# Searching for Uncollected Litter with Computer Vision

arXiv: https://arxiv.org/abs/2211.14743 · HTML: https://mlsanity.com/paper/2211.14743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 27 Nov 2022.

## Builds on (most cited first, 5 of 5)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [TACO: Trash Annotations in Context for Litter Detection](https://mlsanity.com/paper/2003.06975/) (2020)
- [Deep Learning Based Robot for Automatically Picking up Garbage on the Grass](https://mlsanity.com/paper/1904.13034/) (2019)

## Abstract (arXiv)

This study combines photo metadata and computer vision to quantify where uncollected litter is present. Images from the Trash Annotations in Context (TACO) dataset were used to teach an algorithm to detect 10 categories of garbage. Although it worked well with smartphone photos, it struggled when trying to process images from vehicle mounted cameras. However, increasing the variety of perspectives and backgrounds in the dataset will help it improve in unfamiliar situations. These data are plotted onto a map which, as accuracy improves, could be used for measuring waste management strategies and quantifying trends.