基于MSRC的遙感影像面向?qū)ο蠓诸愌芯?/H1>
發(fā)布時間：2019-04-18 11:33
【摘要】：遙感影像數(shù)據(jù)具有覆蓋范圍大、信息客觀真實(shí)、成本低、獲取方便等優(yōu)點(diǎn)，已經(jīng)在各個領(lǐng)域得到了廣泛應(yīng)用。對于交通行業(yè)，，利用高分辨率遙感技術(shù)，并結(jié)合已有的交通信息采集手段，可以為城市交通監(jiān)測、路網(wǎng)規(guī)劃與建設(shè)、交通路網(wǎng)運(yùn)行狀態(tài)判別、行業(yè)管理、領(lǐng)導(dǎo)決策等綜合決策服務(wù)提供有效的技術(shù)手段。但隨著遙感影像分辨率的不斷提高，地物信息的提取技術(shù)發(fā)展相對滯后，遙感技術(shù)在交通行業(yè)的應(yīng)用仍處于初級階段。 高分辨率遙感影像相對于中、低分辨率遙感影像具有更為豐富的空間信息、紋理信息和地物幾何信息。隨著遙感技術(shù)的不斷發(fā)展，遙感影像的分辨率的不斷提高，影像數(shù)據(jù)的信息提取和分類技術(shù)面臨著新的問題和挑戰(zhàn)。傳統(tǒng)的基于像元的分類方法由于其分類精度的限制已經(jīng)不能滿足遙感技術(shù)發(fā)展的需求，因此面向?qū)ο蟮姆诸惣夹g(shù)應(yīng)運(yùn)而生。面向?qū)ο蠓诸惣夹g(shù)在處理遙感影像時，最小信息提取單元不再是單個像元，而是光譜和紋理特征相似的“均質(zhì)對象”，因此可以充分利用包含光譜特征在內(nèi)的其他結(jié)構(gòu)信息，大幅度地提高分類精度與效率。 在面向?qū)ο蠓诸惣夹g(shù)的基礎(chǔ)上，①采用標(biāo)記分水嶺算法獲取影像對象。提出了一種溢水模型，并用該模型修改標(biāo)記產(chǎn)生方式，同時利用邊緣檢測手段，提高微弱邊緣的提取能力且極大的抑制過分割現(xiàn)象；②對獲得的區(qū)域?qū)ο筇崛“ü庾V信息、紋理信息、邊緣幾何信息等特征，通過不同的特征組合分類實(shí)驗(yàn)，分析出不同特征對各類地物的分類效果，得出最佳的特征組合；③利用自適應(yīng)權(quán)重的多重稀疏表示分類算法（Multiple Sparse Representation Classification approach,MSRC）自適應(yīng)地調(diào)整各特征的權(quán)重，并獲得最終分類結(jié)果。定量和定性的實(shí)驗(yàn)結(jié)果對比分析可以看出，基于MSRC的面向?qū)ο蠓诸惙椒芨浞值睦貌煌卣鞯膮f(xié)同作用，整體分類精度和Kappa系數(shù)得到了明顯提高，取得了較好的分類結(jié)果。
[Abstract]:Remote sensing image data has been widely used in various fields because of its advantages such as large coverage, objective and real information, low cost, convenient access and so on. For the traffic industry, the use of high-resolution remote sensing technology, combined with the existing means of traffic information collection, can be used for urban traffic monitoring, road network planning and construction, traffic network operational status discrimination, industry management, Comprehensive decision-making services, such as leadership decision-making, provide effective technical means. However, with the continuous improvement of remote sensing image resolution, the development of feature information extraction technology lags behind, and the application of remote sensing technology in traffic industry is still in the initial stage. Compared with middle and low resolution remote sensing images, high resolution remote sensing images have more abundant spatial information, texture information and geometric information. With the development of remote sensing technology and the improvement of remote sensing image resolution, the information extraction and classification technology of image data is facing new problems and challenges. The traditional pixel-based classification method has been unable to meet the needs of the development of remote sensing technology because of the limitation of its classification accuracy, so object-oriented classification technology emerges as the times require. Object-oriented classification technology in processing remote sensing images, the minimum information extraction unit is no longer a single pixel, but a "homogeneous object" with similar spectral and texture features, so other structural information, including spectral features, can be fully utilized. The accuracy and efficiency of classification are greatly improved. On the basis of object-oriented classification (OO), the image object is obtained by using the marked watershed algorithm. In this paper, a overflow model is proposed, and the label generation mode is modified by this model. At the same time, the edge detection method is used to improve the ability of weak edge extraction and greatly restrain the over-segmentation phenomenon. (2) feature extraction includes spectral information, texture information, edge geometry information and so on. Through different feature combination classification experiments, the classification effect of different features on all kinds of ground objects is analyzed, and the best feature combination is obtained. (3) the weight of each feature is adjusted adaptively by (Multiple Sparse Representation Classification approach,MSRC (multiple sparse representation algorithm of adaptive weight), and the final classification result is obtained. The comparative analysis of quantitative and qualitative experimental results shows that the object-oriented classification method based on MSRC can make full use of the synergetic effect of different features, and the overall classification accuracy and Kappa coefficient have been significantly improved, and better classification results have been obtained.
