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 ›› 2012, Vol. 38 ›› Issue (15): 175-178. doi: 10.3969/j.issn.1000-3428.2012.15.049

• 人工智能及识别技术 • 上一篇    下一篇

基于改进特征跟踪的客流量统计

金 鑫a,梁雪春a,宫宁生b   

  1. (南京工业大学 a. 自动化与电气工程学院;b. 电子与信息工程学院,南京 211816)
  • 收稿日期:2011-09-23 出版日期:2012-08-05 发布日期:2012-08-05
  • 作者简介:金 鑫(1989-),男,硕士研究生,主研方向:模式识别,图像处理;梁雪春,教授、博士;宫宁生,教授
  • 基金资助:
    江苏省博士后科研资助计划基金资助项目(1001027B);江苏省高校自然科学研究基金资助项目(09KJB510002)

Passenger Flow Statistics Based on Improved Feature Tracking

JIN Xin a, LIANG Xue-chun a, GONG Ning-sheng b   

  1. (a. College of Automation and Electrical b. College of Electronics and Information Engineering, Nanjing University of Technology, Nanjing 211816, China)
  • Received:2011-09-23 Online:2012-08-05 Published:2012-08-05

摘要: 为实现多目标的精确跟踪,提出一种基于视频客流量的跟踪计数方法。利用图像差分法提取运动目标,对差分图像进行形态学处理,使用连通域分析创建人体结点,得到目标的形心,采用向前优先搜索像素点的原则搜索下一帧图像的所有像素点,通过搜索到的像素点确定目标的新中心位置,根据目标中心与计数线的关系进行计数。实验结果表明,该方法简单可行,统计数据具有较高的正确率。

关键词: 视频监控, 客流量统计, 差分法, 形态学处理, 连通域分析, 多目标跟踪

Abstract: In order to solve the problem about multitarget tracking, this paper proposes a new video-based traffic tracking counting method. The frame difference method is used to extract the moving target and the image needs morphological processing. Connected domain analysis is applied to create the human node and get the node’s centroid. According to the nodes’ centroids which are created in the list, first search forward is used. All target pixels are searched in the next frame which are used to determine the new position of the object in the video. Experimental results show that the method is simple and feasible, and achieves statistical data with high accuracy.

Key words: video surveillance, passenger flow statistics, difference method, morphologic processing, connected domain analysis, multitarget tracking

中图分类号: