Local Shape Patch based Object Detection

摘要：

We present a novel object detection framework that uses the local shape patches features combining the interclass global features information. A supervised local model learning architecture is proposed: a novel interest point descriptor is proposed and applied to detect the local shape patches, the local shape patches are formed by chains of several connected contour segments. Then the object local contour parts model are learned from a small set of training images. In order to make the local contour patch model is invariant to rotation and translation, the local contour patch descriptor is represented by modifled shape context. By adding the edge orientation information and interclass global information, the power of differentiating mismatches is increased, especially detecting the objects existing similar parts. Both experiments on image feature point matching and object detection comparing with other feature descriptors are carried out in order to validate the proposed method.

作者: Zhijiang Du Chen Guodong Lining Sun Junhong Ji Ming Xie

作者单位: State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin,China,150080 School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore,637553

会议类型: 国际会议

会议名称: 2010 IEEE信息与自动化国际会议(ICIA 2010)

会议地点: 哈尔滨

会议语种:英文

页码: 1-6

在线出版日期: 2010-06-20（万方平台首次上网日期，不代表论文的发表时间）