| Summary: | 碩士 === 國立交通大學 === 多媒體工程研究所 === 103 === With the popularity of vision-based surveillance system, the improvement in accuracy and efficiency of people localization has got lots of attention. Recently, using probabilistic occupancy map (POM) becomes one of main approaches to people localization because of its great localization accuracy under severe occlusions and lighting changes. To estimate the probabilities of people locations, 2-D integral images are used iteratively, which would be time-consuming during the process of the POM-based approach. To enhance the efficiency of the POM approach, we propose the use of 1-D integral images which are produced for foreground object 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 of the POM approach, with little sacrifice in the accuracy of people localization.
|
|---|
