach mit dem integrierten Profiler von Visual Studio 2015 analysieren.

MEAN Stack Tutorial MongoDB ExpressJS AngularJS NodeJS - We are going to build a full stack Todo App using the MEAN (MongoDB, ExpressJS, AngularJS and NodeJS). This is the last part of three-post series tutorial.

Creating RESTful APIs with NodeJS and MongoDB Tutorial - Welcome to this tutorial about RESTful API using Node.js (Express.js) and MongoDB (mongoose)! We are going to learn how to install and use each component individually and then proceed to create a RESTful API.