A Multi-Level Approach to Waste Object Segmentation
This work addresses waste object segmentation for robotic interaction, presenting an incremental improvement with a new dataset.
The paper tackles waste object segmentation from RGBD images by integrating intensity and depth information at multiple spatial levels, achieving pixel-level accuracy through a coarse-to-fine approach and a conditional random field. It validates the method on a new MJU-Waste dataset and the TACO dataset, though no specific performance numbers are provided.
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.