利用计算机视觉搜寻未收集的垃圾
Searching for Uncollected Litter with Computer Vision
AI总结：
本文提出结合照片元数据与计算机视觉检测未收集垃圾，利用 TACO 数据集训练算法识别 10 类垃圾，并指出增加视角与背景多样性可提升车载图像处理能力，最终将结果映射到地图以支持废弃物管理策略评估。
摘要：
本研究结合照片元数据与计算机视觉，量化未收集垃圾的分布位置。使用 Trash Annotations in Context（TACO）数据集中的图像训练算法，以检测 10 类垃圾。尽管该算法在处理智能手机照片时表现良好，但在处理车载摄像头图像时遇到困难。然而，增加数据集中视角和背景的多样性将有助于其在陌生场景下改进表现。这些数据被绘制到地图上，随着准确率的提高，可用于衡量废弃物管理策略并量化趋势。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
