基于圖與改進(jìn)Wishart距離的極化SAR分類(lèi)研究
發(fā)布時(shí)間：2019-05-16 15:16
【摘要】：極化合成孔徑雷達(dá)(Polarimetric Synthetic Aperture Radar,簡(jiǎn)稱極化SAR)是一種先進(jìn)的獲取遙感信息的手段,通過(guò)測(cè)量地面每一個(gè)分辨單元在四種不同的極化組合下的散射特性,從而得到目標(biāo)對(duì)應(yīng)的極化信息,極化SAR比傳統(tǒng)單極化SAR所記錄的地物目標(biāo)電磁散射特征信息更完整。極化SAR分類(lèi)的意義重要在于它既能作為一個(gè)中間步驟,為極化SAR的解譯提供幫助,協(xié)助極化SAR圖像提取邊緣信息、檢測(cè)目標(biāo)、識(shí)別目標(biāo),也可能是用戶最終需求。傳統(tǒng)的極化SAR分類(lèi)均是以單個(gè)像素為分類(lèi)單元,而極化SAR特有的相干斑噪聲對(duì)以像素為分類(lèi)單元的分類(lèi)結(jié)果影響很大,因此本文構(gòu)造包含點(diǎn)和含權(quán)值的邊的全連圖,對(duì)極化SAR數(shù)據(jù)先進(jìn)行過(guò)分割,減小相干斑噪聲對(duì)分類(lèi)的影響,然后以分割后的區(qū)域?yàn)榉诸?lèi)單元,結(jié)合數(shù)據(jù)的極化特征和結(jié)構(gòu)信息實(shí)現(xiàn)對(duì)極化SAR數(shù)據(jù)的分類(lèi)研究,文章主要包含了以下三方面的內(nèi)容:1.提出一種基于圖方法的極化SAR分割方法。該方法中先提取像素點(diǎn)的極化特征,結(jié)合極化SAR數(shù)據(jù)的Wishart距離構(gòu)建圖,然后基于圖對(duì)極化SAR數(shù)據(jù)進(jìn)行初始分割,最后對(duì)基于圖方法初始分割后的區(qū)域進(jìn)行一個(gè)分層合并,按照區(qū)域大小的等級(jí)設(shè)定不同的合并策略,得到一個(gè)相對(duì)均勻的分割結(jié)果。該算法引入了應(yīng)用在自然圖像上的分割算法圖方法,結(jié)合極化SAR數(shù)據(jù)的特點(diǎn)改進(jìn)權(quán)值的計(jì)算方法,合并過(guò)程中考慮了像素的空間信息,思路簡(jiǎn)明,便于理解。2.提出一種基于圖方法過(guò)分割的極化SAR有監(jiān)督分類(lèi)方法。該方法利用了上面介紹的分割方法得到分割結(jié)果,以過(guò)分割后的區(qū)域?yàn)榉诸?lèi)單元,利用Wishart距離計(jì)算每個(gè)區(qū)域與各個(gè)訓(xùn)練類(lèi)別之間的距離,對(duì)每個(gè)區(qū)域進(jìn)行類(lèi)別劃分。該分類(lèi)方法為基于區(qū)域的有監(jiān)督分類(lèi),減小了傳統(tǒng)分類(lèi)結(jié)果中出現(xiàn)雜點(diǎn)的情況,并且提高了分類(lèi)結(jié)果的區(qū)域一致性,而且提高了極化SAR的分類(lèi)精度。3.提出一種基于圖方法過(guò)分割以及改進(jìn)的Wishart距離的極化SAR二分樹(shù)分類(lèi)方法。該方法同上面提到的有監(jiān)督分類(lèi)方法一樣,以圖方法分割得到的區(qū)域?yàn)榉诸?lèi)單元,計(jì)算每?jī)蓚�(gè)區(qū)域之間的不相似度構(gòu)建二分樹(shù),最終得到的分類(lèi)樹(shù)的個(gè)數(shù)即類(lèi)別個(gè)數(shù)。該方法中用到的不相似度計(jì)算方式為改進(jìn)的Wishart距離,考慮到區(qū)域的尺寸大小。該方法減少了分類(lèi)結(jié)果中出現(xiàn)局部收斂的情況,減小了一般無(wú)監(jiān)督方法中出現(xiàn)雜點(diǎn)的現(xiàn)象,且提升了分類(lèi)精度。
[Abstract]:Polarization synthetic Aperture Radar (Polarimetric Synthetic Aperture Radar,) is an advanced method to obtain remote sensing information. The scattering characteristics of each resolution unit on the ground under four different polarization combinations are measured. Thus, the polarization information corresponding to the target is obtained, and the electromagnetic scattering characteristic information of the ground object recorded by the polarization SAR is more complete than that recorded by the traditional unipolar SAR. The significance of polarization SAR classification is that it can be used as an intermediate step to help the interpretation of polarization SAR, assist polarization SAR images to extract edge information, detect targets, identify targets, and may also be the final requirements of users. The traditional polarization SAR classification takes a single pixel as the classification unit, and the speckle noise unique to the polarization SAR has a great influence on the classification results with pixels as the classification unit. Therefore, this paper constructs a fully connected graph containing points and edges with weights. Firstly, the polarimetric SAR data is segmented to reduce the influence of speckle noise on the classification, and then the polarimetric SAR data classification is realized by taking the segmented region as the classification unit and combining the polarization characteristics and structural information of the data. The article mainly contains the following three aspects: 1. A polarization SAR segmentation method based on graph method is proposed. In this method, the polarization features of pixels are extracted, and the Wishart distance of polarized SAR data is combined to construct the graph, and then the polarized SAR data is initially segmented based on the graph. Finally, a hierarchical