【學(xué)位授予單位】：湖南工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 王建仁;魏龍;段剛龍;黃梯云;;自適應(yīng)學(xué)習(xí)的多特征元素協(xié)同表示分類算法[J];計(jì)算機(jī)應(yīng)用;2014年04期
2 黃秋燕;肖鵬峰;馮學(xué)智;王珂;;結(jié)合相位一致與全變差模型的高分辨率遙感圖像邊緣檢測[J];中國圖象圖形學(xué)報(bào);2014年03期
3 陳林林;楊晨;李敏娟;徐宏偉;;基于形態(tài)學(xué)梯度重建的分水嶺算法改進(jìn)研究[J];中國印刷與包裝研究;2013年04期
4 江怡;梅小明;鄧敏;陳杰;陳鐵橋;;一種結(jié)合形態(tài)濾波和標(biāo)記分水嶺變換的遙感圖像分割方法[J];地理與地理信息科學(xué);2013年02期
5 段菲;章毓晉;;基于多尺度稀疏表示的場景分類[J];計(jì)算機(jī)應(yīng)用研究;2012年10期
6 段剛龍;魏龍;李妮;;基于自適應(yīng)權(quán)重的多重稀疏表示分類算法[J];計(jì)算機(jī)工程與應(yīng)用;2014年08期
7 王珂;肖鵬峰;馮學(xué)智;吳桂平;李暉;;基于改進(jìn)二維離散希爾伯特變換的圖像邊緣檢測方法[J];測繪學(xué)報(bào);2012年03期
8 時愈;汪國有;劉建國;;基于拓?fù)浣Y(jié)構(gòu)的分水嶺算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年11期
9 肖鵬峰;馮學(xué)智;趙書河;鄧敏;佘江峰;;一種基于相位一致的高分辨率遙感圖像特征檢測方法[J];遙感學(xué)報(bào);2007年03期
10 王文宇;李博;;基于eCogniton的高分辨率遙感圖像的自動識別分類技術(shù)[J];北京建筑工程學(xué)院學(xué)報(bào);2006年04期
相關(guān)博士學(xué)位論文 前3條
1 陳杰;高分辨率遙感影像面向?qū)ο蠓诸惙椒ㄑ芯縖D];中南大學(xué);2010年
2 崔衛(wèi)紅;基于圖論的面向?qū)ο蟮母叻直媛视跋穹指罘椒ㄑ芯縖D];武漢大學(xué);2010年
3 陳忠;高分辨率遙感圖像分類技術(shù)研究[D];中國科學(xué)院研究生院（遙感應(yīng)用研究所）;2006年
本文編號：2460011
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2460011.html
[Abstract]:Remote sensing image data has been widely used in various fields because of its advantages such as large coverage, objective and real information, low cost, convenient access and so on. For the traffic industry, the use of high-resolution remote sensing technology, combined with the existing means of traffic information collection, can be used for urban traffic monitoring, road network planning and construction, traffic network operational status discrimination, industry management, Comprehensive decision-making services, such as leadership decision-making, provide effective technical means. However, with the continuous improvement of remote sensing image resolution, the development of feature information extraction technology lags behind, and the application of remote sensing technology in traffic industry is still in the initial stage. Compared with middle and low resolution remote sensing images, high resolution remote sensing images have more abundant spatial information, texture information and geometric information. With the development of remote sensing technology and the improvement of remote sensing image resolution, the information extraction and classification technology of image data is facing new problems and challenges. The traditional pixel-based classification method has been unable to meet the needs of the development of remote sensing technology because of the limitation of its classification accuracy, so object-oriented classification technology emerges as the times require. Object-oriented classification technology in processing remote