發(fā)布時(shí)間：2018-06-07 21:23

  本文選題：LIDAR + 地物分類(lèi)　； 參考：《中北大學(xué)》2015年碩士論文

【摘要】：激光掃描與測(cè)距技術(shù)（Light Detection and Ranging,LIDAR)可以快速、主動(dòng)、自動(dòng)獲取大范圍地物密集采樣點(diǎn)的三維信息，彌補(bǔ)了傳統(tǒng)攝影測(cè)量技術(shù)獲取地物信息單一的缺陷，自上世紀(jì)九十年代投入商業(yè)使用以來(lái)，已被廣泛地應(yīng)用于構(gòu)造數(shù)字地形模型（DigitalTerrain Model,DTM）與數(shù)字城市模型、突發(fā)自然災(zāi)害評(píng)估、道路與電力線(xiàn)勘探、生物量估計(jì)等領(lǐng)域。如何利用LIDAR系統(tǒng)提供的光譜、紋理、高程、強(qiáng)度等多源信息精確快速地獲取地物分布信息已成為當(dāng)前亟需解決的問(wèn)題。 本文針對(duì)機(jī)載LIDAR數(shù)據(jù)地物分類(lèi)領(lǐng)域內(nèi)的特征提取、特征重要性分析、分類(lèi)器構(gòu)建、分類(lèi)結(jié)果類(lèi)別混淆出現(xiàn)原因及分類(lèi)精度優(yōu)化方法進(jìn)行了深入的研究和探討。論文主要研究?jī)?nèi)容包括： 1.針對(duì)以往在對(duì)LIDAR數(shù)據(jù)進(jìn)行地物分類(lèi)時(shí)，特征選取缺乏依據(jù)，主要依賴(lài)個(gè)人經(jīng)驗(yàn)與偏好，并由此導(dǎo)致分類(lèi)精度未能達(dá)到最優(yōu)的問(wèn)題，首先，，在進(jìn)行特征提取時(shí)，對(duì)LIDAR點(diǎn)云與影像數(shù)據(jù)所提供的特征進(jìn)行較為完備的提�。黄浯�，在隨機(jī)森林分類(lèi)算法框架下，利用袋外樣本的特征置換重要性測(cè)度評(píng)估特征對(duì)分類(lèi)精度的影響程度；最后，選擇對(duì)分類(lèi)精度影響較大特征代替原有的高維特征進(jìn)行分類(lèi)。 2.從算法原理上，對(duì)支持向量機(jī)、隨機(jī)森林、馬爾科夫隨機(jī)場(chǎng)、D-S證據(jù)理論等LIDAR數(shù)據(jù)地物分類(lèi)領(lǐng)域內(nèi)常用的分類(lèi)算法的優(yōu)缺點(diǎn)進(jìn)行分析，通過(guò)實(shí)驗(yàn)驗(yàn)證構(gòu)建最適合LIDAR數(shù)據(jù)的分類(lèi)方案。 3.針對(duì)分類(lèi)器分類(lèi)結(jié)果存在分類(lèi)精度低、不符合真實(shí)地物特性、不符合人們觀測(cè)習(xí)慣等缺陷，研究分析分類(lèi)結(jié)果中易出現(xiàn)混淆的類(lèi)型、位置；利用目標(biāo)邊緣測(cè)度分析混淆出現(xiàn)的原因；根據(jù)各類(lèi)混淆出現(xiàn)的原因，利用地物類(lèi)間空間限制構(gòu)建具有針對(duì)性的混淆目標(biāo)類(lèi)別修正算法，改善分類(lèi)結(jié)果。
[Abstract]:The laser scanning and ranging technology, Light Detection and ranging list (LIDARL), can acquire 3D information of dense sampling points in a large area quickly, actively and automatically, which makes up for the single defect of traditional photogrammetry technology in obtaining ground object information. Since it was put into commercial use in 1990s, it has been widely used in the construction of digital terrain models (DTM) and digital city models, sudden natural disaster assessment, road and power line exploration, biomass estimation and so on. How to use the spectrum, texture, elevation, intensity and other multi-source information provided by the LIDAR system to accurately and quickly obtain the distribution information of ground objects has become a problem that needs to be solved. This paper aims at feature extraction in the field of airborne LIDAR data in the field of ground object classification. The analysis of feature importance, the construction of classifier, the cause of classification confusion and the optimization method of classification accuracy are discussed. The main contents of this paper are as follows: 1. In order to solve the problem that the feature selection of LIDAR data is lack of basis, it mainly depends on personal experience and preference, and thus leads to the classification accuracy can not reach the optimal. Firstly, in feature extraction, The features provided by LIDAR point cloud and image data are extracted completely. Secondly, under the framework of stochastic forest classification algorithm, the importance measure of feature replacement of out-of-bag samples is used to evaluate the degree of influence of features on classification accuracy. Select the feature which has a great influence on the classification accuracy instead of the original high dimensional feature to classify. 2. Based on the principle of the algorithm, the advantages and disadvantages of the common classification algorithms in the field of LIDAR data object classification, such as support vector machine, random forest, Markov random field D-S evidence theory, are analyzed. Through the experimental verification to construct the most suitable classification scheme for LIDAR data. 3. The classification results of the classifier have some defects, such as low classification accuracy, not accord with the real features of ground objects, and do not accord with the observation habits of people, so the types and positions that are easily confused in the classification results are studied and analyzed. The reason of confusion is analyzed by using target edge measure, and according to the cause of all kinds of confusion, a modified algorithm is constructed to improve the classification result by using space restriction between ground objects.
【學(xué)位授予單位】：中北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TN249

