Saved in:
Bibliographic Details
Main Authors: Hernandez, Julian, Fitzgerald, Clark
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.14743
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910582573105152
author Hernandez, Julian
Fitzgerald, Clark
author_facet Hernandez, Julian
Fitzgerald, Clark
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2211_14743
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Searching for Uncollected Litter with Computer Vision
Hernandez, Julian
Fitzgerald, Clark
Computer Vision and Pattern Recognition
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.
title Searching for Uncollected Litter with Computer Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.14743