sensing images, the minimum information extraction unit is no longer a single pixel, but a "homogeneous object" with similar spectral and texture features, so other structural information, including spectral features, can be fully utilized. The accuracy and efficiency of classification are greatly improved. On the basis of object-oriented classification (OO), the image object is obtained by using the marked watershed algorithm. In this paper, a overflow model is proposed, and the label generation mode is modified by this model. At the same time, the edge detection method is used to improve the ability of weak edge extraction and greatly restrain the over-segmentation phenomenon. (2) feature extraction includes spectral information, texture information, edge geometry information and so on. Through different feature combination classification experiments, the classification effect of different features on all kinds of ground objects is analyzed, and the best feature combination is obtained. (3) the weight of each feature is adjusted adaptively by (Multiple Sparse Representation Classification approach,MSRC (multiple sparse representation algorithm of adaptive weight), and the final classification result is obtained. The comparative analysis of quantitative and qualitative experimental results shows that the object-oriented classification method based on MSRC can make full use of the synergetic effect of different features, and the overall classification accuracy and Kappa coefficient have been significantly improved, and better classification results have been obtained.
【學(xué)位授予單位】：湖南工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 王建仁;魏龍;段剛龍;黃梯云;;自適應(yīng)學(xué)習(xí)的多特征元素協(xié)同表示分類算法[J];計(jì)算機(jī)應(yīng)用;2014年04期
2 黃秋燕;肖鵬峰;馮學(xué)智;王珂;;結(jié)合相位一致與全變差模型的高分辨率遙感圖像邊緣檢測[J];中國圖象圖形學(xué)報(bào);2014年03期
3 陳林林;楊晨;李敏娟;徐宏偉;;基于形態(tài)學(xué)梯度重建的分水嶺算法改進(jìn)研究[J];中國印刷與包裝研究;2013年04期
4 江怡;梅小明;鄧敏;陳杰;陳鐵橋;;一種結(jié)合形態(tài)濾波和標(biāo)記分水嶺變換的遙感圖像分割方法[J];地理與地理信息科學(xué);2013年02期
5 段菲;章毓晉;;基于多尺度稀疏表示的場景分類[J];計(jì)算機(jī)應(yīng)用研究;2012年10期
6 段剛龍;魏龍;李妮;;基于自適應(yīng)權(quán)重的多重稀疏表示分類算法[J];計(jì)算機(jī)工程與應(yīng)用;2014年08期
7 王珂;肖鵬峰;馮學(xué)智;吳桂平;李暉;;基于改進(jìn)二維離散希爾伯特變換的圖像邊緣檢測方法[J];測繪學(xué)報(bào);2012年03期
8 時愈;汪國有;劉建國;;基于拓?fù)浣Y(jié)構(gòu)的分水嶺算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年11期
9 肖鵬峰;馮學(xué)智;趙書河;鄧敏;佘江峰;;一種基于相位一致的高分辨率遙感圖像特征檢測方法[J];遙感學(xué)報(bào);2007年03期
10 王文宇;李博;;基于eCogniton的高分辨率遙感圖像的自動識別分類技術(shù)[J];北京建筑工程學(xué)院學(xué)報(bào);2006年04期
相關(guān)博士學(xué)位論文 前3條
1 陳杰;高分辨率遙感影像面向?qū)ο蠓诸惙椒ㄑ芯縖D];中南大學(xué);2010年
2 崔衛(wèi)紅;基于圖論的面向?qū)ο蟮母叻直媛视跋穹指罘椒ㄑ芯縖D];武漢大學(xué);2010年
3 陳忠;高分辨率遙感圖像分類技術(shù)研究[D];中國科學(xué)院研究生院（遙感應(yīng)用研究所）;2006年
本文編號：2460011
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2460011.html
