新的航空图像道路检测与跟踪算法

李书晓; 常红星

新的航空图像道路检测与跟踪算法

中国科学院自动化研究所综合信息中心,北京 100080

详细信息

作者简介:
李书晓(1981-),男,河南南阳人,博士生,shuxiao.li@ia.ac.cn.

中图分类号: TP 391
计量
- 文章访问数: 2076
- HTML全文浏览量: 60
- PDF下载量: 1099
- 被引次数: 0
出版历程
- 收稿日期: 2006-05-25
- 网络出版日期: 2007-04-30

Novel road detection and tracking algorithm for aerial images

IISRC, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China

摘要

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.
- 道路检测和跟踪 /
- 最小化思想 /
- 迭代算法
Abstract: A novel road detection and tracking algorithm for intelligent pilotless aircraft applications was illustrated. Initially, synthetic image was extracted from electron road maps to initialize the road areas. Then, road detection was expressed as a minimizing problem by means of using distance transformation of input image and edges of synthetic image. Finally an iterative algorithm took shape and was applied to solve the minimizing problem mentioned above to abtain road regions. Road tracking method initialized its corresponding minimizing problem utilizing the prediction image out of the detection results of previous video frames. Concerning the function of this method, strict experimental results are presented to demonstrate the satisfactory performances of our approach with its highly stability and adaptability.
- road detection and tracking /
- minimization philosophy /
- iterative algorithm

HTML全文

参考文献(1)

[1] Fortier A, Ziou D, Armenakis C,et al. Survey of work on road extraction in aerial and satellite images .Technical Report N. 247, Université de Sherbrooke, 2000 [2] Lai S, Yung C. Lane detection by orientation and length discrimination[J].IEEE Transactions on Systems, Man and Cybernetics, 2000, 30(4):539-548 [3] Zhang C, Murai S, Baltsavias E.Road network detection by mathematical morphology Proc of ISPRS Workshop on "3D Geospatial Data Production:Meeting Application Requirements".Paris:, 1999:185-200 [4] Leitao P, Tilie S, Mangeas M,et al. Road singularities detection and classification European Symposium on Artificial Neural Networks. Bruges:d-side publi, 2003:301-306 [5] Foedisch M,Takeuchi A.Adaptive real-time road detection using neural networks Proc 7th Int Conf on Intelligent Transportation Systems. Washington D C:IEEE, 2004:3-6 [6] Porikli F. Road extraction by point-wise Gaussian models[J]. The International Society for Optical Engineering, 2003, 5093:758-764 [7] Thorpe C, Hebert M H. Vision and navigation for the Carnegie Mellon Navlab[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988,10(3):362-373 [8] Bicego M, Dalfini S, Vernazza G, et al. Automatic road extraction from aerial images by probabilistic contour tracking ICIP(3). Barcelona:IEEE,2003:585-588 [9] Lacoste C, Descombes X, Zerubia J. Road network extraction in remote sensing by a Markov object process ICIP(3).Barcelona:IEEE, 2003:1017-1020 [10] Rambabu C, Rathore T,Chakrabarti I. A new watershed algorithm based on hill-climbing technique for image segmentation IEEE TENCON.Bangalore:IEEE, 2003 [11] Snyder E, Qi H. Machine Vision[M]. Cambridge University Press, 2004:197-201 [12] Broggi A, Berte S.Vision-based road detection in automotive systems:a real-time expectation-driven approach[J]. Journal of Artificial Intelligence Research, 1995, 3:325-348

施引文献

资源附件(0)

访问统计