本文關(guān)鍵詞： LiDAR 濾波 分類 二面角濾波 決策樹　出處：《首都師范大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：激光雷達(LiDAR, Light Detection and Ranging)是一種向目標發(fā)射激光束,將接收的目標返回信號與發(fā)射信號比較,通過處理得到地物三維信息和地面空間特征信息的雷達系統(tǒng)[1-2]。近年來,因LiDAR技術(shù)可快速獲取高空間分辨率地表三維信息、高自動化數(shù)據(jù)采集效率,從而廣泛應(yīng)用于地形測繪、城市建模等多個領(lǐng)域[3-5]。激光雷達數(shù)據(jù)是離散的三維點云,點云數(shù)據(jù)的應(yīng)用明顯滯后于激光雷達系統(tǒng)的硬件發(fā)展。如何快速地處理大量三維點云數(shù)據(jù),獲取關(guān)注的建筑物三維信息,實現(xiàn)建筑物的提取工作,是學(xué)者們研究的重點和難點。 基于以上觀點,本文深入了解總結(jié)了近十多年來激光LiDAR點云數(shù)據(jù)濾波和分類的相關(guān)方法。重點研究LiDAR點云數(shù)據(jù)的濾波和分類算法兩部分,首先根據(jù)首、末次回波高程值,去除植被點,將剩下的點云數(shù)據(jù)規(guī)則格網(wǎng)化,提升點云的處理效率,隨后,提出一種新的考慮到相鄰三點間高程變化快慢程度的二面角濾波法,進行濾波,然后,通過濾波前后的高程值變化對實驗區(qū)進行區(qū)域分割,引入地物二面角均值屬性特征,并結(jié)合回波次數(shù)、高程值和回波強度三個參數(shù)作為判定地物分類的約束條件,構(gòu)建決策樹;最后,采用Alpha Shapes算法提取建筑物輪廓線,進行地表三維顯示。 本文的主要研究內(nèi)容如下： 1.深入地對機載雷達系統(tǒng)的定位原理以及點云的數(shù)據(jù)結(jié)構(gòu)進行了介紹；并且,總結(jié)了激光LiDAR點云數(shù)據(jù)的處理流程。根據(jù)首、尾次回波高程值,去除植被點,進一步將點云數(shù)據(jù)進行規(guī)則格網(wǎng)化,提升了LiDAR點云的處理效率。 2.在規(guī)則格網(wǎng)存儲的LiDAR點云基礎(chǔ)上,鑒于傳統(tǒng)的計算兩點間坡度值的濾波算法,在地形變化劇烈時難以確定坡度閾值的情況,本文提出一種新的考慮到相鄰三點間高程變化快慢程度的二面角濾波法,首次將空間二面角的平面角余弦值,表達空間中相鄰兩平面相對位置的概念引入LiDAR點云數(shù)據(jù)濾波中。首先,基于地表的連續(xù)性提取LiDAR點云數(shù)據(jù)中的高程突變點,然后,分別統(tǒng)計高程突變點和非突變點的二面角余弦頻數(shù)分布,采用交點處對應(yīng)的余弦值和提取高程突變點迭代的最小坡度閾值來判定地面點、非地面點,最后引入數(shù)學(xué)形態(tài)學(xué)“開”算子,去除低矮植被,最終得到可靠的濾波結(jié)果。本文方法,針對復(fù)雜城區(qū)環(huán)境,在濾除大型建筑物的同時,能準確快速地獲取地面點集。 3.本文通過濾波前后LiDAR點云數(shù)據(jù)的高程值變化進行區(qū)域分割：在點云數(shù)據(jù)濾波后,LiDAR數(shù)據(jù)點被分為地面點及非地面點,于非地面點集中采用區(qū)域增長法分割點云；采用二面角均值、回波次數(shù)、高程值和回波強度四個參數(shù)構(gòu)建決策樹,將實驗區(qū)地物分類為建筑物、植被、地面、道路四個屬性,在此基礎(chǔ)上,采用Alpha Shapes算法提取建筑物輪廓線,實現(xiàn)地表的三維顯示 4.本文選擇了2塊海地太子港的局部LiDAR點云數(shù)據(jù)作為試驗區(qū),在Visual studio2010中采用二面角濾波法,進行點云數(shù)據(jù)的濾波,并在現(xiàn)有濾波方法中,與“漸進三角網(wǎng)法”(TerraSolid-Scan軟件)進行對比分析,驗證了本文算法的可行性。統(tǒng)計了分類結(jié)果混淆矩陣及Kappa系數(shù),對本文的分類精度進行評估。最后,在Visual studio2010中實現(xiàn)了實驗數(shù)據(jù)建筑物的提取和三維顯示。
[Abstract]:Laser radar ( LiDAR , Light Detection and Radar ) is a kind of radar system which emits laser beam to the target , compares the received target return signal with the transmission signal , and obtains the three - dimensional information of the ground object and the surface space feature information by processing . In recent years , the application of the LiDAR technology can quickly acquire the three - dimensional information of high spatial resolution surface and high automation data acquisition efficiency . The laser radar data is a discrete three - dimensional point cloud , and the application of point cloud data is obviously lagging behind the hardware development of the laser radar system . Based on the above viewpoint , this paper deeply understands the correlation method of laser LiDAR point cloud data filtering and classification for more than ten years . It focuses on the filtering and classification algorithms of LiDAR point cloud data . Firstly , according to the first and last echo elevation values , the vegetation points are removed , the remaining point cloud data rules are meshed and the processing efficiency of the point cloud is promoted . Then , a new method is put forward , which takes the three parameters of the echo frequency , the elevation value and the echo intensity to be used as the constraint conditions for judging the classification of the ground objects , and finally , the surface three - dimensional display is carried out by using the Alpha Shapes algorithm to extract the building outline . The main contents of this paper are as follows : 1 . The positioning principle of airborne radar system and the data structure of point cloud are introduced in - depth ; and the processing flow of laser LiDAR point cloud data is summarized . According to the first and tail echo elevation values , the vegetation points are removed , and the point cloud data is further regularly meshed , so that the processing efficiency of the LiDAR point cloud is improved . 2 . On the basis of the LiDAR point cloud stored in the regular grid , in view of the traditional filtering algorithm for calculating the slope value between two points , it is difficult to determine the slope threshold value when the terrain changes violently . 3 . This paper divides the elevation value of LiDAR point cloud data before and after filtering : After the point cloud data is filtered , the LiDAR data points are divided into the ground point and the non - ground point , and the point cloud is divided by the regional growth method in the non - ground point set ; 4 . In this paper , the local LiDAR point cloud data in Port - au - Prince of Haiti is selected as the test area . In Visual Studio2010 , the filtering of point cloud data is carried out , and compared with TerraSolid - Scan software in the existing filtering method , the feasibility of the algorithm is verified . The classification accuracy is evaluated by using the classification result confusion matrix and Kappa coefficient . Finally , the extraction and three - dimensional display of experimental data buildings are realized in Visual Studio2010 .

