Addresses the problem of segmenting objects into parts usingstereo images. There are three components in the part segmentationprocess: surface segmentation, region grouping, and volumetric modelsrecovery/segmentation. The surface segmentation process segments theimage into a set of regions such that each region represents a surfacesmooth in depth. The region grouping process merges the segmentedregions into meaningful parts. Finally the process of volumetric modelrecovery/segmentation phase recovers the part model and segments thatpart into smaller parts if necessary. Since multi-shape models have beenused to drive the part segmentation process, one can capture moregeometric properties of the object and the application domain of theapproach is broader than that of the previous approaches
展开▼