We propose a new method for warping high-resolution images to efficiently track objects on the ground plane in real time. Recently, the emergence of high resolution video cameras (> 5 megapixels) has enabled surveillance over a much larger area using only a single camera. However, real-time processing of high resolution video for automatic detection and tracking of multiple targets is a challenge. When the surveillance camera covers greater depth of ground regions, due to perspective effect, the image size of a target varies significantly depending on the distance between the camera and the target. In this study, we propose a framework to transform high resolution images into warped images using a plane homography to make the target size uniform regardless of the position. The method not only reduces the number of pixels to be processed for speed-up, but also improves the tracking performance. We provide experimental results on object tracking in high-resolution maritime videos to demonstrate the validity of our method.
[1]
Rama Chellappa,et al.
Video Mensuration Using a Stationary Camera
,
2006,
ECCV.
[2]
Andrew Zisserman,et al.
Multiple View Geometry in Computer Vision: Scene planes and homographies
,
2004
.
[3]
C Tomasi,et al.
Shape and motion from image streams: a factorization method.
,
1992,
Proceedings of the National Academy of Sciences of the United States of America.
[4]
Mohan M. Trivedi,et al.
Homography-based Analysis of People and Vehicle Activities in Crowded Scenes
,
2007,
2007 IEEE Workshop on Applications of Computer Vision (WACV '07).
[5]
Ramakant Nevatia,et al.
Tracking multiple humans in complex situations
,
2004,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[6]
Robert C. Bolles,et al.
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
,
1981,
CACM.