Object recognition based on image sequences by using inter-feature-line consistencies

被引:16
作者
Chen, JH
Chen, CS [1 ]
机构
[1] Acad Sinica, Inst Informat Sci, Taipei, Taiwan
[2] Univ Washington, Dept Comp Sci & Engn, Seattle, WA USA
关键词
object recognition; appearance-based object recognition; nearest feature lines; sequence-based object recognition;
D O I
10.1016/j.patcog.2003.12.003
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An image sequence-based framework for appearance-based object recognition is proposed in this paper. Compared with the methods of using a single view for object recognition, inter-frame consistencies can be exploited in a sequence-based method, so that a better recognition performance can be achieved. We use the nearest feature line (NFL) method (IEEE Trans. Neural Networks 10 (1999) 439) to model each object. The NFL method is extended in this paper by further integrating motion-continuity information between features lines in a probabilistic framework. The associated recognition task is formulated as maximizing an a posteriori probability measure. The recognition problem is then further transformed to a shortest-path searching problem, and a dynamic-programming technique is used to solve it. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码:1913 / 1923
页数:11
相关论文
共 19 条
[1]  
[Anonymous], IEEE C CVPR
[2]   What is the set of images of an object under all possible illumination conditions? [J].
Belhumeur, PN ;
Kriegman, DJ .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 28 (03) :245-260
[3]   EigenTracking: Robust matching and tracking of articulated objects using a view-based representation [J].
Black, MJ ;
Jepson, AD .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 26 (01) :63-84
[4]   A new LDA-based face recognition system which can solve the small sample size problem [J].
Chen, LF ;
Liao, HYM ;
Ko, MT ;
Lin, JC ;
Yu, GJ .
PATTERN RECOGNITION, 2000, 33 (10) :1713-1726
[5]   Video-based eye tracking for autostereoscopic displays [J].
Chen, YS ;
Su, CH ;
Chen, JH ;
Chen, CS ;
Hung, YP ;
Fuh, CS .
OPTICAL ENGINEERING, 2001, 40 (12) :2726-2734
[6]   Augmenting panoramas with object movies by generating novel views with disparity-based view morphing [J].
Hung, YP ;
Chen, CS ;
Tsai, YP ;
Lin, SW .
JOURNAL OF VISUALIZATION AND COMPUTER ANIMATION, 2002, 13 (04) :237-247
[7]  
Koubaroulis D., 2002, Proceedings of the Fifth Asian Conference on Computer Vision, P840
[8]  
Li SZ, 2000, IEEE T PATTERN ANAL, V22, P1335, DOI 10.1109/34.888719
[9]   Face recognition using the nearest feature line method [J].
Li, SZ ;
Lu, JW .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (02) :439-443
[10]   Probabilistic visual learning for object representation [J].
Moghaddam, B ;
Pentland, A .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (07) :696-710