作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (23): 204-206. doi: 10.3969/j.issn.1000-3428.2009.23.070

• 人工智能及识别技术 • 上一篇    下一篇

使用单目摄像头的实时行人计数算法

靳 晶,万卫兵,方 涛   

  1. (上海交通大学图像处理与模式识别研究所,上海 200240)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-12-05 发布日期:2009-12-05

Real-time Pedestrians Counting Algorithm Using Single Camera

JIN Jing, WAN Wei-bing, FANG Tao   

  1. (Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200240)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-12-05 Published:2009-12-05

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

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

中图分类号: