INTERACTIVE ROTOSCOPING: EXTRACTING AND TRACKING OBJECT SKETCH

被引:0
|
作者
Lv, Han [1 ,3 ]
Lin, Liang [2 ,3 ]
Zeng, Kun [1 ,3 ]
Sang, Nong [1 ]
机构
[1] Huazhong Univ Sci & Technol, Wuhan 430074, Peoples R China
[2] Univ Calif Los Angeles, Dept Stat, Los Angeles, CA 90024 USA
[3] Lotus Hill Res Inst, Beijing, Peoples R China
基金
国家高技术研究发展计划(863计划); 中国国家自然科学基金;
关键词
Rotoscoping; Primal sketch; Graph matching; Object tracking;
D O I
暂无
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 discuss an integrated system for video rotoscoping extracting and tracking object sketch (structural shape) across video sequence. This system consists of two key components: object sketch computing and graph-based object tracking. Given a video clip, we first use a primal sketch algorithm to search bottom-up sketch proposals and additively pursue sketch strokes in each frame. User is allowed to edit the sketch in the beginning frame, such as adding strokes and removing the cluttered edges, and the refined sketch is saved as the template. A graph-based tracking method is then proposed for sequentially matching the template to following frames, and the template is kept update by geometric transformation. Once the matching is unsatisfied at one frame, the system is allowed the user interaction for correction. In the experiments, we apply this system on several videos and present the performance evaluation with comparison.
引用
收藏
页码:881 / +
页数:2
相关论文
共 50 条
  • [1] Extracting symbolic descriptors for interactive object retrieval
    Wickel, J
    Alvarado, P
    Kraiss, KF
    IMAGE ANALYSIS, PROCEEDINGS, 2003, 2749 : 290 - 297
  • [2] Effective re-texturing with interactive object extracting
    Wang, Xiaoju
    Sun, Qian
    Chen, Xin
    Guo, He
    Yang, Hongji
    Chen, Feng
    PROCEEDINGS OF 2007 10TH IEEE INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN AND COMPUTER GRAPHICS, 2007, : 240 - 245
  • [3] Interactive Multiple Object Tracking (iMOT)
    Thornton, Ian M.
    Buelthoff, Heinrich H.
    Horowitz, Todd S.
    Rynning, Aksel
    Lee, Seong-Whan
    PLOS ONE, 2014, 9 (02):
  • [4] Keyframe-based tracking for rotoscoping and animation
    Agarwala, A
    Hertzmann, A
    Salesin, DH
    Seitz, SM
    ACM TRANSACTIONS ON GRAPHICS, 2004, 23 (03): : 584 - 591
  • [5] AutoTrack: Interactive Visual Object Tracking for Efficient Object Annotations
    Keh, Jefferson
    Cruz, Meygen
    Rivera, Maverick
    Jose, John Anthony
    Sybingco, Edwin
    Dadios, Elmer
    Madria, Wira
    Miguel, Angelimarie
    2020 IEEE 12TH INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY, COMMUNICATION AND CONTROL, ENVIRONMENT, AND MANAGEMENT (HNICEM), 2020,
  • [6] INTERACTIVE MULTI-OBJECT TRACKING FOR VIRTUAL OBJECT MANIPULATION
    Guo, Yibo
    Yang, Michael Ying
    Rosenhahn, Bodo
    ISA13 - THE ISPRS WORKSHOP ON IMAGE SEQUENCE ANALYSIS 2013, 2013, II-3/W2 : 19 - 24
  • [7] Algorithm for extracting and tracking moving object in object-based video coding
    Zhu, Zhong-Jie
    Jiang, Gang-Yi
    Yu, Mei
    Wang, Rang-Ding
    Wu, Xun-Wei
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2003, 31 (09): : 1426 - 1428
  • [8] Interactive object tracking modulates attentional distribution
    Koning, A. R.
    Leenders, M.
    Wolk, C.
    van Lier, R.
    PERCEPTION, 2014, 43 (01) : 29 - 30
  • [9] Online object tracking based interactive attention
    Wang, Hongmei
    Guo, Fan
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 236
  • [10] ROAM: A Rich Object Appearance Model with Application to Rotoscoping
    Perez-Rua, Juan-Manuel
    Miksik, Ondrej
    Crivelli, Tomas
    Bouthemy, Patrick
    Torr, Philip H. S.
    Perez, Patrick
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (08) : 1996 - 2010