期刊文献+

基于机器视觉的道路上前方多车辆探测方法研究 被引量:1

Study on Method of Multiple Vehicle Detection and Tracking Based on Vision
下载PDF
导出
摘要 本文提出了一种基于车辆特征的方法识别和跟踪前方的车辆。首先,利用车辆底部存在阴影的特征,在图像中获得可能的车辆存住区域。然后,通过分形维数计算车辆的纹理特征,排除非车辆区域。最后,利用车辆的边缘信息,通过投影变换方法,对候选区域内的车辆进行定位。此外,利用NMI特征法对定位的车辆进行确认。该算法对不同环境和光照条件下的车辆图片进行了测试,以及在高速公路上进行了实时跟踪,具有较好的鲁棒性和可靠性。 This paper describes vehicle detection and tracking method based on vehicle feature. First, some AOI regions of vehicles are obtained by vehicle underneath shadow. Second, the no-vehicle regions are filtered by texture feature of AOI based on DBC. At last, the edge information is used to located vehicles by project transform, and we can locate the vehicle in the potential vehicle region. At the same time, a verification algorithm is proposed to check the correctness of vehicle based on NMI feature, It has a good result to locate vehicle in different illumination and road environment.
出处 《ITS通讯》 2005年第2期28-31,共4页
关键词 视觉 车辆探测 底部阴影 盒子维 车辆边缘 NMI特征 车辆 探测方法 机器视觉 道路 Vision, vehicle detection, shadow and edge, Fractal Box Dimension, NMI feature
  • 引文网络
  • 相关文献

同被引文献11

  • 1崔高健,黄银花,田原嫄.基于立体机器视觉的前方车辆探测[J].计算机测量与控制,2005,13(9):890-891. 被引量:2
  • 2Gideon P. Stein, Mano O, Shashua A. Vision-based ACC with a single camera: bounds on range and range rate accuracy[C]. Intelligent Vehicles Sympo- sium, Columbus: Proceedings, IEEE. 9-11 June 2003 : 120-125. 被引量:1
  • 3Bertozzi M, Broggi A. GOLD: A parallel real-time stereo vision system for generic obstacle and lane detection[J]. Image Processing, IEEE Transactions on,1998,7(1) :62-81. 被引量:1
  • 4Dean A, Pomerleau DA, Ralph H. Rapidly adaptinglateral position handler[R]. Detroit, USA, Proceed- ings of IEEE Symposium on Intelligent Vehicles, 1995.506-511. 被引量:1
  • 5Kreucher C, Lakshmanan S. LANA A lane extrac- tion algorithm that uses frequency domain features[J].Robotics and Automation, IEEE Transactions on, 1999,15(2) : 343-350. 被引量:1
  • 6Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C] /// Computer Vision and PatternRecognition (CVPR), Proceed- ings of the 2001 IEEE Computer Society Conference on. Hawaii:IEEE, 2001. 被引量:1
  • 7WU Chifeng,LIN Chengjian, LEE Chiyung. Apply- ing a functional neurofuzzy networkto real-time lane detection and front-vehicle distance measurement [C]. IEEE Tramsaetopms on Systems, Man, and Cybernetics-partc : Applications and Reviews, 2012, 42f4). 577-589. 被引量:1
  • 8Bella F, Russo R. A collision warning system for rear-end collision:a driving simulatorstudy[J]. Pro- cedia-Social and Behavioral Sciences, 2011,20 ( 11 ) : 676-686. 被引量:1
  • 9李文波,王立研.一种基于Adaboost算法的车辆检测方法[J].长春理工大学学报(自然科学版),2009,32(2):292-295. 被引量:17
  • 10魏武,龚树锋,龚树超.一种改进的基于视频的车辆检测与识别方法[J].计算机测量与控制,2010,18(1):20-22. 被引量:15

引证文献1

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部