基于模糊和最小二乘的SAR图像线特征提取

王艳丽; 陈哲

基于模糊和最小二乘的SAR图像线特征提取

王艳丽,
陈哲

北京航空航天大学自动化科学与电气工程学院

基金项目: 航空基础科学基金资助项目(99E51018)

详细信息

作者简介:
王艳丽(1977-),女,陕西西安人,博士生,100083,北京.

中图分类号: TP 391.41
计量
- 文章访问数: 2458
- HTML全文浏览量: 28
- PDF下载量: 1435
- 被引次数: 0
出版历程
- 收稿日期: 2002-01-16
- 网络出版日期: 2003-04-30

Extraction of Linear Features of SAR Images Based on Fuzzy and Least Square

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics

摘要

摘要: 针对合成孔径雷达(SAR, Synthetic Aperture Radar)图像的特点,提出一种线特征提取算法.该算法首先抑制相干斑噪声,然后对SAR图像进行模糊变换和增强,再基于假设的SAR图像灰度模型,用最小二乘法设计出低通和高通滤波器,最后检测出线特征散点,并进行连接,得到SAR图像的线特征图.实验证明本算法抗噪声干扰,边缘定位精度达到1个像素.
- 合成孔径雷达 /
- 特征抽取 /
- 最小二乘法 /
- 线特征 /
- 模糊增强
Abstract: A linear feature extraction method is proposed for SAR image. Firstly, the speckle noise in the radar image is filtered out. Secondly, the SAR image is processed by fuzzy transition and enhancement. Then, the low-pass and high-pass filters are designed by the least squares methods and the gradient strength map and direction map are acquired. Lastly, the gradient profile maximum method is adopted to detect feature points, which are connected to form the linear feature map of the SAR image. Simulation results show that the proposed method has the characteristic of anti-noise, the precision of positioning can reach 1 pixel.
- synthetic aperture radar /
- feature extraction /
- least squares methods /
- linear feature /
- fuzzy enhancement

HTML全文

参考文献(1)

[1] 汪洋.景象匹配算法研究及软件开发. 北京:北京航空航天大学自动化科学与电气工程学院,2000 Wang Yang. Research on the algorithms in SMNS and development of software. Beijing:School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, 2000(in Chinese) [2] 周蓉蓉,陈刚,王正志.一种基于小波变换的SAR图像边缘检测算法[J]. 遥感信息,2000,(1):17~19 Zhou Rongrong, Chen Gang, Wang Zhengzhi. A wavelet based edge detection method for SAR image[J]. Remote Sensing Information, 2000, (1):17~19(in Chinese) [3] 张天序,李巍,桑农,等. 雷达与光学景象共性特征提取与匹配算法研究[J]. 红外与激光工程,1996,25(3):15~20 Zhang Tianxu, Li Wei, Sang Nong, et al. An algorithmic approach to extracting and matching the common characteristics of radar and optical scenes[J]. Infrared and Laser Engineering, 1996,25(3):15~20 (in Chinese) [4] Hellwich O. Detection of linear objects in ERS-1 SAR image using neural network technology. Surface and Atmospheric Remote Sensing:Technologies, Data Analysis and Interpretation. IGARSS, 1994, 4:1886~1888 [5] 张祖勋,张剑清.数字摄影测量学[M].武汉:武汉测绘科技大学出版社,2000 Zhang Zuxun, Zhang Jianqing. Digital photographic mapping[M]. Wuhan:Wuhan University Publishing House, 2000(in Chinese) [6] 郭华东.雷达对地观测理论与应用[M].北京:科学出版社,2000 Guo Huadong. Radar for earth observation:theory and applications[M]. Beijing:Science Press,2000(in Chinese) [7] 李铁军.实时下视景象匹配算法的研究. 郑州:郑州测绘学院, 1999 Li Tiejun. A study on real time down looking scene matching algorithm. Zhengzhou:Zhengzhou Institute of Surveying and Mapping, 1999(in Chinese) [8] 陈鹰,李铁军,熊兴华.带约束条件的特征与最小二乘影像匹配[J]. 中国图像图形学报,1998,3(4):299~303 Chen Ying, Li Tiejun, Xiong Xinghua. A feature based and least square image matching with constrains[J]. Journal of Image and Graphics, 1998,3(4):299~303(in Chinese) [9] Li Tiejun, Wang Yanli, Chen Zhe. Linear feature extraction for infrared image. Image Extraction, Segmentation, and Recognition. SPIE,2001, 4550:281~286

施引文献

资源附件(0)

访问统计