Issue No. 09 - Sept. (2014 vol. 36)
Edward Hsiao , Robotics Institute, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh,
Martial Hebert , Robotics Institute, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh,
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 by incorporating occlusion reasoning with the state-of-the-art LINE2D and Gradient Network methods for object instance detection and demonstrate significant improvement in recognizing texture-less objects under severe occlusions.
Three-dimensional displays, Cognition, Solid modeling, Computational modeling, Approximation methods, Object detection, Data models,arbitrary viewpoint, Occlusion reasoning, object detection
Edward Hsiao, Martial Hebert, "Occlusion Reasoning for Object Detectionunder Arbitrary Viewpoint", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 36, no. , pp. 1803-1815, Sept. 2014, doi:10.1109/TPAMI.2014.2303085