Occlusion reasoning for object detection under arbitrary viewpoint

E. Hsiao, M. Hebert
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
We present a unified occlusion model for object instance detection under arbitrary viewpoint. Whereas previous approaches primarily modeled local coherency of occlusions or attempted to learn the structure of occlusions from data, we propose to explicitly model occlusions by reasoning about 3D interactions of objects. Our approach accurately represents occlusions under arbitrary viewpoint without requiring additional training data, which can often be difficult to obtain. We validate our model
more » ... extending the state-of-the-art LINE2D method for object instance detection and demonstrate significant improvement in recognizing texture-less objects under severe occlusions.
doi:10.1109/cvpr.2012.6248048 dblp:conf/cvpr/HsiaoH12 fatcat:shshsyglubb4pfinvlo4pypeji