Title: Using spatiotemporal blocks to reduce the uncertainty in detecting and tracking moving objects in video

Authors: Longin Jan Latecki, Vasileios Megalooikonomou, Roland Miezianko, Dragoljub Pokrajac

Addresses: Department of Computer and Information Sciences, Temple University, 3rd floor Wachman Hall, 1805 N. Broad St., Philadelphia PA 19122, USA. ' Data Engineering Laboratory (DEnLab), Center for Information Science and Technology, Department of Computer and Information Sciences, Temple University, 3rd floor Wachman Hall, 1805 N. Broad St., Philadelphia PA 19122, USA. ' Department of Computer and Information Sciences, Temple University, 3rd floor Wachman Hall, 1805 N. Broad St., Philadelphia PA 19122, USA. ' Computer and Information Science Department, Delaware State University, 1200 N Dupont Hwy, Dover, 19901 DE, USA

Abstract: We present a novel method for detecting moving objects in videos. The method represents videos using spatiotemporal blocks instead of pixels. Dimensionality reduction is performed to obtain a compact representation of each block|s values. The block vectors provide a joint representation of texture and motion patterns. The motion detection and tracking experiments demonstrate that our method although simpler than a state-of-the-art method based on the Stauffer-Grimson Gaussian mixture model has superior performance. It reduces both the instability and the processing time making real-time processing of high resolution videos and efficient analysis of large scale video data feasible.

Keywords: video analysis; uncertainty; moving objects; detection; tracking; dimensionality reduction; Gaussian mixture model; spatiotemporal blocks; video processing.

DOI: 10.1504/IJISTA.2006.009914

International Journal of Intelligent Systems Technologies and Applications, 2006 Vol.1 No.3/4, pp.376 - 392

Published online: 01 Jun 2006 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article