期刊名称：International Journal of Image Processing (IJIP)
电子版ISSN：1985-2304
出版年度：2013
卷号：7
期号：1
页码：1-16
出版社：Computer Science Journals
摘要：The demand for automatic counting of pedestrians at event sites, buildings, or streets has been increased. Existing systems for counting pedestrians in video sequences have a problem that counting accuracy degrades when many pedestrians coexist and occlusion occurs frequently. In this paper, we introduce a method of clustering optical flows extracted from pedestrians in video frames to improve the counting accuracy. The proposed method counts the number of pedestrians by using pre-learned statistics, based on the strong correlation between the number of optical flow clusters and the actual number of pedestrians. We evaluate the accuracy of the proposed method using several video sequences, focusing in particular on the effect of parameters for optical flow clustering. We find that the proposed method improves the counting accuracy by up to 25% as compared with a non-clustering method. We also report that using a clustering threshold of angles less than 1 degree is effective for enhancing counting accuracy. Furthermore, we compare the performance of two algorithms that use feature points and lattice points when optical flows are detected. We confirm that the counting accuracy using feature points is higher than that using lattice points especially when the number of occluded pedestrians increases.
关键词：Pedestrian Counting; Video Processing; Optical Flow; Clustering.
