Efficient Model Selection for Detachable Object Detection

[摘要] We describe a computationally efficient scheme to perform model selection whilesimultaneously segmenting a short video stream into an unknown number of detachable objects. Detachable objects are regions of space bounded by surfaces that are surrounded by the medium other than for their region of support, and the region of support changes over time. These include humans walking, vehicles moving, etc.We exploit recent work on occlusion detection to bootstrap an energy minimization approach that is solved with linear programming. The energy integrates both appearance and motion statistics, and can be used to seed layer segmentation approaches that integrate temporal information on long timescales.

[发布机构] UCLA Henry Samueli School of Engineering and Applied Science

[学科分类] 计算机科学（综合）