Clustering of video objects by graph matching

被引:0
|
作者
Lee, J [1 ]
Oh, J [1 ]
Hwang, S [1 ]
机构
[1] Univ Texas, Dept Comp Sci & Engn, Arlington, TX 76019 USA
关键词
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
We propose a new graph-based data structure, called Spatio temporal Region Graph (STRG) which can represent the content of video sequence. Unlike existing ones which consider mainly spatial information in the frame level of video, the proposed STRG is able to formulate its temporal information in the video level additionally. After an STRG is constructed from a given video sequence, it is decomposed into its subgraphs called Object Graphs (OGs), which represent the temporal characteristics of video objects. For unsupervised learning, we cluster similar OGs into a group, in which we need to match two OGs. For this graph matching, we introduce a new distance measure, called E.,tended Graph Edit Distance (ECED), which can handle the temporal characteristics of OGs. For actual clustering, we exploit Expectations Maximization (EM) with EGED. The experiments have been conducted on real video streams, and their results show the effectiveness and robustness of the proposed schemes.
引用
收藏
页码:394 / 397
页数:4
相关论文
共 50 条
  • [41] VLG-Net: Video-Language Graph Matching Network for Video Grounding
    Soldan, Mattia
    Xu, Mengmeng
    Qu, Sisi
    Tegner, Jesper
    Ghanem, Bernard
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021), 2021, : 3217 - 3227
  • [42] Semantic Video-to-Video Search using Sub-Graph Grouping and Matching
    Choe, Tae Eun
    Deng, Hongli
    Guo, Feng
    Lee, Mun Wai
    Haering, Niels
    2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2013, : 787 - 794
  • [44] GRAPH BASED MULTIMODAL WORD CLUSTERING FOR VIDEO EVENT DETECTION
    Vembu, Aravind
    Natarajan, Pradeep
    Wu, Shuang
    Prasad, Rohit
    Natarajan, Prem
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 3667 - 3671
  • [45] Combining graph connectivity & dominant set clustering for video summarization
    D. Besiris
    A. Makedonas
    G. Economou
    S. Fotopoulos
    Multimedia Tools and Applications, 2009, 44 : 161 - 186
  • [46] Combining graph connectivity & dominant set clustering for video summarization
    Besiris, D.
    Makedonas, A.
    Economou, G.
    Fotopoulos, S.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2009, 44 (02) : 161 - 186
  • [47] Segmenting, modeling, and matching video clips containing multiple moving objects
    Rothganger, F
    Lazebnik, S
    Schmid, C
    Ponce, J
    PROCEEDINGS OF THE 2004 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, 2004, : 914 - 921
  • [48] Moving Objects Detection in Birds Video Based on Multiple Block Matching
    Li, Yan
    Yin, Yongyi
    ICCIT: 2009 FOURTH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND CONVERGENCE INFORMATION TECHNOLOGY, VOLS 1 AND 2, 2009, : 1262 - 1265
  • [49] Scalable unpaired multi-view clustering with Bipartite Graph Matching
    Li, Xingfeng
    Pan, Yuangang
    Sun, Yuan
    Sun, Yinghui
    Sun, Quansen
    Ren, Zhenwen
    Tsang, Ivor W.
    INFORMATION FUSION, 2025, 116
  • [50] Inexact graph matching using eigen-subspace projection clustering
    Caelli, T
    Kosinov, S
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2004, 18 (03) : 329 - 354