Robust background subtraction for quick illumination changes

Authors:
Shinji Fukui;Yuji Iwahori;Hidenori Itoh;Haruki Kawanaka;Robert J. Woodham
Affiliations:
Faculty of Education, Aichi University of Education, Kariya, Japan;Faculty of Engineering, Chubu University, Kasugai, Japan;Faculty of Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, Japan;Faculty of Info. Sci. and Tech., Aichi Prefectural University, Aichi-Gun, Japan;Dept. of Computer Science, University of British Columbia, Vancouver, B.C., Canada
Venue:
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Year:
2006

Citing 2
Cited 4

Learning Patterns of Activity Using Real-Time Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust object detection and segmentation by peripheral increment sign correlation image

Systems and Computers in Japan

Real-Time 3D Reconstruction for Collision Avoidance in Interventional Environments

MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Motion Detection with Entropy in Dynamic Background

CAR '09 Proceedings of the 2009 International Asia Conference on Informatics in Control, Automation and Robotics
Real-Time 3D Reconstruction for Occlusion-Aware Interactions in Mixed Reality

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Estimating radiation exposure in interventional environments

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new method to extract moving objects from a color video sequence. The proposed method is robust to both noise and intensity changes in the observed image. A present background image is estimated by generating conversion tables from the original background image to the present image. Then, the moving object region is extracted by background subtraction. Using color gives more accurate detection than a previous method which used only monochrome data. Color images increase the computational load. The method addresses this problem by using the GPU's throughput. Results are demonstrated with experiments on real data.