典型Otsu算法阈值比较及其SAR图像水域分割性能分析

安成锦; 牛照东; 李志军; 陈曾平

doi:10.3724/SP.J.1146.2009.01426

典型Otsu算法阈值比较及其SAR图像水域分割性能分析

doi: 10.3724/SP.J.1146.2009.01426

基金项目:

新世纪优秀人才支持计划项目(NCET-06-0921)资助课题

计量
- 文章访问数: 4391
- HTML全文浏览量: 230
- PDF下载量: 1199
- 被引次数: 0
出版历程
- 收稿日期: 2009-11-04
- 修回日期: 2010-03-03
- 刊出日期: 2010-09-19

Otsu Threshold Comparison and SAR Water Segmentation Result Analysis

摘要

摘要: 遥感图像中水域呈现低灰度、灰度起伏小特性。该文从实时性出发，采用1维Otsu算法分割SAR图像。证明了两种典型Otsu分割算法的阈值关系，提出了分割性能评估方法，并通过实测SAR图像对比分析了多阈值分割与单阈值递归分割的水域分割性能。结果表明，与单阈值递归分割相比，多阈值分割能够更好地提取水域轮廓，且漏警率低，可应用于桥梁自动目标识别和景象匹配等方面。
- 合成孔径雷达 /
- 水域分割 /
- 多阈值 /
- 递归分割
Abstract: Water shows low gray level and small wave from remote sensing images. As the fastest segmentation algorithm, 1D Otsu is used for Synthetic Aperture Radar (SAR) image segmentation. Level relation between multilevel Otsu and recursive Otsu is proved, and the evaluation of segmentation results is proposed, then quantitative comparison is given using SAR image. Results show that multilevel Otsu has better outline of water region, and can be used for SAR auto bridge recognition and scene matching.
- SAR /
- Water segmentation /
- Multilevel threshold /
- Recursive segmentation

HTML全文

参考文献(1)

吴一全，潘喆，吴文怡. 二维直方图区域协分阈值分割及快速递推算法[J].通信学报.2008, 29(4):77-83Wu Yi-quan, Pan Zhe, and Wu Wen-yi. Image thresholding based on two-dimensional histogram oblique segmentation and its fast recurring algorithm[J]. Journal on Communications, 2008, 29(4): 77-83.[2]康怀祺，陈保国. 基于分形的改进Otsu红外图像分割算法[J].红外技术，2009, 31(6): 359-361.Kang Huai-qi and Chen Bao-guo. Improved Otsu segmentation algorithm for IR image based on fractal algorithm[J]. Infrared Technology, 2009, 31(6): 359-361.[3]朱俊，王世唏，计科峰，粟毅. 一种适用于SAR图像的2维Otsu改进算法[J].中国图象图形学报.2009, 14(1):14-18Zhu Jun, Wang Shi-xi, Ji Ke-feng, and Su Yi. Improved 2D otsu algorithm for SAR images[J]. Journal of Image and Graphics, 2009, 14(1): 14-18.[4]Lee S U, Chung S Y, and Park R H. A comparative performance study of several global thresholding techniques for segmentation[J].Computer Vision, Graphics and Image Processing.1990, 52(2):171-190[5]王国有，邹玉兰，凌勇. 基于显著性的OTSU局部递归分割算法[J]. 华中科技大学学报(自然科学版), 2002, 30(9): 57-59.Wang Guo-you, Zou Yu-lan, and Ling Yong. An algorithm for salience-based local recursive Otsu segmentation[J]. Huazhong University of Science and Technology(Nature Science Edition), 2002, 30(9): 57-59.[6]陶文兵，刘李漫，田金文，柳健. 采用递归门限分析的红外目标分割[J].光电工程.2004, 31(10):46-49Tao Wen-bing, Liu Li-man, Tian Jin-wen, and Liu Jian. A recursive threshold analysis for infrared object segmentation[J]. Opto-Electronic Engineering, 2004, 31(10): 46-49.[7]Otsu N. A threshold selection method from gray-level histogram[J].IEEE Transactions on Systems, Man, and Cybernetics.1979, 9(1):62-66[8]高贵，匡纲要，李德仁. 高分辨率SAR图像分割及目标特性提取[J].宇航学报.2006, 27(2):238-244Gao Gui, Kuang Gang-yao, and Li De-ren. High resolution SAR image segmentation and targets feature extraction[J]. Journal of Astronautics, 2006, 27(2): 238-244.

施引文献

资源附件(0)

访问统计