期刊文献+

基于全景鸟瞰视图的障碍物检测方法研究 被引量:3

Research of Obstacle Detection Based on Aerial Panorama Image
下载PDF
导出
摘要 目前,车载环视系统的障碍物检测大多采用基于特征的方法,主要针对车辆和行人等特定障碍物,不能完全消除障碍物对车辆行驶安全的威胁。采取基于运动的方法检测所有高于地面的障碍物。建立了平坦路面上的车辆运动模型,使用逆投影变换,推导出车辆运动参数、障碍物点高度和对应像素光流的关系。根据车载环视系统中相邻摄像头生成的俯视图存在重叠区域、重叠区域的障碍物特征点存在两个不同的光流矢量的特点,快速筛选出相交区域中的障碍点,并加速最优车辆运动参数的求取。最后使用运动参数生成运动补偿图像,检测图像中的所有障碍物点。实际道路测试证明,提出的算法在常规的路面环境下,能有效地标记出行驶过程中高于地面的所有障碍物。 At present,feature-based method is used to detect vehicles and pedestrians of panorama images,can not avoid all the threats of obstacles to driving.Different from the method above,we detected all the obstacles taller than the ground plane using motion-based method.First,we built the vehicle motion model,then deducd the relation-ship of vehicle motion,obstacle height and pixel optical-flow.Taking advantage of the fact that vertical views of adjacent cameras overlap each other and obstacle points in overlapping region have two different optical flows,we detected obstacles in intersection areas,fastened the solving of optimal motion parameters.At last,we detected all the obstacles using the motion compensated image.The vehicle experiments on the road demonstrate that the method proposed by us can detect all the obstacles taller than the ground effectively when vehicles are on the flat road.
出处 《计算机科学》 CSCD 北大核心 2014年第B11期78-82,共5页 Computer Science
基金 汽车移动物联网总体技术研究(2012ZX03005018) 智能交通创新服务系统(XDA06040300) 国家自然科学基金NSFC:面向"智慧工厂"的视觉目标检测和智能决策研究(61303174) 面向智慧交通的车联网高安全性内容保障技术研究与核心产品研发(2012B0910) 广东省教育部产学研结合项目资助
关键词 车载环视系统 逆投影变换 光流运动 自车运动估计 Vehicle around view system Inverse projection transformation Optical-flow Ego-motion estimation
  • 相关文献

参考文献11

  • 1Stein G P, Mano O,Shashua A. A robust method for computing vehicle ego-motion[C]//Proceedings of the IEEE Intelligent Vehicles Symposium, 2000( IV 2000). IEEE, 2000 : a62-a68.
  • 2Matthews N D, Greenway P. A Mathematical Framework for Robust Obstacle Detection Using Feature Matching [C] // Charnley D(ed) 1st IFAC International Workshop on Intelligent Autonomous Vehicles IAV. 1993:18 21.
  • 3Kriiger W, Robust real-time ground plane motion compensation.from a moving vehicle[J]. Machine Vision and Applications, 1999,11(4) :203 212.
  • 4Bar-Shalom Y, Li X R, Kirubarajan T. Estimation with applica- tions to tracking and navigatiom theory algorithms and software [M]. John Wiley Sons,2004.
  • 5Gandhi T, Trivedi M. Motion analysis of omni-directional video streams for a mobile sentry[C] // First ACM SIGMM interna- tional workshop on Video surveillance. ACM, 2003 : 49-58.
  • 6FUJITSU[OL]. http://www, fujitsu, corn/us/semiconductors/ gdc/products/omni, html.
  • 7Gandhi T, Trivedi M. Motion based vehicle surround analysis u- sing an omni-directional camera[C] // Intelligent Vehicles Sym- posium, 2004 IEEE. IEEE, 2004 : 560-565.
  • 8Broggi A, Bertozzi M, Fascioli A, et al. Shape-based pedestrian detection [C]//Proceedings of the IEEE Intelligent VehiclesSymposium. 2000:215-220.
  • 9Shashua A, Gdalyahu Y, Hayun G. Pedestrian detection for dri ving assistance systems: Single-frame classification and system level performance [C] // Intelligent Vehicles Symposium, 2004 IEEE. IEEE, 2004 1-6.
  • 10Bertozzi M, Broggi A. GOLD: A parallel real-time stereo vision system for generic obstacle and lane detection[J]. IEEE Trans actions on Image Processing, 1998,7 ( 1 ) : 62-81.

二级参考文献11

  • 1Kato K, Suzuki M, Fujita Y, et al. Image synthesis display method and apparatus for vehicle camera[P]. United States Patent 7, 139,412.
  • 2Luo Lin-bo. Low-cost and real-time implementation of bird's eye view system for camera-on vehicle[D]. Hanyang Univ. Ko- rea,Jan. 2012.
  • 3Liu Yu-chih, Lin Kai-ying, Chen Yong-sheng . Bird's eye View Vision System for Vehicle Surrounding Monitoring [C]//De- partment of Computer Science. National Chiao Tung University, Hsinchu, Taiwan. RobVis 2008 LNCS, 2008,4931 : 207-218.
  • 4Stenkula A. A Study of All-Around Enviroment Displaying Sys- tem for Heavy Vehicles[Z]. Royal Institute of Technology.
  • 5Zivkovic Z, Booij O. How did we built our hyperbolic mirror Fish-eye camera-practical issues and basic geometry[D]. Ne- therlands, May 2005.
  • 6Scaramuzzal D, Martinelli A, Siegwart R. A Flexible Technique for Accurate Fish-eye Camera Calibration and Structure from Motion[C]//Swiss Federal Institute of Technology Lausanne. ICVS, 2006.
  • 7Braner-Burchardt C, Voss K. A new algorithm to correct fish- eye and strong wide-angle-lens-distortion from single images[C]// Proc. ICIP. 2001:225-228.
  • 8Mallot H A, Buthoff H H, Little J J, et al. Inverse perspective mapping simplifies optical flow computation and obstacle detec- tion[J]. Biological Cybernetics, 1991,64:177-185.
  • 9Bertozzi M, Broggi A, Fascioli A. Stereo Inverse Perspective Mapping:Theory and Application[J]. Image and Vision Compu- ting, 1998,16 : 585-590.
  • 10Ying X, Hu Z. Catadioptric Camera Calibration Using Geomrtric Invariants[J]. IEEE Trans. on PAMI,2004,26(10) :1260-1271.

共引文献3

同被引文献28

引证文献3

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