Probabilistic object tracking with dynamic attributed relational feature graph

被引:20
作者
Tang, Feng [1 ]
Tao, Hai [1 ]
机构
[1] Univ Calif Santa Cruz, Dept Comp Engn, Santa Cruz, CA 95060 USA
关键词
attributed relational graph (ARG); object representation; object tracking; relaxation labeling;
D O I
10.1109/TCSVT.2008.927106
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Object tracking is one of the fundamental problems in computer vision and has received considerable attention in the past two decades. The success of a tracking algorithm relies on two key issues: 1) an effective representation so that the object being tracked can be distinguished from the background and other objects and 2) an update scheme of the object representation to, accommodate object appearance and structure changes. Despite the progress made in the past, reliable and efficient tracking of objects with changing appearance remains a challenging problem. In this paper, a novel sparse, local feature-based object representation, the attributed relational feature graph,is proposed to solve this problem. The object is modeled using invariant features such as the scale-invariant feature transform and the geometric relations among features are encoded in the form of a graph. A dynamic model is developed to evolve the feature graph according to the appearance and structure changes by adding new stable features as well as removing inactive features. Extensive experiments show that our method can achieve reliable tracking even under significant appearance changes, view point changes, and occlusion.
引用
收藏
页码:1064 / 1074
页数:11
相关论文
共 50 条
[31]   Multiple object tracking based on the partition of the bipartite graph [J].
Alpatov, Boris ;
Babayan, Pavel .
ELECTRO-OPTICAL REMOTE SENSING, PHOTONIC TECHNOLOGIES, AND APPLICATIONS V, 2011, 8186
[32]   Spatial feature embedding for robust visual object tracking [J].
Liu, Kang ;
Liu, Long ;
Yang, Shangqi ;
Fu, Zhihao .
IET COMPUTER VISION, 2024, 18 (04) :540-556
[33]   On-line Feature Enhancement for Adaptive Object Tracking [J].
Ma, Lei ;
Wang, Yanqing ;
Tian, Yuan ;
Yang, Yiping .
2010 2ND INTERNATIONAL ASIA CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS (CAR 2010), VOL 1, 2010, :468-471
[34]   Object Tracking for Grabing Robot Based on Multiple Feature [J].
Wang, Yifan ;
Wang, Fei ;
Liang, Chen ;
Wu, Wei ;
Zhao, Haobo ;
Zhang, Yuze .
2018 IEEE 8TH ANNUAL INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (IEEE-CYBER), 2018, :1356-1359
[35]   Object compressive tracking via online feature selection [J].
College of Internet of Things Engineering, Hohai University, Changzhou ;
213022, China ;
不详 ;
213022, China .
Zidonghua Xuebao Acta Auto. Sin., 11 (1961-1970) :1961-1970
[36]   TFITrack: Transformer Feature Integration Network for Object Tracking [J].
Hu, Xiuhua ;
Liu, Huan ;
Li, Shuang ;
Zhao, Jing ;
Hui, Yan .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2024, 17 (01)
[37]   Combined feature evaluation for adaptive visual object tracking [J].
Han, Zhenjun ;
Ye, Qixiang ;
Jiao, Jianbin .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2011, 115 (01) :69-80
[38]   Robust object tracking based on adaptive feature selection [J].
Chen, D.-Y., 1600, Asian Network for Scientific Information (12) :7325-7330
[39]   Grid feature and visualizition for occlusion perception in object tracking [J].
Meng, B. (mengbo_nannan@163.com), 2013, Chinese Optical Society (42) :98-103
[40]   Dynamic Object Counting Application based on Object Detection and Tracking [J].
Shi, Jinglei ;
Tao, Wenbing .
TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806