Detection and Classification of Human Movements in Video Scenes
A novel approach for the detection and classification of human movements in videos scenes is presented in this paper. It consists in detecting, segmenting and tracking foreground objects in video scenes to further classify their movements as conventional or non-conventional. From each tracked object in the scene, features such as position, speed, changes in direction and temporal consistency of the bounding box dimension are extracted. These features make up feature vectors that are stored together with labels that categorize the movement and which are assigned by human supervisors. At the classification step, an instance-based learning algorithm is used to classify the object movement as conventional or non-conventional. For this aim, feature vectors computed from objects in motion are matched against reference feature vectors previously labeled. Experimental results on video clips from two different databases (Parking Lot and CAVIAR) have shown that the proposed approach is able to detect non-conventional human movements in video scenes with accuracies between 77% and 82%.
KeywordsHuman Movement Classification Computer Vision Security
Unable to display preview. Download preview PDF.
- 2.Lühr, S., Bui, H.H., Venkatesh, S., West, G.A.W.: Recognition of human activity through hierarchical stochastic learning. In: IEEE Annual Conf on Pervasive Computing and Communications, Fort Worth, pp. 416–421. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
- 5.Mecocci, A., Pannozzo, M., Fumarola, A.: Automatic detection of anomalous behavioral events for advanced real-time video surveillance. In: IEEE Intl Symp on Computational Intelligence for Measurement Systems and Applications, pp. 187–192. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
- 6.Niu, W., Long, J., Han, D., Wang, Y.F.: Human activity detection and recognition for video surveillance. In: IEEE Intl Conf Multimedia and Expo, pp. 719–722. IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
- 10.Lei, B., Xu, L.Q.: From pixels to objects and trajectories: A generic real-time outdoor video surveillance system. In: IEE Intl Symp Imaging for Crime Detection and Prevention, London, UK, pp. 117–122 (2005)Google Scholar
- 11.Latecki, L.J., Miezianko, R.: Object tracking with dynamic template update and occlusion detection. In: 18th Intl Conf on Pattern Recognition, Washington, USA, pp. 556–560 (2006)Google Scholar
- 12.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: 7th Intl Joint Conf Artificial Intelligence, Vancouver, Canada, pp. 674–679 (1981)Google Scholar
- 13.Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Machine Learning 6(1), 37–66 (1991)Google Scholar