We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation. The results of the above steps are further integrated into a densely connected conditional random field that learns to respect the appearance, depth, and spatial affinities with pixel-level accuracy. In addition, we create a new RGBD waste object segmentation dataset, MJU-Waste, that is made public to facilitate future research in this area. The efficacy of our method is validated on both MJU-Waste and the Trash Annotation in Context (TACO) dataset.

中文翻译：

---

废物分类的多层次方法。

我们解决了从彩色​​图像和可选的深度图像中定位废品的问题，这是机器人与此类对象进行交互的关键感知组件。具体来说，我们的方法在多个空间粒度级别上集成了强度和深度信息。首先，场景级深度网络会产生初始的粗略分割，在此基础上，我们选择一些潜在的对象区域进行放大并执行精细分割。上述步骤的结果进一步集成到一个紧密连接的条件随机字段中，该条件随机字段学习以像素级精度尊重外观，深度和空间亲和力。此外，我们创建了一个新的RGBD废物对象分割数据集MJU-Waste，该数据集已公开，以促进该领域的未来研究。