DocumentCode :
3486634
Title :
Rapid and robust human detection and tracking based on omega-shape features
Author :
Li, Min ; Zhang, Zhaoxiang ; Huang, Kaiqi ; Tan, Tieniu
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
fYear :
2009
fDate :
7-10 Nov. 2009
Firstpage :
2545
Lastpage :
2548
Abstract :
This paper proposes a novel method for rapid and robust human detection and tracking based on the omega-shape features of people´s head-shoulder parts. There are two modules in this method. In the first module, a Viola-Jones type classifier and a local HOG (Histograms of Oriented Gradients) feature based AdaBoost classifier are combined to detect head-shoulders rapidly and effectively. Then, in the second module, each detected head-shoulder is tracked by a particle filter tracker using local HOG features to model target´s appearance, which shows great robustness in scenarios of crowding, background distractors and partial occlusions. Experimental results demonstrate the effectiveness and efficiency of the proposed approach.
Keywords :
gradient methods; image classification; object detection; tracking; AdaBoost classifier; Viola-Jones type classifier; head-shoulder detection; histograms of oriented gradients; omega shape features; particle filter tracker; robust human detection; robust human tracking; Head; Humans; Image edge detection; Layout; Particle filters; Particle tracking; Robustness; Shape; Surveillance; Target tracking; HOG; head-shoulder detection; tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
ISSN :
1522-4880
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2009.5414008
Filename :
5414008
Link To Document :
بازگشت