Toward Robust Online Visual Tracking

被引：8
作者：
Yang, Ming-Hsuan [1 ]
Ho, Jeffrey [2 ]
机构：
[1] Univ Calif Merced, Elect Engn & Comp Sci, Merced, CA 95344 USA
[2] Univ Florida, Comp & Informat Sci & Engn, Gainesville, FL 32607 USA
来源：
DISTRIBUTED VIDEO SENSOR NETWORKS | 2011年
关键词：
Visual tracking; Object tracking; Online learning; Incremental learning; OBJECT DETECTION; PEOPLE; RECOGNITION; HISTOGRAMS; MODELS;
D O I：
10.1007/978-0-85729-127-1_8
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We pursue a research direction that will empower machines with simultaneous tracking and recognition capabilities similar to human cognition. Toward that, we develop algorithms that leverage prior knowledge/model obtained offline with information available online via novel learning algorithms. While humans can effortlessly locate moving objects in different environments, visual tracking remains one of the most important and challenging problems in computer vision. Robust cognitive visual tracking algorithms facilitate answering important questions regarding how objects move and interact in complex environments. They have broad applications including surveillance, navigation, human computer interfaces, object recognition, motion analysis and video indexing, to name a few.
引用
收藏
页码：119 / 136
页数：18
相关论文
共 63 条
[1]  
Adam A., 2006, IEEE C COMPUTER VISI, V1, P798, DOI [DOI 10.1109/CVPR.2006.256, 10.1109/CVPR.2006.256]
[2]  
[Anonymous], P NIPS 05
[3]  
[Anonymous], 2006, BMVC06
[4]  
[Anonymous], 1991, Computational models of visual processing
[5]  
[Anonymous], 2005, NIPS
[6]  
[Anonymous], PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2000.854758
[7]  
[Anonymous], 2001, THESIS
[8]   Ensemble tracking [J].
Avidan, Shai .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (02) :261-271
[9]  
Babenko B, 2009, PROC CVPR IEEE, P983, DOI 10.1109/CVPRW.2009.5206737
[10]  
Balan A.O., 2006, COMPUTER VISION PATT, V1, P758
1234567