Abstract:
Based on background segmentation by mixed model of Gaussian distributions, a real-time people counter using blobs is built to get the pedestrian flow passing through a gate or a door. The proposed algorithm mounts the camera vertically and sets a region of interest to detect and track pedestrians. A queue module is built to help the system achieve good performance. Experimental results show that effective detection and counting accuracy can be achieved.
Key words:
single camera,
pedestrians counting,
Gaussian model
摘要: 为解决智能视频监控系统通道入口处的行人计数问题,设计在高斯背景建模下的行人检测计数算法。在该算法中,摄像头垂直放置在入口处的门顶上。为了降低计算复杂度,提高计算精度,设置一个感兴趣的检测区域,在该区域中通过对行人的检测及跟踪进行计数,并采用队列模型处理以提高检测效果。实验结果表明,该算法可以有效地对入口行人进行检测计数。
关键词:
单目摄像头,
行人计数,
高斯模型
CLC Number:
JIN Jing; WAN Wei-bing; FANG Tao. Real-time Pedestrians Counting Algorithm Using Single Camera[J]. Computer Engineering, 2009, 35(23): 204-206.
靳 晶;万卫兵;方 涛. 使用单目摄像头的实时行人计数算法[J]. 计算机工程, 2009, 35(23): 204-206.