Human Gait Modeling and Simulation


Abstract in English

The extraction and analysis of human gait characteristics using image sequences is currently an intense area of research. Recently, the focus of this research area has turned to the realm of computer vision as a way of performing quickly and accurately gait analysis system. Such a system could be used as a preprocessing step in a more sophisticated gait analysis system or could be used for rehabilitation purposes.In this thesis, a new method is proposed which utilizes a novel fusion of spatial computer vision operations as well as motion in order to accurately and efficiently determine the center of mass of a walking person at a video scene. Then we make a comparison between our method’s results and the inverted pendulum model of the movement's center of mass of a walking person in the XY plane. The results showed a significant correspondence between the model and the results we have obtained, which opens the way for further research to discover defects walking or develop algorithms for humanoid robots.

References used

J. Rose and J. Gamble, Human Walking, 3rd edition, New York: Lippencott Williams and Wilkins, 2006
M. Kohle and D. Merkle, "Clinical Gait Analysis by Neural Networks: Isses and Experiences," Proceedings of the IEEE Symposium on Computer-Based Medical Systems, pp. 138-143, 1997.
L. a. T. T. Wang, "Silhouette Analysis-Based Gait Recognition for Human Identification," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 12, 2003.

Download