標題: 1-D Integral Image for Enhancing Efficiency and Effectiveness of Probabilistic Occupancy Map-Based People Localization Approach
作者: Lin, Yen-Shuo
Chen, Hua-Tsung
Hwang, Jenq-Neng
Hsiao, Ching-Ju
Chuang, Jen-Hui
交大名義發表
資訊工程學系
National Chiao Tung University
Department of Computer Science
關鍵字: Multiple cameras;probabilistic occupancy map;people localization;efficient algorithm;video surveillance
公開日期: 2016
摘要: The popularity of vision-based surveillance systems arouses much research attention in improving the accuracy and efficiency of people localization. Using probabilistic occupancy map (POM) becomes one of the mainstream approaches to people localization due to its great localization accuracy under severe occlusions and lighting changes. However, to enable the usage of rectangular human models and the subsequent 2-D integral image computation, it is assumed that videos are taken at head or eye level. Even so, the computation complexity is still high. Moreover, surveillance videos are often taken from security cameras located at a higher-up location with an oblique viewing angle, so that human models may be quadrilateral and the pixel-based 2-D integral image cannot be utilized. Accordingly, we propose the use of 1-D integral images which are produced for foreground object(s) in an image along equally-spaced line samples originated from the vanishing point of vertical lines (VPVL). Experimental results show that the proposed approach does improve the efficiency and effectiveness of the POM approach in more general camera configurations.
URI: http://dx.doi.org/10.1117/12.2244978
http://hdl.handle.net/11536/135254
ISBN: 978-1-5106-0503-9
978-1-5106-0504-6
ISSN: 0277-786X
DOI: 10.1117/12.2244978
期刊: EIGHTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2016)
Volume: 10033
Appears in Collections:Conferences Paper