`a`
Inverse Problems and Imaging (IPI)
 

Surveillance video processing using compressive sensing

Pages: 201 - 214, Volume 6, Issue 2, May 2012      doi:10.3934/ipi.2012.6.201

 
       Abstract        References        Full Text (1603.6K)       Related Articles       

Hong Jiang - Bell Labs, Alcatel-Lucent, 700 Mountain Ave, Murray Hill, NJ 07974, United States (email)
Wei Deng - Dept. of Computational and Applied Math., Rice University, Houston, TX 77005, United States (email)
Zuowei Shen - Dept. of Math., National Univ. of Singapore, 119076, Singapore (email)

Abstract: A compressive sensing method combined with decomposition of a matrix formed with image frames of a surveillance video into low rank and sparse matrices is proposed to segment the background and extract moving objects in a surveillance video. The video is acquired by compressive measurements, and the measurements are used to reconstruct the video by a low rank and sparse decomposition of matrix. The low rank component represents the background, and the sparse component is used to identify moving objects in the surveillance video. The decomposition is performed by an augmented Lagrangian alternating direction method. Experiments are carried out to demonstrate that moving objects can be reliably extracted with a small amount of measurements.

Keywords:  Compressive sensing, surveillance video, background subtraction, low-rank and sparse decomposition, alternating direction method, tight frames.
Mathematics Subject Classification:  Primary: 00A69, 41-02; Secondary: 46N10.

Received: December 2011;      Revised: February 2012;      Available Online: May 2012.

 References