一種結(jié)合顏色特征的PolSAR圖像分類方法
發(fā)布時間:2019-02-19 22:16
【摘要】:為了提出一種顏色特征與極化特征相結(jié)合的極化SAR圖像分類方法,首先,通過極化目標(biāo)分解得到極化特征向量;然后,采用最佳指數(shù)模型方法生成極化SAR的假彩色合成圖像,并提取顏色特征向量;最后,將這2種特征組成綜合特征向量,利用SVM方法進(jìn)行分類。利用Radar Sat-2的Pol SAR數(shù)據(jù)進(jìn)行了SAR圖像分類實(shí)驗(yàn),并對分類結(jié)果進(jìn)行定性和定量比較分析。實(shí)驗(yàn)結(jié)果表明,顏色特征的加入能有效提高極化SAR圖像的分類精度。
[Abstract]:In order to propose a polarization SAR image classification method which combines color features with polarization features, firstly, polarization feature vectors are obtained by polarimetric target decomposition. Then, the pseudocolor synthetic image of polarized SAR is generated by the best exponential model method, and the color feature vector is extracted. Finally, the two features are composed of the synthetic feature vectors and classified by the SVM method. The experiment of SAR image classification is carried out by using Pol SAR data of Radar Sat-2, and the classification results are compared and analyzed qualitatively and quantitatively. Experimental results show that the addition of color features can effectively improve the classification accuracy of polarized SAR images.
【作者單位】: 遼寧工程技術(shù)大學(xué)測繪與地理科學(xué)學(xué)院;洛陽理工學(xué)院土木工程學(xué)院;
【基金】:國家自然科學(xué)基金青年科學(xué)基金項(xiàng)目“MRF模型的車載全景視覺位姿估計最優(yōu)化方法研究”(編號:41501504) 遼寧省教育廳一般項(xiàng)目“復(fù)雜運(yùn)動場景下衛(wèi)星視頻的超分辨率重建方法研究”(編號:LJYL011)共同資助
【分類號】:TN957.52
本文編號:2426936
[Abstract]:In order to propose a polarization SAR image classification method which combines color features with polarization features, firstly, polarization feature vectors are obtained by polarimetric target decomposition. Then, the pseudocolor synthetic image of polarized SAR is generated by the best exponential model method, and the color feature vector is extracted. Finally, the two features are composed of the synthetic feature vectors and classified by the SVM method. The experiment of SAR image classification is carried out by using Pol SAR data of Radar Sat-2, and the classification results are compared and analyzed qualitatively and quantitatively. Experimental results show that the addition of color features can effectively improve the classification accuracy of polarized SAR images.
【作者單位】: 遼寧工程技術(shù)大學(xué)測繪與地理科學(xué)學(xué)院;洛陽理工學(xué)院土木工程學(xué)院;
【基金】:國家自然科學(xué)基金青年科學(xué)基金項(xiàng)目“MRF模型的車載全景視覺位姿估計最優(yōu)化方法研究”(編號:41501504) 遼寧省教育廳一般項(xiàng)目“復(fù)雜運(yùn)動場景下衛(wèi)星視頻的超分辨率重建方法研究”(編號:LJYL011)共同資助
【分類號】:TN957.52
【相似文獻(xiàn)】
相關(guān)期刊論文 前3條
1 劉忠偉,章毓晉;十種基于顏色特征圖像檢索算法的比較和分析[J];信號處理;2000年01期
2 鄧斌;張基宏;;基于顏色特征及運(yùn)動信息提取關(guān)鍵幀[J];深圳信息職業(yè)技術(shù)學(xué)院學(xué)報;2012年01期
3 徐建國,馬萬良,梁永全,房玉峰;基于顏色特征的圖象索引和檢索方法[J];山東礦業(yè)學(xué)院學(xué)報(自然科學(xué)版);1999年03期
相關(guān)碩士學(xué)位論文 前2條
1 張悅;顏色的層次性編碼研究[D];上海交通大學(xué);2014年
2 張智;城市視頻監(jiān)控中并行檢索系統(tǒng)的研究與實(shí)現(xiàn)[D];武漢理工大學(xué);2014年
,本文編號:2426936
本文鏈接:http://sikaile.net/kejilunwen/xinxigongchenglunwen/2426936.html
最近更新
教材專著