Object Segmentation by Long Term Analysis of Point Trajectories

被引:0
|
作者
Brox, Thomas [1 ]
Malik, Jitendra [1 ]
机构
[1] Univ Calif Berkeley, Berkeley, CA 94720 USA
来源
COMPUTER VISION-ECCV 2010, PT V | 2010年 / 6315卷
关键词
MOTION SEGMENTATION; VIDEO;
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
Unsupervised learning requires a grouping step that defines which data belong together. A natural way of grouping in images is the segmentation of objects or parts of objects. While pure bottom-up segmentation from static cues is well known to be ambiguous at the object level, the story changes as soon as objects move. In this paper, we present a method that uses long term point trajectories based on dense optical flow. Defining pair-wise distances between these trajectories allows to cluster them, which results in temporally consistent segmentations of moving objects in a video shot. In contrast to multi-body factorization, points and even whole objects may appear or disappear during the shot. We provide a benchmark dataset and an evaluation method for this so far uncovered setting.
引用
收藏
页码:282 / 295
页数:14
相关论文
共 50 条
  • [1] Multiple Object Tracking based on Motion Segmentation of Point Trajectories
    Dimitriou, Nikolaos
    Stavropoulos, Georgios
    Moustakas, Konstantinos
    Tzovaras, Dimitrios
    2016 13TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2016, : 200 - 206
  • [2] Object Segmentation in Video: A Hierarchical Variational Approach for Turning Point Trajectories into Dense Regions
    Ochs, Peter
    Brox, Thomas
    2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 1583 - 1590
  • [3] LVOS: A Benchmark for Long-term Video Object Segmentation
    Hong, Lingyi
    Chen, Wenchao
    Liu, Zhongying
    Zhang, Wei
    Guo, Pinxue
    Chen, Zhaoyu
    Zhang, Wenqiang
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 13434 - 13446
  • [4] Video Object Segmentation Based on Superpixel Trajectories
    Abdelwahab, Mohamed A.
    Abdelwahab, Moataz M.
    Uchiyama, Hideaki
    Shimada, Atsushi
    Taniguchi, Rin-ichiro
    IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016), 2016, 9730 : 191 - 197
  • [5] Video Object Segmentation Via Dense Trajectories
    Chen, Lin
    Shen, Jianbing
    Wang, Wenguan
    Ni, Bingbing
    IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 17 (12) : 2225 - 2234
  • [6] Video Object Segmentation by Clustering Region Trajectories
    Zhang, Geng
    Yuan, Zejian
    Chen, Dapeng
    Liu, Yuehu
    Zheng, Nanning
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 2598 - 2601
  • [7] Object point processes for image segmentation
    Drot, S
    Descombes, X
    Le Men, H
    Zerubia, J
    16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2002, : 913 - 916
  • [8] Segmentation and Sampling of Moving Object Trajectories Based on Representativeness
    Panagiotakis, Costas
    Pelekis, Nikos
    Kopanakis, Ioannis
    Ramasso, Emmanuel
    Theodoridis, Yannis
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2012, 24 (07) : 1328 - 1343
  • [9] Unsupervised object segmentation through change detection in a long term autonomy scenario
    Ambrus, Rares
    Folkesson, John
    Jensfelt, Patric
    2016 IEEE-RAS 16TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2016, : 1181 - 1187
  • [10] SEMI-AUTOMATIC MOTION BASED SEGMENTATION USING LONG TERM MOTION TRAJECTORIES
    Baugh, Gary
    Kokaram, Anil
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 3009 - 3012