Drinking Waste Dataset

This Drinking Waste Dataset was manually labelled and collected as a part of author final year Individual Project at University College London. Pictures were taken with 12 MP phone camera. He created a real-time waste detection and identification system powered by YOLO framework. The dataset used images from Trashnet classification dataset.本饮酒废弃物数据集系由伦敦大学学院作者在毕业设计阶段亲手标注与搜集而成。图像均采用具备1200万像素的智能手机相机拍摄。作者构建了一套基于YOLO框架的实时废弃物检测与识别系统。该数据集采用了来自Trashnet分类数据集的图像。

搜集汇总

背景与挑战

背景概述

Drinking Waste Dataset是一个用于目标检测的数据集，专注于环境行业中的饮料废弃物识别。它包含4816张图像和5058个标注对象，覆盖塑料瓶、玻璃瓶、铝罐和塑料奶瓶四类常见废弃物，所有图像均带有边界框标注，但未划分训练/验证/测试集。该数据集于2023年发布，采用CC0 1.0许可证，适用于开发实时废弃物检测系统。