DocumentCode :
2352371
Title :
Tracking of object with SVM regression
Author :
Zhu, Weiyu ; Wang, Song ; Lin, Ruei-Sung ; Levinson, Stephen
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Volume :
2
fYear :
2001
fDate :
2001
Abstract :
This paper presents a novel feature-matching based approach for rigid object tracking. The proposed method models the tracking problem as discovering the affine transforms of object images between frames according to the extracted feature correspondences. False feature matches (outliers) are automatically detected and removed with a new SVM regression technique, where outliers are iteratively identified as support vectors with the gradually decreased insensitive margin ε. This method, in addition to object tracking, can also be used for general feature-based epipolar constraint estimation, in which it can quickly detect outliers even if they make up, in theory, over 50% of the whole data. We have applied the proposed method to track real objects under cluttering backgrounds with very encouraging results.
Keywords :
feature extraction; learning automata; object detection; optimisation; affine transforms; epipolar constraint estimation; extracted feature correspondences; feature-matching based approach; object images; object tracking; rigid object tracking; support vector machine regression; support vectors; Computer vision; Constraint theory; Feature extraction; Layout; Least squares approximation; Mechanical sensors; Noise robustness; Object detection; Support vector machines; Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-1272-0
Type :
conf
DOI :
10.1109/CVPR.2001.990966
Filename :
990966
Link To Document :
بازگشت