Background modeling from surveillance video using rank minimization

Authors:
Min Yang
Affiliations:
College of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China
Venue:
AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
Year:
2012

Citing 5
Cited 0

Learning Patterns of Activity Using Real-Time Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Adaptive Tracking to Classify and Monitor Activities in a Site

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A Singular Value Thresholding Algorithm for Matrix Completion

SIAM Journal on Optimization
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization

SIAM Review
Robust principal component analysis?

Journal of the ACM (JACM)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Intelligent video surveillance systems can be applied to a wide range of potential applications. In this paper, we propose a new background modeling scheme that draws from the principles of low rank representation. We assume that the underlying background images are linearly correlated. Thus, the matrix composed of vectorized video frames can be approximated by a low-rank background matrix plus the sparse foreground components. Low rank representation can be exactly recovered via convex optimization that minimizes a combination of the nuclear norm and the l1-norm, and this non-convex problem can be solved very efficiently in the inexact Augmented Lagrange Multiplier method. We tested our algorithm on real video, and our approach obtained good results, comparable to the Gaussian Mixture Model method.