Panoramic background generation and abnormal behavior detection in PTZ camera networks

Authors:
Sang-Hyun Cho;Hang-Bong Kang
Affiliations:
Dept. of Computer Engineering, The Catholic University of Korea, Bucheon, Gyeonggi-do, Korea;Dept. of Digital Media, The Catholic University of Korea, Gyeonggi-do, Korea
Venue:
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
Year:
2011

Citing 7
Cited 0

Learning the distribution of object trajectories for event recognition

BMVC '95 Proceedings of the 6th British conference on Machine vision (Vol. 2)
Construction of panoramic image mosaics with global and local alignment

Panoramic vision
Recognising Panoramas

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Automatic Panoramic Image Stitching using Invariant Features

International Journal of Computer Vision
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Eliminating Ghosting Artifacts for Panoramic Images

ISM '09 Proceedings of the 2009 11th IEEE International Symposium on Multimedia
Unexpected Human Behavior Recognition in Image Sequences Using Multiple Features

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel method to abnormal behavior detection in PTZ camera networks. To extract motion information of scene in moving camera environment, we use panoramic background which is generated by frames. In contrast with previous methods, we use MRF framework to integrate temporal and spatial information of frames to generate panoramic background. In addition, we introduce a panoramic activity map to detect abnormal behavior of people. The panoramic activity map is useful in various abnormal situation since it includes multiple features such as location, motion, direction and pace of objects. Experimental results from real sequences demonstrate the effectiveness of our method.