SAR images classification method based on Dempster-Shafer theory and kernel estimate |
| |
作者单位: | He Chu(Electronic Information School, Wuhan Univ., Wuhan 430079, P.R. China) ;
Xia Guisong(Electronic Information School, Wuhan Univ., Wuhan 430079, P.R. China) ;
Sun Hong(Electronic Information School, Wuhan Univ., Wuhan 430079, P.R. China) ; |
| |
摘 要: | To study the scene classification in the Synthetic Aperture Radar (SAR) image, a novel method based on kernel estimate, with the Markov context and Dempster-Shafer evidence theory is proposed. Initially, a nonparametric Probability Density Function (PDF) estimate method is introduced, to describe the scene of SAR images. And then under the Markov context, both the determinate PDF and the kernel estimate method are adopted respectively, to form a primary classification. Next, the primary classification results are fused using the evidence theory in an unsupervised way to get the scene classification. Finally, a regularization step is used, in which an iterated maximum selecting approach is introduced to control the fragments and modify the errors of the classification. Use of the kernel estimate and evidence theory can describe the complicated scenes with little prior knowledge and eliminate the ambiguities of the primary classification results. Experimental results on real SAR images illustrate a rather impressive performance.
|
收稿时间: | 3 March 2006. |
SAR images classification method based on Dempster-Shafer theory and kernel estimate |
| |
Authors: | He Chu Xia Guisong Sun Hong |
| |
Institution: | Electronic Information School, Wuhan Univ., Wuhan 430079, P.R. China |
| |
Abstract: | To study the scene classification in the Synthetic Aperture Radar (SAR) image, a novel method based on kernel estimate, with the Markov context and Dempster-Shafer evidence theory is proposed. Initially, a nonparametric Probability Density Function (PDF) estimate method is introduced, to describe the scene of SAR images. And then under the Markov context, both the determinate PDF and the kernel estimate method are adopted respectively, to form a primary classification. Next, the primary classification results are fused using the evidence theory in an unsupervised way to get the scene classification. Finally, a regularization step is used, in which an iterated maximum selecting approach is introduced to control the fragments and modify the errors of the classification. Use of the kernel estimate and evidence theory can describe the complicated scenes with little prior knowledge and eliminate the ambiguities of the primary classification results. Experimental results on real SAR images illustrate a rather impressive performance. |
| |
Keywords: | Image classification Synthetic aperture Radar (SAR) Dempster-Shafer theory Kernel estimate |
本文献已被 万方数据 ScienceDirect 等数据库收录! |
| 点击此处可从《系统工程与电子技术(英文版)》浏览原始摘要信息 |
| 点击此处可从《系统工程与电子技术(英文版)》下载免费的PDF全文 |
|