基于Snakes模型的高分辨率遥感影像城区道路提取方法研究

大气与环境光学学报 ›› 2011, Vol. 6 ›› Issue (2): 106-.

基于Snakes模型的高分辨率遥感影像城区道路提取方法研究

施海亮1，周绍光2，徐勇3

(1 中国科学院通用光学定标与表征技术重点实验室，安徽合肥，230031；
2 河海大学测绘科学与工程系，江苏南京，210098；
3 香港中文大学地理与资源管理学系，香港)

收稿日期:2009-09-03 发布日期:2011-03-29
通讯作者: 施海亮（1983-），男，博士生，助理研究员，主要从事高分辨率光谱遥感技术方面的研究。 E-mail:hlshi@aiofm.ac.cn
作者简介:施海亮（1983-），男，博士生，助理研究员，主要从事高分辨率光谱遥感技术方面的研究。

Urban Road Detection of High Resolution Remote Sensing Images Based on Snakes Model

SHI Hai-liang1, ZHOU Shao-guang2, XU Yong3

(1 Key Laboratory of Optical Calibration and Characterization,CAS, Hefei 230031, China;
2 Department of Geomatics, Hohai University, Nanjing 210098, China;
3 Department of Geography and Resource Management, the Chinese University of Hong Kong, Hong Kong, China)

Received:2009-09-03 Online:2011-03-29

摘要/Abstract

摘要：

基于主动轮廓模型（Snakes）理论研究了高分辨率遥感影像道路的提取。针对高分辨率遥感影像中道路特征，通过改进现存方法得出更为适合道路提取的主动轮廓模型，并利用其完成道路提取工作。通过对1 m分辨率的IKONOS影像进行实验，结果表明该方法能够较好地提取出城市高分辨率影像中弯曲道路的完整对称边缘信息。

关键词: 高分辨率遥感影像, 道路提取, 主动轮廓模型

Abstract:

Based on the active contour model (Snakes) theory, the road extraction of high resolution remote sensing images is studied. According to characteristics of roads in high resolution remote sensing images, an active contour model more suited to the road extraction is drawed by improving the existing method, and the road extraction is completed. IKONOS image of 1 m resolution is studied, and results show that this method can be used to extract the road edge information of high resolution images.

Key words: high resolution remote sensing image, road extraction, active contour model

中图分类号:

TP391.41

施海亮周绍光徐勇. 基于Snakes模型的高分辨率遥感影像城区道路提取方法研究[J]. 大气与环境光学学报, 2011, 6(2): 106-.

SHI Hai-Liang, ZHOU Shao-Guang, XU Yong. Urban Road Detection of High Resolution Remote Sensing Images Based on Snakes Model[J]. Journal of Atmospheric and Environmental Optics, 2011, 6(2): 106-.

参考文献

[1] Shi Wenzhong, Zhu Changqing, Wang Yu. Road feature extraction from remotely sensed image: review and prospects [J]. Acta Geodaetica Et Cartographic Sinica, 2001, 30(3): 257-262(in Chinese).
史文中, 朱长青, 王昱. 从遥感影像提取道路特征的方法综述与展望 [J]. 测绘学报, 2001, 30(3): 257-262.
[2] Kass M, Witkin A, Terzopoulos D. Snakes: active contour models [J]. International Journal of Computer Vision, 1988, 1(4): 321-331.
[3] Gruen A, Li H H. Semi-automatic linear feature extraction by dynamic programming and LSB-Snakes [J]. Photogrammetric Engineering and Remote Sensing, 1997, 63(8): 985-995.
[4] Tang Liang. Studies on Extraction Techniques of Primary Objects from Urban Aerial Images [D]. Xi’an: Doctorial Dissertation of University of Xi’dian University, 2004(in Chinese).
唐亮. 城市航空影像关键地物提取技术研究 [D]. 西安: 西安电子科技大学博士论文, 2004.
[5] Zhou Shaoguang, Xin Li, Tian Linya. Detecting line segments by using the structural features of them in digital image [J]. Computer Engineering and Applications, 2004，40(22): 71-74(in Chinese).
周绍光, 辛莉, 田林亚. 利用数字影像中直线的结构特征检测直线段 [J]. 计算机工程与应用, 2004, 40(22): 71-74.
[6] Zhou Shaoguang, Shi Hailiang. New method for extracting straight line and linear band in remote sensing image [J]. Chinese Journal of Scientific Instrument, 2007, 28(3): 519-523(in Chinese).
周绍光, 施海亮. 遥感影像中直线和直线条带特征提取的新算法 [J]. 仪器仪表学报, 2007, 28(3): 519-523.
[7] Velasco F A, Marroquin J L. Growing snakes: active contours for complex topologies [J]. Pattern Recognition, 2003, 36(2): 475-482.
[8] Williams D J, Shah M. A fast algorithm for active contours and curvature estimation [J]. CVGIP: Image Understanding, 1992, 55(1): 14-26.