merging of the regions after the initial segmentation based on the graph method is carried out. Different merging strategies are set according to the level of region size, and a relatively uniform segmentation result is obtained. The algorithm introduces the graph method of segmentation algorithm applied to natural images, and improves the calculation method of weights according to the characteristics of polarized SAR data. The spatial information of pixels is considered in the process of merging, and the train of thought is simple and easy to understand. 2. A polarization SAR supervised classification method based on graph method is proposed. In this method, the segmentation results are obtained by using the segmentation method described above. Taking the over-segmented region as the classification unit, the distance between each region and each training category is calculated by using Wishart distance, and each region is classified. The classification method is region-based supervised classification, which reduces the occurrence of miscellaneous points in the traditional classification results, improves the regional consistency of the classification results, and improves the classification accuracy of polarized SAR. 3. A polarization SAR binary tree classification method based on graph method oversegmentation and improved Wishart distance is proposed. This method is the same as the supervised classification method mentioned above, taking the region segmented by graph method as the classification unit, and calculating the dissimilarity between each two regions to construct the binary tree, and the number of classification trees is the number of categories. The dissimilarity calculation method used in this method is the improved Wishart distance, which takes into account the size of the region. This method reduces the local convergence in the classification results, reduces the phenomenon of miscellaneous points in the general unsupervised method, and improves the classification accuracy.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN957.52
本文編號(hào)：2478371
[Abstract]:Polarization synthetic Aperture Radar (Polarimetric Synthetic Aperture Radar,) is an advanced method to obtain remote sensing information. The scattering characteristics of each resolution unit on the ground under four different polarization combinations are measured. Thus, the polarization information corresponding to the target is obtained, and the electromagnetic scattering characteristic information of the ground object recorded by the polarization SAR is more complete than that recorded by the traditional unipolar SAR. The significance of polarization SAR classification is that it can be used as an intermediate step to help the interpretation of polarization SAR, assist polarization SAR images to extract edge information, detect targets, identify targets, and may also be the final requirements of users. The traditional polarization SAR classification takes a single pixel as the classification unit, and the speckle noise unique to the polarization SAR has a great influence on the classification results with pixels as the classification unit. Therefore, this paper constructs a fully connected graph containing points and edges with weights. Firstly, the polarimetric SAR data is segmented to reduce the influence of speckle noise on the classification, and then the polarimetric SAR data classification is realized by taking the segmented region as the classification unit and combining the polarization characteristics and structural information of the data. The article mainly contains the following three