Joint occlusion boundary detection and figure/ground assignment by extracting common-fate fragments in a back-projection scheme

作     者：Chen, Cheng Corso, Jason J. 

作者机构：Oklahoma State Univ Image & Sensor Lab Pavement Stillwater OK 74078 USA Univ Michigan Elect Engn & Comp Sci 1301 Beal Ave Ann Arbor MI 48109 USA 

出 版 物：《PATTERN RECOGNITION》 (图形识别)

年 卷 期：2017年第64卷

页      面：15-28页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：DARPA/ARL MINDSEYE program [W911NF-10-2-0062] 

主　　题：REAR-screen projection PATTERN perception PATTERN recognition systems SEGMENTATION (Image processing) NAVIGATION 

摘      要：Occlusion boundary detection and figure/ground assignment are among the fundamental challenges for the real world visual pattern recognition applications, such as 3D spatial understanding, robotic navigation and object search. We attack these challenges by extracting an intermediate-level image/video representation, namely, Common-Fate Fragments. A Common-Fate Fragment is composed of both over-segmented region and edge fragments. Physically, it exists as a coupled edge-region fragment bound with dynamic information. Common Fate Fragment candidates are generated by an integrated line-region growing process, which does not require complete object segmentation or closed object boundary extraction. To identify Common-Fate Fragments from these extracted candidates, we introduce a back-projection verification scheme that can circumvent the notoriously difficult task of direct motion estimation on boundaries. This allows occlusion detection and figure/ground labeling to be jointly conducted within a simple but effective hypothesize-and-test framework. We test the proposed method on YouTube Motion Boundaries (YMB) data set and two benchmark data sets: the CMU and Berkeley motion data sets. Even though the idea of the proposed method is simple and transparent, promising experimental results are observed.