Learning Spatiotemporal T-Junctions for Occlusion Detection

The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly strong indicator of occlusion, in both computer vision and neuroscience, is the T-junction; however, little progress has been made in T-junction detection. One reason for this is the difficulty in distinguishing false T-junctions (i.e. those not on an occluding edge) and real T-junctions in cluttered images. In addition to this, their photometric profile alone is not enough for reliable detection. This paper overcomes the first problem by searching for T-junctions not in space, but in space-time. This removes many false T-junctions and creates a simpler image structure to explore. The second problem is mitigated by learning the appearance of T-junctions in these spatiotemporal images. An RVM T-junction classifier is learnt from handlabelled data using SIFT to capture its redundancy. This detector is then demonstr...

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Nicholas Apostoloff, Andrew W. Fitzgibbon
• Keywords: Canny Edges, Computer Vision, CVPR 2005, Rvm T-junction Classifier, Simpler Image Structure, Spatiotemporal Domain, Spatiotemporal Images