Segmentation and Tracking Multiple Objects Under Occlusion From Multiview Video

被引:18
|
作者
Zhang, Qian [1 ]
King Ngi Ngan [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Elect Engn, Shatin, Hong Kong, Peoples R China
关键词
Graph cut; layer transition; multiview video; object segmentation; object tracking; PEOPLE; STEREO;
D O I
10.1109/TIP.2011.2159228
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a multiview approach to segment the foreground objects consisting of a group of people into individual human objects and track them across the video sequence. Depth and occlusion information recovered from multiple views of the scene is integrated into the object detection, segmentation, and tracking processes. Adaptive background penalty with occlusion reasoning is proposed to separate the foreground regions from the background in the initial frame. Multiple cues are employed to segment individual human objects from the group. To propagate the segmentation through video, each object region is independently tracked by motion compensation and uncertainty refinement, and the motion occlusion is tackled as layer transition. The experimental results implemented on both our sequences and other's sequence have demonstrated the algorithm's efficiency in terms of subjective performance. Objective comparison with a state-of-the-art algorithm validates the superior performance of our method quantitatively.
引用
收藏
页码:3308 / 3313
页数:7
相关论文
共 50 条
  • [21] Real-time segmentation and tracking technique of multiple moving objects in video sequence
    Sun, Zhi-Hai
    Zhu, Shan-An
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2008, 42 (09): : 1631 - 1635
  • [22] Occlusion Handling in Depth Estimation from Multiview Video
    Wegner, Krzysztof
    Stankiewicz, Olgierd
    Domanski, Marek
    2014 INTERNATIONAL CONFERENCE ON SIGNALS AND ELECTRONIC SYSTEMS (ICSES), 2014,
  • [23] User-assisted segmentation and tracking of video objects
    Hong, SH
    Lee, MMO
    HIGH-SPEED NETWORKS AND MULTIMEDIA COMMUNICATIONS, PROCEEDINGS, 2003, 2720 : 275 - 283
  • [24] Method for segmentation and tracking of moving objects in video sequences
    Wang, Cheng-Ru
    Liu, Yu
    Guangdian Gongcheng/Opto-Electronic Engineering, 2006, 33 (07): : 9 - 12
  • [25] Segmentation of multiple human objects in video sequences
    Yang, Hsin-Tai
    Ouyang, Chen-Sen
    Huang, Li-Ming
    Lee, Shie-Jue
    APPLIED ARTIFICIAL INTELLIGENCE, 2007, 21 (09) : 831 - 859
  • [26] A particle filter for tracking densely populated objects based on explicit multiview occlusion analysis
    Otsuka, K
    Mukawa, N
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, 2004, : 745 - 750
  • [27] Detection and tracking of multiple moving objects in video
    Huang, Wei
    Wu, Jonathan
    VISAPP 2007: PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOLUME IU/MTSV, 2007, : 492 - +
  • [28] Tracking multiple nonrigid objects in video sequences
    INRIA Sophia Antipolis, Sophia-Antipolis, France
    IEEE Trans Circuits Syst Video Technol, 5 (585-591):
  • [29] Tracking multiple nonrigid objects in video sequences
    Bremond, F
    Thonnat, M
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 1998, 8 (05) : 585 - 591
  • [30] Robust multiple objects tracking using image segmentation and trajectory estimation scheme in video frames
    Hsiao, Ying-Tung
    Chuang, Cheng-Long
    Lu, Yen-Ling
    Jiang, Joe-Air
    IMAGE AND VISION COMPUTING, 2006, 24 (10) : 1123 - 1136