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳松堯;程新文;;機(jī)載LIDAR系統(tǒng)原理及應(yīng)用綜述[J];測(cè)繪工程;2007年01期

2 張小紅,劉經(jīng)南;機(jī)載激光掃描測(cè)高數(shù)據(jù)濾波[J];測(cè)繪科學(xué);2004年06期

3 李學(xué)友;IMU/DGPS輔助航空攝影測(cè)量綜述[J];測(cè)繪科學(xué);2005年05期

4 馮琰;郭容寰;程遠(yuǎn)達(dá);;基于機(jī)載LIDAR技術(shù)快速建立3維城市模型研究[J];測(cè)繪與空間地理信息;2008年04期

5 李征航,張小紅,樓益棟,朱智勤;一種解算GPS短基線(xiàn)向量的新方法[J];大地測(cè)量與地球動(dòng)力學(xué);2005年03期

6 張玉方;程新文;歐陽(yáng)平;王冬梅;熊娜;;機(jī)載LIDAR數(shù)據(jù)處理及其應(yīng)用綜述[J];工程地球物理學(xué)報(bào);2008年01期

7 張峰;薛艷麗;李英成;丁曉波;;基于SVM的多源遙感影像面向?qū)ο蠼ㄖ锾崛》椒╗J];國(guó)土資源遙感;2008年02期

8 杜娜娜;彭軍還;;基于決策樹(shù)的機(jī)載LiDAR點(diǎn)云數(shù)據(jù)分類(lèi)[J];測(cè)繪科學(xué);2013年03期

9 喬紀(jì)綱;陳明輝;艾彬;張亦漢;;SVM用于LiDAR數(shù)據(jù)的地物分類(lèi)[J];測(cè)繪通報(bào);2013年07期

10 唐華松,姚耀文;數(shù)據(jù)挖掘中決策樹(shù)算法的探討[J];計(jì)算機(jī)應(yīng)用研究;2001年08期

相關(guān)博士學(xué)位論文 前4條

1 劉麗娟;基于機(jī)載LiDAR和高光譜融合的森林參數(shù)反演研究[D];東北林業(yè)大學(xué);2011年

2 龔輝;基于四元數(shù)的高分辨率衛(wèi)星遙感影像定位理論與方法研究[D];解放軍信息工程大學(xué);2011年

3 駱社周;激光雷達(dá)遙感森林葉面積指數(shù)提取方法研究與應(yīng)用[D];中國(guó)地質(zhì)大學(xué)(北京);2012年

4 管海燕;LiDAR與影像結(jié)合的地物分類(lèi)及房屋重建研究[D];武漢大學(xué);2009年

本文編號(hào)：1992848