Water Quality Assessment Using Visual Sensors

Mohbat Tharani, Abdul Wahab Amin, Fezan Rasool, Muhammad Maaz, Murtaza Taj, Abubakr Muhammad

Summary

In the absence of an effective trash management framework, trash is often illegally dumped in rivers and canals running through urban areas, contaminating freshwater and blocking drainage lines which result in urban floods. When this contaminated water reaches agricultural fields, it results in the degradation of soil and poses critical environmental as well as economic threats. In this research, we aim to devise an automated vision-based approach to detect, classify and quantify the trash present in canals and drains which would eventually assist the government and policymakers to take appropriate steps.

IoT-based Camera Node

IoT and AI-based Trash Skimmer Boat

Resources

Preliminary dataset with 2000 images: Download
Object Detection Dataset: Download
Segmentation Dataset: Download
Code repository: Github
Slides: Wahab’s Thesis, Fezan’s Thesis

 If you happen to use the data set, please refer to the following paper:

Text Reference:

Mohbat Tharani, Abdul Wahab Amin, Fezan Rasool, Muhammad Maaz, Murtaza Taj,
"Trash Detection on Water Channels", 
https://arxiv.org/abs/2007.04639, 2020

Bibtex Reference:

@inproceedings{TharaniArxiv2020,
   author   = "Mohbat Tharani and
               Abdul Wahab Amin and
               Fezan Rasool and 
               Muhammad Maaz and 
               Murtaza Taj",
               Abubakr Muhammmad
   title     = "Trash Detection on Water Channels",    
   booktitle = "ICONIP",    
   month = "Dec",
   year = "2021", }