【學(xué)位授予單位】：首都師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TN957.52

【參考文獻】

相關(guān)期刊論文 前10條

1 李慧盈;李文輝;陳圣波;;一種機載雷達點云數(shù)據(jù)的快速分類方法[J];吉林大學(xué)學(xué)報(地球科學(xué)版);2010年05期

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

3 張小紅;;利用機載LIDAR雙次回波高程之差分類激光腳點[J];測繪科學(xué);2006年04期

4 李濤;岑敏儀;;結(jié)合影像的LIDAR數(shù)據(jù)三維建筑物提取[J];測繪科學(xué);2007年05期

5 周曉明;馬秋禾;李二森;唐德瑾;;基于小波多分辨率方向高程限差的LiDAR數(shù)據(jù)濾波[J];測繪科學(xué);2010年04期

6 袁楓;張繼賢;張力;高井祥;;結(jié)合強度信息的LIDAR數(shù)據(jù)濾波方法[J];測繪科學(xué);2010年05期

7 曾靜靜;盧秀山;王健;楊書大;;基于LIDAR回波信息的道路提取[J];測繪科學(xué);2011年02期

8 李琳;崔先國;別君;郭恒慶;季民;王瑞富;;基于機載LiDAR數(shù)據(jù)的區(qū)域林木信息提取[J];測繪科學(xué);2011年02期

9 龔亮;張永生;李正國;包全福;;基于多尺度虛擬網(wǎng)格與坡度閾值的機載LiDAR點云濾波方法[J];測繪科學(xué);2012年01期

10 張齊勇;岑敏儀;周國清;楊曉云;;城區(qū)LiDAR點云數(shù)據(jù)的樹木提取[J];測繪學(xué)報;2009年04期

相關(guān)博士學(xué)位論文 前2條

1 周曉明;機載激光雷達點云數(shù)據(jù)濾波算法的研究與應(yīng)用[D];解放軍信息工程大學(xué);2011年

2 曾齊紅;機載激光雷達點云數(shù)據(jù)處理與建筑物三維重建[D];上海大學(xué);2009年

，

本文編號：1455645