本文關(guān)鍵詞：影像與LiDAR數(shù)據(jù)信息融合復(fù)雜場(chǎng)景下的道路自動(dòng)提取，由筆耕文化傳播整理發(fā)布。

影像與LiDAR數(shù)據(jù)信息融合復(fù)雜場(chǎng)景下的道路自動(dòng)提取

Automatic Road Extraction in Complex Scenes Based on Information Fusion from LiDAR Data and Remote Sensing Imagery

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

LI Yijing1＇2, HU Xiangyun1 , ZHANG Jianqing1 , JIANG Wanshou3 , ZHANG Yongjun（1. School of Remote Sensing and Information Engineering, Wuhan University, Wuiqan 430079, China~

[1]武漢大學(xué)遙感信息工程學(xué)院,湖北武漢430079; [2]南昌大學(xué)建筑工程學(xué)院,江西南昌330031; [3]武漢大學(xué)測(cè)繪遙感信息工程國(guó)家重點(diǎn)實(shí)驗(yàn)室,湖北武漢430079

文章摘要：城區(qū)的道路自動(dòng)提取受場(chǎng)景復(fù)雜度的影響一直是極具挑戰(zhàn)的任務(wù)，尤其是陰影和遮擋較嚴(yán)重地區(qū)的道路提取難度較大。結(jié)合LiDAR數(shù)據(jù)和高分辨率遙感影像，提出一種自動(dòng)道路提取方法。該方法首先對(duì)濾波后的點(diǎn)云強(qiáng)度信息獲取初始道路中線(xiàn)及道路關(guān)鍵點(diǎn)；將地面點(diǎn)云強(qiáng)度、離散度及高分辨率遙感影像光譜數(shù)據(jù)多重信息融合建立道路模型，并以?xún)?yōu)化后的道路關(guān)鍵點(diǎn)作為種子點(diǎn)利用動(dòng)態(tài)規(guī)劃計(jì)算模型最優(yōu)解，進(jìn)一步提取道路網(wǎng)。試驗(yàn)表明，該方法在城市復(fù)雜場(chǎng)景下的自動(dòng)提取主要道路是有效的。

Abstr：Automatic road extraction from remote sensing images in urban area has been a very challenging task due to the complexity of the scene, especially in the occluded or shadowed areas. An integrated method to fuse LiDAR data and high resolution imagery for automatic extraction of road centrelines is proposed. Firstly, theLiDAR point cloud is filtered to get the ground points whose intensity data is used to detect initial road centrelines and key points of the roads. A road model is then built on the intensity and dispersion of the ground points as well as spectral information obtained from the high resolution image. Based on the model, the dynamic programming algorithm is applied to find the optimal road centrelines linking the key points which are selected by evaluation. The experimental results indicate its effectiveness in automatic road extraction in urban and complex scenes.

文章關(guān)鍵詞：

Keyword：:road extraction LiDAR remote sensing imagery information fusion dynamic programming

課題項(xiàng)目：國(guó)家自然科學(xué)基金（41171292;61172175）;國(guó)家973計(jì)劃（2012CB719904）

作者信息：會(huì)員可見(jiàn)

  本文關(guān)鍵詞：影像與LiDAR數(shù)據(jù)信息融合復(fù)雜場(chǎng)景下的道路自動(dòng)提取，，由筆耕文化傳播整理發(fā)布。