Sciweavers

3DPVT
2004
IEEE

Unsupervised Motion Classification by Means of Efficient Feature Selection and Tracking

14 years 4 months ago
Unsupervised Motion Classification by Means of Efficient Feature Selection and Tracking
This paper presents an efficient technique for human motion recognition; in particular, it is focused on labeling a movement as a walking or running displacement, which are the most frequent type of locomotion. The proposed technique consists of two stages and is based on the study of feature points' trajectories. The first stage detects peaks and valleys of points' trajectories, which are used on the second stage to discern whether the movement corresponds to a walking or a running displacement. Prior knowledge of human body kinematics structure together with the corresponding motion model are the basis for the motion recognition. Experimental results with different video sequences are presented.
Angel Domingo Sappa, Niki Aifanti, Sotiris Malassi
Added 20 Aug 2010
Updated 20 Aug 2010
Type Conference
Year 2004
Where 3DPVT
Authors Angel Domingo Sappa, Niki Aifanti, Sotiris Malassiotis, Michael G. Strintzis
Comments (0)