Camera self-calibration from tracking of moving persons

Zheng Tang, Yen Shuo Lin, Kuan Hui Lee, Jenq Neng Hwang, Jen-Hui Chuang, Zhijun Fang

研究成果: Conference contribution同行評審

13 引文 斯高帕斯(Scopus)


In a video surveillance system with a single static camera, tracking results of moving persons can be effectively used for camera self-calibration. However, the current methods need to depend on robustness of both tracking and segmentation procedures. RANSAC has been widely used to remove outliers in finding the vertical vanishing point and the horizon line, but the performance is degraded when the proportion of outliers is high. Last but not least, all of them require excessive simplifications in the algorithmic procedures resulting in increasing reprojection error. In this paper, a robust segmentation and tracking system is applied to provide accurate estimation of head and foot locations of moving persons. The noise in the computation of vanishing points is handled by mean shift clustering and Laplace linear regression through convex optimization. We also propose to use the estimation of distribution algorithm (EDA) to search for the local optimal solution for camera calibration that minimizes average reprojection error on the ground plane, while relaxing the assumptions on camera parameters. Promising evaluations of the performance of our proposed method on real scenes are presented.

主出版物標題2016 23rd International Conference on Pattern Recognition, ICPR 2016
發行者Institute of Electrical and Electronics Engineers Inc.
出版狀態Published - 1 一月 2016
事件23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
持續時間: 4 十二月 20168 十二月 2016


名字Proceedings - International Conference on Pattern Recognition


Conference23rd International Conference on Pattern Recognition, ICPR 2016

指紋 深入研究「Camera self-calibration from tracking of moving persons」主題。共同形成了獨特的指紋。