新的航空图像道路检测与跟踪算法

被引:2
作者
李书晓
常红星
机构
[1] 中国科学院自动化研究所综合信息中心
关键词
道路检测和跟踪; 最小化思想; 迭代算法;
D O I
10.13700/j.bh.1001-5965.2007.04.016
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
介绍了一种新的面向智能无人机应用的道路检测与跟踪算法.首先从电子道路地图中得到标示道路初始区域的合成图像,然后利用光学图像的距离变换图像、合成图像的边缘图像等信息把道路检测问题表述为一最优化问题,最后利用迭代算法解此问题得到路面区域.道路跟踪利用前一帧检测结果的预测值初始化其对应的优化问题.实验证明该方法具有较高的稳定性和适应能力.
引用
收藏
页码:445 / 449
页数:5
相关论文
共 11 条
[1]  
Automatic road extrac-tion from aerial images by probabilistic contour tracking//ICIP(3). Bicego M,Dalfini S,Vernazza G,et al. . 2003
[2]  
Machine Vision. Snyder E,Qi H. . 2004
[3]  
Adaptive real-time road detection usingneural networks//Proc 7th Int Conf on Intelligent Transpor-tation Systems. Foedisch M,Takeuchi A. . 2004
[4]  
A new watershed algo-rithm based on hill-climbing technique for image segmentation//IEEE TENCON. Rambabu C,Rathore T,Chakrabarti I. . 2003
[5]  
Vision and navigation for the CarnegieMellon Navlab. Thorpe C,Hebert M H. IEEE Transactions on Pattern Analysis andMachine Intelligence . 1988
[6]  
Road extraction by point-wise Gaussian models. Porikli F. The International Society for Optical Engineering . 2003
[7]  
Road network extraction inremote sensing by a Markov object process//ICIP(3). Lacoste C,Descombes X,Zerubia J. . 2003
[8]  
Road network detection bymathematical morphology//Proc of ISPRS Workshop on"3DGeospatial Data Production:Meeting Application Require-ments". Zhang C,Murai S,Baltsavias E. Paris:[s.n.] . 1999
[9]  
Vision-based road detection in automotivesystems:a real-time expectation-driven approach. Broggi A,Berte S. Journal ofArtificial Intelligence Research . 1995
[10]  
Road singularities detectionand classification//European Symposium on Artificial Neu-ral Networks. Leitao P,Tilie S,Mangeas M,et al. . 2003