期刊文献+

汽车智能辅助驾驶系统中的单目视觉导航技术 被引量:24

MONOCULAR VISION NAVIGATION IN VEHICLE INTELLIGENT AUXILIARY DRIVE SYSTEM
在线阅读 下载PDF
导出
摘要 在智能交通系统中 ,自动驾驶系统或许是最难于实现的技术之一 .许多学者努力想找到解决自动驾驶这个难题的方法 .本文介绍了一种新的思想和一些新的算法 ,它立足于单目视觉技术来实现车道保持和进行障碍物检测 ,进而力图解决视觉导航问题 .首先运用多阈值分割技术提取高速公路上当前车道的分道线 ,接着对分道线建立了圆锥曲线模型进行二维重建 .在道路模型的约束下 ,笔者提出方向分形维的算法确定前方车辆的位置 ,进而运用旋转 ,平移和缩放中心不变矩 (RTM)判断其真伪 ,最后采用有色噪声的卡尔曼滤波对真实障碍物进行跟踪 .本系统不但能根据分道线模型获得保持车道所需的方向信息 ,也能检测本车道前方障碍物而防止碰撞 .系统在四川和重庆的高速公路上以每小时 10 0公里的速度进行了试验 ,能圆满完成车道保持和障碍物检测的任务 . In the intelligent transportation systems, maybe the automatic navigation system is the most difficult problem. Many researchers try to find a way to carry out cruise assistance. This paper describes some new thoughts and algorithms for lane keeping and obstacle detection with a single view for cruise assistance. The system uses multi-threshold to extract the lane line. Then, the conic model is used to reconstruct them. Based on the image direction-fractal dimension and rotation, translation and magnification invariable central moment (RTM), it detects the obstacle in front in the same lane. At last, it uses Kalman filtering to track the obstacle. We have experimented the system with the algorithms on highway at 100km/h in Sichuan province and Chongqing city in China. The result shows that the algorithms can work perfectly.
出处 《机器人》 EI CSCD 北大核心 2003年第4期289-295,共7页 Robot
基金 国家自然科学基金项目资助 (编号 :6 96 74 0 12 )
关键词 多阈值分割 圆锥曲线模型 方向分形维 RTM 卡尔曼滤波 multi-threshold segmentation, conic model, direction-fractal dimension, RTM, Kalman filtering
  • 相关文献

参考文献19

  • 1Broggi A. Vision-based driving assistance[J]. IEEE Intelligent Systems, 1998, Nov/Dec, 22--23.
  • 2Murphy R R. Sensor and information fusion for improved visionbased vehicle guidance . IEEE Intelligent Systems, 1998,Nov/Dec, 49--56.
  • 3Franke U. Fast stereo based object detection for stop & go traffic . Proc 1996 IEEE Int' 1 Symp. Intelligent Vehicles .IEEE Press, 1996. 339--344.
  • 4Morizet-Mahoudeaux P. On-board and real-time expert control. IEEE Expert. Aug 1996. 71--81.
  • 5Thorpe C, Hebert M H. Vision and navigation for the carnegiemellonNavlab[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(3) : 362-- 373.
  • 6Turk M A, Morgenhaler D G. VITS-A vision system for autonomous land vehicle navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10 (3) : 342-- 361.
  • 7Kuan D, Phipps G. Autonomous robotic vehicle road following. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(5) : 648-- 658.
  • 8Kanatani K, Watanabe K. Reconstruction of 3-D road geometry from images for autonomous land vehicles[J]. IEEE Transactions on Robotics and Automation, 1990,6(1): 127--132.
  • 9Guiducci A. Parametric model of the perspective projection of a road with applications to lane keeping and 3D road reconstruction. Computer Vision and Image Understanding, 1999,73 (3) :414--427.
  • 10Giachetti A, Campani M. The use of optical flow for road navigation. IEEE Transactions on Robotics and Automation, 1998,14(1) : 34--48.

同被引文献200

引证文献24

二级引证文献105

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