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 ›› 2011, Vol. 37 ›› Issue (21): 141-143. doi: 10.3969/j.issn.1000-3428.2011.21.048

• 人工智能及识别技术 • 上一篇    下一篇

自适应车流方向的跨道行人检测

许崇博1,王美华1,谭志标2   

  1. (1. 华南农业大学信息学院,广州 510642;2. 广东鑫程电子科技有限公司,广州 510100)
  • 收稿日期:2011-04-21 出版日期:2011-11-05 发布日期:2011-11-05
  • 作者简介:许崇博(1984-),男,硕士研究生,主研方向:模式识别,图像处理;王美华,副教授;谭志标,硕士
  • 基金资助:
    广东省科技计划基金资助项目(2008B080701005);广东省科技计划国际合作基金资助项目(2010B080701070)

Crossing Pedestrians Detection Adapted to Traffic Flow Direction

XU Chong-bo 1, WANG Mei-hua 1, TAN Zhi-biao 2   

  1. (1. College of Information, South China Agricultural University, Guangzhou 510642, China; 2. Guangdong Gold Sunny Electronic Technology Co. Ltd., Guangzhou 510100, China)
  • Received:2011-04-21 Online:2011-11-05 Published:2011-11-05

摘要: 针对视频交通事件监控中的行人检测问题,提出一种自适应车流方向的跨道行人检测算法。利用运动历史图像计算画面中物体的运动方向,通过学习获得运动参考方向场,并对运动目标进行跟踪。依据参考方向场分析其轨迹的走向,以确定运动目标是否发生跨道行为。实验结果表明,该算法能适应车流方向并有效检测跨道行人,具有较好的实时性和较高的检测成功率。

关键词: 行人检测, 智能监控, 车流方向, 运动历史图像, 参考方向场

Abstract: For video traffic events detection, a novel algorithm to detect crossing pedestrians is researched, which can be adaptive to the direction of traffic flows. It calculates the motion directions of objects in the video by Motion History Image(MHI) motion history images. A referenced motion direction field is obtained at learning step. When an object is tracked, its trajectory will be analyzed on line. Its motion direction is compared with the direction defined by the referenced motion direction field, which results in whether it is a crossing pedestrian. Experimental results show that this algorithm has the ability to adapt the traffic flow direction, and that it can run at real time with great accuracy.

Key words: pedestrian detection, intelligent monitoring, traffic flow direction, Motion History Image(MHI), referenced direction field

中图分类号: