Share Email Print
cover

Proceedings Paper

Moving target detection based on temporal-spatial information fusion for infrared image sequences
Author(s): Wu-qin Toing; Jin-yu Xiong; An-jun Zeng; Xiao-ping Wu; Hao-peng Xu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Moving target detection and localization is one of the most fundamental tasks in visual surveillance. In this paper, through analyzing the advantages and disadvantages of the traditional approaches about moving target detection, a novel approach based on temporal-spatial information fusion is proposed for moving target detection. The proposed method combines the spatial feature in single frame and the temporal properties within multiple frames of an image sequence of moving target. First, the method uses the spatial image segmentation for target separation from background and uses the local temporal variance for extracting targets and wiping off the trail artifact. Second, the logical "and" operator is used to fuse the temporal and spatial information. In the end, to the fusion image sequence, the morphological filtering and blob analysis are used to acquire exact moving target. The algorithm not only requires minimal computation and memory but also quickly adapts to the change of background and environment. Comparing with other methods, such as the KDE, the Mixture of K Gaussians, etc., the simulation results show the proposed method has better validity and higher adaptive for moving target detection, especially in infrared image sequences with complex illumination change, noise change, and so on.

Paper Details

Date Published: 5 August 2009
PDF: 9 pages
Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73831I (5 August 2009); doi: 10.1117/12.834112
Show Author Affiliations
Wu-qin Toing, Southwest Electronics and Telecommunication Technology Research Institute (China)
Jin-yu Xiong, Southwest Electronics and Telecommunication Technology Research Institute (China)
An-jun Zeng, Southwest Electronics and Telecommunication Technology Research Institute (China)
Xiao-ping Wu, Southwest Electronics and Telecommunication Technology Research Institute (China)
Hao-peng Xu, Researcher (China)


Published in SPIE Proceedings Vol. 7383:
International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications

© SPIE. Terms of Use
Back to Top