Pedestrian segmentation using deformable triangulation and kernel density estimation

Jun-Wei Hsieh*, Sin Yu Chen, Chi Hung Chuang, Yung Sheng Chen, Zhong Yi Guo, Kuo Chin Fan

*此作品的通信作者

研究成果: Conference contribution同行評審

5 引文 斯高帕斯(Scopus)

摘要

This paper proposes a novel kernel-based and technique to segment pedestrians from a single image. An important concept introduced in this paper is "detection before segmentation" for extracting pedestrians' boundaries more precisely no matter what cameras (mobile, PTZ, or stationary) are used or how does the background include various lighting changes. First of all, the Adaboost-based detector is trained for detecting all possible pedestrians from still images. Then, we adopt the Watershed algorithm to over-segment each frame as a rough segmentation. Since two homogenous regions will still connect together, a triangulation-based scheme is then used to divide them into different tinier regions using their edge features. Then, we propose a novel kernel density analysis to estimate the probability of each tinier region to be foreground or background. With the kernel modeling, an optimal segmentation of pedestrian can be found by maximizing a posteriori probability for maintaining the visual and spatial consistencies between each segmented regions. Then, each desired pedestrian can be more accurately extracted for content analysis even though it is occluded with other objects or captured by a mobile camera. Experimental results have shown the effectiveness and superiority of the proposed method in pedestrian segmentation.

原文English
主出版物標題Proceedings of the 2009 International Conference on Machine Learning and Cybernetics
頁面3270-3274
頁數5
DOIs
出版狀態Published - 10 十一月 2009
事件2009 International Conference on Machine Learning and Cybernetics - Baoding, China
持續時間: 12 七月 200915 七月 2009

出版系列

名字Proceedings of the 2009 International Conference on Machine Learning and Cybernetics
6

Conference

Conference2009 International Conference on Machine Learning and Cybernetics
國家/地區China
城市Baoding
期間12/07/0915/07/09

指紋

深入研究「Pedestrian segmentation using deformable triangulation and kernel density estimation」主題。共同形成了獨特的指紋。

引用此