aspects: 1. A polarization SAR segmentation method based on graph method is proposed. In this method, the polarization features of pixels are extracted, and the Wishart distance of polarized SAR data is combined to construct the graph, and then the polarized SAR data is initially segmented based on the graph. Finally, a hierarchical merging of the regions after the initial segmentation based on the graph method is carried out. Different merging strategies are set according to the level of region size, and a relatively uniform segmentation result is obtained. The algorithm introduces the graph method of segmentation algorithm applied to natural images, and improves the calculation method of weights according to the characteristics of polarized SAR data. The spatial information of pixels is considered in the process of merging, and the train of thought is simple and easy to understand. 2. A polarization SAR supervised classification method based on graph method is proposed. In this method, the segmentation results are obtained by using the segmentation method described above. Taking the over-segmented region as the classification unit, the distance between each region and each training category is calculated by using Wishart distance, and each region is classified. The classification method is region-based supervised classification, which reduces the occurrence of miscellaneous points in the traditional classification results, improves the regional consistency of the classification results, and improves the classification accuracy of polarized SAR. 3. A polarization SAR binary tree classification method based on graph method oversegmentation and improved Wishart distance is proposed. This method is the same as the supervised classification method mentioned above, taking the region segmented by graph method as the classification unit, and calculating the dissimilarity between each two regions to construct the binary tree, and the number of classification trees is the number of categories. The dissimilarity calculation method used in this method is the improved Wishart distance, which takes into account the size of the region. This method reduces the local convergence in the classification results, reduces the phenomenon of miscellaneous points in the general unsupervised method, and improves the classification accuracy.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN957.52
【共引文獻(xiàn)】
相關(guān)期刊論文 前7條
1 謝昌志;尹東;孫濤;;基于塊匹配的迭代濾波SAR圖像去噪[J];光電工程;2015年01期
2 管濤;牛曉太;;α穩(wěn)定分布及其在斑點(diǎn)抑制中的應(yīng)用研究[J];計(jì)算機(jī)科學(xué);2014年S1期
3 俞曉妮;;基于SAR圖像的艦船檢測(cè)算法[J];艦船科學(xué)技術(shù);2014年12期
4 董純柱;胡利平;朱國(guó)慶;殷紅成;;地面車(chē)輛目標(biāo)高質(zhì)量SAR圖像快速仿真方法[J];雷達(dá)學(xué)報(bào);2015年03期
5 王茜;韓慶邦;趙勝永;朱昌平;徐杉;;波紋管注漿缺陷超聲檢測(cè)方法[J];實(shí)驗(yàn)技術(shù)與管理;2014年02期
6 李鵬;王萍;楊正銀;;機(jī)載合成孔徑雷達(dá)測(cè)圖技術(shù)研究[J];測(cè)繪;2014年02期
7 王云艷;何楚;涂峰;陳東;廖明生;;特征選擇雙層SVM的融合算法用于極化SAR圖像分類(lèi)[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2015年09期
相關(guān)博士學(xué)位論文 前1條
1 胡安洲;主客觀一致的圖像感知質(zhì)量評(píng)價(jià)方法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年
相關(guān)碩士學(xué)位論文 前6條
1 吳浩杰;具有移變特性的星機(jī)雙基地SAR成像算法研究[D];電子科技大學(xué);2011年
2 車(chē)云龍;基于RadarSat-2全極化SAR的船舶檢測(cè)[D];大連海事大學(xué);2014年
3 項(xiàng)德良;SAR圖像相似度評(píng)估技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年
4 陳文婷;SAR圖像艦船目標(biāo)特征提取與分類(lèi)識(shí)別方法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年
5 崔建楠;雙極化SAR數(shù)據(jù)在古河道探測(cè)中的應(yīng)用[D];吉林大學(xué);2015年
6 謝昌志;SAR圖像相干斑抑制及艦船檢測(cè)方法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2015年
，本文編號(hào)：2478371
本文鏈接：http://sikaile.net/kejilunwen/wltx/2478371.html
最近更新
教材專(zhuān)著
