A novel highway background generate approach

Authors:
Surong Yan
Affiliations:
College of Information, Zhejiang University of Finance & Economics, Hangzhou, P.R. China
Venue:
ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Year:
2006

Citing 3
Cited 0

Stationary background generation: an alternative to the difference of two images

Pattern Recognition
Multi-level background initialization using Hidden Markov Models

IWVS '03 First ACM SIGMM international workshop on Video surveillance
Background initialization with a new robust statistical approach

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The highway background generate is essential for highway vehicle detecting and analyzing. A novel background generate algorithm is proposed. The statistical information of pixels is collected to initialize the background. Three further optimization steps, the continuous luminance compensation, the spatial disturbance elimination and the inertial factor utilization, are exerted. Obstacle, such as environment light change, can be effectively overcome. A large number of images taken from highway have been tested. And our algorithm proves to be robust and efficient.