DocumentCode :
3380629
Title :
Body tracking in human walk from monocular video sequences
Author :
Jean, Frederic ; Bergevin, Robert ; Albu, Alexandra Branzan
Author_Institution :
Dept. of Electr. & Comput. Eng., Laval Univ., Sainte-Foy, Que., Canada
fYear :
2005
fDate :
9-11 May 2005
Firstpage :
144
Lastpage :
151
Abstract :
This paper proposes a method to automatically track human body parts in the context of gait modelisation and recognition. The proposed approach is based on a five points human model (head, hands, and feet) where the points are detected and tracked independently. Tracking is fully automatic (no manual initialization of the five points) since it will be used in a real-time surveillance system. Feet are detected in each frame by first finding the space between the legs in the human silhouette. The issue of feet self-occlusion is handled using optical flow and motion correspondence. Skin color segmentation is used to find hands in each frame and tracking is achieved by using a bounding box overlap algorithm. The head is defined as the mass center of a region of the upper silhouette.
Keywords :
gait analysis; image segmentation; image sequences; real-time systems; surveillance; target tracking; video signal processing; bounding box overlap algorithm; feet self-occlusion; gait modelisation; gait recognition; human body tracking; monocular video sequences; optical flow; real-time surveillance system; skin color segmentation; Biological system modeling; Biomedical optical imaging; Cameras; Computer vision; Humans; Image motion analysis; Legged locomotion; Optical variables control; Surveillance; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer and Robot Vision, 2005. Proceedings. The 2nd Canadian Conference on
Print_ISBN :
0-7695-2319-6
Type :
conf
DOI :
10.1109/CRV.2005.24
Filename :
1443123
Link To Document :
بازگشت