DocumentCode :
2985453
Title :
A markerless approach for consistent action recognition in a multi-camera system
Author :
Calderara, Simone ; Prati, Andrea ; Cucchiara, Rita
Author_Institution :
Dipt. di Ing. dell´´Inf., Univ. of Modena & Reggio Emilia, Modena
fYear :
2008
fDate :
7-11 Sept. 2008
Firstpage :
1
Lastpage :
8
Abstract :
This paper presents a method for recognizing human actions in a multi-camera setup. The proposed method automatically extracts significant points on the human body, without the need of artificial markers. A sophisticated appearance-based tracking able to cope with occlusions is exploited to extract a probability map for each moving object. A segmentation technique based on mixture of Gaussians is then employed to extract and track significant points on this map, corresponding to significant regions on the human silhouette. The point tracking produces a set of 3D trajectories that are compared with other trajectories by means of global alignment and dynamic programming techniques. Preliminary experiments showed the potentiality of the proposed approach.
Keywords :
Gaussian distribution; dynamic programming; feature extraction; gesture recognition; image motion analysis; image segmentation; image sensors; probability; target tracking; Gaussian distribution; appearance-based tracking; consistent action recognition; dynamic programming techniques; feature extraction; markerless approach; mean tracking; moving objects mapping; multicamera system setup; occlusion; probability mapping; segmentation technique; Biological system modeling; Dynamic programming; Gaussian processes; Humans; Image analysis; Image edge detection; Image recognition; Pattern recognition; Trajectory; US Department of Transportation; Action recognition; dynamic programming; mean tracking; mixture of Gaussians;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Distributed Smart Cameras, 2008. ICDSC 2008. Second ACM/IEEE International Conference on
Conference_Location :
Stanford, CA
Print_ISBN :
978-1-4244-2664-5
Electronic_ISBN :
978-1-4244-2665-2
Type :
conf
DOI :
10.1109/ICDSC.2008.4635691
Filename :
4635691
Link To Document :
بازگشت