本文選題：極化合成孔徑雷達(dá)　切入點(diǎn)：建筑物提取　出處：《遙感技術(shù)與應(yīng)用》2017年03期 　論文類型：期刊論文

【摘要】：極化SAR圖像中建筑物相關(guān)特征的不充分利用將影響建筑物提取的有效性或引發(fā)錯(cuò)誤。為解決該問題,提出了一種利用多尺度SVM-CRF模型的極化SAR圖像建筑物提取方法。在圖像最優(yōu)分割的基礎(chǔ)上,將基于像素的SVM-CRF模型擴(kuò)展到面向?qū)ο蟮亩喑叨萐VM-CRF模型,使之能同時(shí)有效地描述建筑物突出的"面狀"特征及其層次、空間上下文相關(guān)性。同時(shí),考慮對(duì)建筑物描述特征利用不充分所引起的類別模糊問題,使用隨機(jī)森林算法實(shí)現(xiàn)多特征的選擇,形成更有效的特征組合以優(yōu)化SVM-CRF模型中的特征向量。采用Oberpfaffenhofen地區(qū)E-SAR數(shù)據(jù)進(jìn)行了實(shí)驗(yàn),定性和定量的結(jié)果驗(yàn)證了該方法的有效性和準(zhǔn)確性。
[Abstract]:The inadequate use of building-related features in polarized SAR images will affect the effectiveness of building extraction or cause errors. In this paper, a building extraction method based on multi-scale SVM-CRF model for polarimetric SAR image is proposed. Based on the optimal segmentation of the image, the pixel based SVM-CRF model is extended to the object-oriented multi-scale SVM-CRF model. It can also effectively describe the prominent "surface" features of buildings and their hierarchy, spatial contextual relevance. At the same time, it considers the problem of category ambiguity caused by inadequate use of building description features. The stochastic forest algorithm is used to select multiple features, and a more effective feature combination is formed to optimize the feature vectors in the SVM-CRF model. The experiments are carried out using E-SAR data in the Oberpfaffenhofen region. The qualitative and quantitative results show that the method is effective and accurate.
【作者單位】： 新疆氣象局氣象服務(wù)中心;中國(guó)地質(zhì)大學(xué)(武漢)信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(41301477、41471355) 中國(guó)博士后科學(xué)基金面上項(xiàng)目(2012M521497)資助
【分類號(hào)】：P237;TN957.52
，

本文編號(hào)：1613489