UniDataPro/outdoor-garbage

该数据集包含5000多张在不同户外环境、不同时间和多样天气条件下拍摄的垃圾桶图像。这个广泛的收集旨在研究废物分类和检测方法，研究人员可以在深度学习和机器学习应用方面提升能力，特别是在图像识别和实例分割领域。通过利用这个数据集，研究人员可以增强推荐系统，优化流程，并自动化智能城市中的社区服务操作。数据集中的每张图像都附带有XML注释，提供关于垃圾桶类型及其容量（满、空或散乱）的详细信息。该数据集对于开发和测试现实场景中的分割模型和检测性能特别有价值。

The dataset comprises over 5,000 images of trash cans captured in various outdoor environments and under diverse weather conditions, designed for research in waste classification and detection methods. Each image is accompanied by an XML annotation file providing detailed information about the types of trash bins and their respective capacities, such as full, empty, or scattered. This dataset is particularly valuable for developing and testing segmentation models and detection performances in real-world scenarios.