本文關(guān)鍵詞：基于多重信息融合的高分辨率遙感影像道路信息提取，由筆耕文化傳播整理發(fā)布。

基于多重信息融合的高分辨率遙感影像道路信息提取

Road Extraction from High-resolution Remote Sensing Images Based on Multiple Information Fusion

[1] [2] [3] [4] [5]

LI Xiao-feng, ZHANG Shu-qing, HAN Fu-wei, QIN Xi-wen, YU Huan（ 1. Northeast Institute of Geography and Agroecology , Chinese Academy of Sciences, Changchun 130012, China; 2.

[1]中國(guó)科學(xué)院東北地理與農(nóng)業(yè)生態(tài)研究所,吉林長(zhǎng)春130012; [2]中國(guó)科學(xué)院研究生院,北京100039; [3]國(guó)家海洋環(huán)境監(jiān)測(cè)中心,遼寧大連116023

文章摘要：在高分辨率遙感影像上進(jìn)行道路提取一直被認(rèn)為是一項(xiàng)具有重要意義但很困難的工作。尤其一些與道路光譜相近的地物，分類(lèi)后與道路相互連接，難以區(qū)分�；诿鏍畹缆泛瓦吘壪嗷ヲ�(yàn)證和輔助的思想，提出一種高分辨率遙感影像上提純道路信息的方法。該方法首先在面狀和邊緣兩個(gè)方面同時(shí)提高提取精度，然后由他們之間的邏輯互運(yùn)算分割道路與非道路對(duì)象，并應(yīng)用有效的形狀指數(shù)（如：極慣性矩和狹長(zhǎng)度指數(shù)）刻畫(huà)和區(qū)分道路與非道路面狀目標(biāo)（如樓房等），，最終達(dá)到提純道路的目的。實(shí)驗(yàn)結(jié)果表明了本文方法在去除非道路目標(biāo)，提純道路網(wǎng)絡(luò)方面的有效性。

Abstr：Road extraction from high-resolution remote sensing images has been considered to be a significant but very difficult task. Especially the spectrum of some buildings is similar with that of roads ,which makes the surfaces being connect with each other after classification and difficult to be distinguished. Based on the cooperation between road surfaces and edges, this paper presents an approach to purify roads from hlgh-resolution remote sensing images. Firstly, we try to improve the extraction accuracy of road surfaces and edges respectively. The logic cooperation between these two binary images is used to separate road and non-road objects. Then the road objects are confirmed by the cooperation between surfaces and edges. And the effective shape indices （e. g. polar moment of inertia and narrow extent index） are applied to eliminate non-road objects. So the road information is refined. The experiments indicate that the proposed approach is efficient for eliminating non-road information and extracting road information from high-resolution remote sensing image.

文章關(guān)鍵詞：

Keyword：:road extraction high-resolution remote sensing image cooperation polar moment of inertia narrow extent index

相關(guān)文章：

[1] 激光掃描與光學(xué)影像數(shù)據(jù)配準(zhǔn)的研究進(jìn)展   《測(cè)繪通報(bào)》  2008年02期
[2] 山區(qū)LiDAR高程精度野外檢驗(yàn)的一種新方法   《測(cè)繪通報(bào)》  2008年02期
[3] 高分辨率衛(wèi)星遙感影像的姿態(tài)角常差檢校   《測(cè)繪學(xué)報(bào)》  2008年01期
[4] 基于預(yù)存儲(chǔ)權(quán)值矩陣的多尺度Hough變換直線提取算法   《測(cè)繪學(xué)報(bào)》  2008年01期
[5] 遙感影像地形校正物理模型的簡(jiǎn)化與改進(jìn)   《測(cè)繪學(xué)報(bào)》  2008年01期
[6] 一種基于道路網(wǎng)絡(luò)模型減少車(chē)輛軌跡數(shù)據(jù)量的算法   《測(cè)繪學(xué)報(bào)》  2008年01期
[7] SPOT衛(wèi)星影像在貴陽(yáng)市總規(guī)修編中的應(yīng)用   《城市勘測(cè)》  2008年01期
[8] 遙感圖像優(yōu)化迭代非監(jiān)督分類(lèi)方法在流域植被分類(lèi)中的應(yīng)用   《城市勘測(cè)》  2008年01期
[9] 基于數(shù)學(xué)形態(tài)學(xué)的土地利用動(dòng)態(tài)可視化   《大地測(cè)量與地球動(dòng)力學(xué)》  2008年01期
[10] 一種全自動(dòng)提取居民地的方法   《地理空間信息》  2008年01期

課題項(xiàng)目：中國(guó)科學(xué)院知識(shí)創(chuàng)新工程重要方向項(xiàng)目（KZCX3-SW-356）;全球環(huán)境基金（GEF）項(xiàng)目（GF/2712-03）.

作者信息：會(huì)員可見(jiàn)

  本文關(guān)鍵詞：基于多重信息融合的高分辨率遙感影像道路信息提取，由筆耕文化傳播整理發(fā)布。