Surveillance video processing using compressive sensing

Hong Jiang,Wei Deng,Zuowei Shen

doi:10.3934/ipi.2012.6.201

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.

Highlights

In a network of cameras for surveillance, a massive number of cameras are deployed, some with wireless connections
Detection of moving objects is traditionally achieved by background subtraction methods [1, 21] which segment background and moving objects in a sequence of surveillance video frames
In low rank and sparse decomposition [4], the background is modeled by a low rank matrix, and the moving

Summary

Introduction

In a network of cameras for surveillance, a massive number of cameras are deployed, some with wireless connections. Compressive sensing, surveillance video, background subtraction, lowrank and sparse decomposition, alternating direction method, tight frames. These traditional background subtraction techniques require all pixels of a surveillance video to be captured, transmitted and analyzed. We propose a method for segmentation of background by using a low rank and sparse decomposition of matrix In this method, the compressive measurements from a surveillance camera are used to reconstruct video which is assumed to be comprised of a low rank and a sparse component.

Video volume

Findings

Conclusion