Part segmentation from stereo

This article addresses the problem of segmenting objects into parts using stereo images. There are three components in the part segmentation process: surface segmentation, region grouping, and volumetric models (superquadrics) recovery/segmentation. The surface segmentation process segments the image into a set of regions such that each region represents a smooth surface. The region grouping process merges the segmented regions into parts. Finally the process of volumetric models recovery/segmentation recovers the part model and segments that part into smaller parts if necessary. Because we use both surface and volumetric models to drive the part segmentation process, we can capture more geometric properties of the object, and the application domain of our approach is broader than that of previous approaches. The performance of the proposed system is demonstrated with real images and synthetic images. Experimental results show that the system is stable and capable of handling a variety of objects.