Cascade Framework for Object Extraction in Image Sequences

摘要：

　　This paper proposes a novel cascade framework to improve spatiotemporal object extraction algorithms for unconstrained image sequences.The cascade framework successively incorporates the constraints on the size of objects for candidate region prediction,an improved backprojection algorithm for coarse localization,ASIFT feature matching for object markers propagation and a novel interactive region merging method for the exact object contour segmentation.Realworld experiments show the effectiveness of the proposed method in the case of varying viewpoint,changing backgrounds,and similar distractors.

关键词： object extraction localization segmentation backprojection ASIFT

作者: Peng Li Zhipeng Cai Cheng Wang Zhuo Sun Hanyun Wang Jonathan Li

作者单位: School of Electronics Science and Engineering, National University of Defense Technology, Changsha, Department of Computer Science, Xiamen University, Xiamen, China, 361005

会议类型: 国际会议

会议名称: 2012年遥感中的计算机视觉国际会议

会议地点: 厦门

会议语种:英文

页码: 1-5

在线出版日期: 2012-12-16（万方平台首次上网日期，不代表论文的发表时间）