【摘要】：近年來(lái),反求工程技術(shù)在汽車(chē)制造、航天航空和醫(yī)學(xué)等領(lǐng)域得到了廣泛的應(yīng)用,而隨著三維掃描技術(shù)的進(jìn)步,通過(guò)三維掃描獲取的點(diǎn)云數(shù)據(jù)量十分龐大,在實(shí)際的應(yīng)用中存在著數(shù)據(jù)冗余的問(wèn)題,因此對(duì)點(diǎn)云數(shù)據(jù)的精簡(jiǎn)成為了當(dāng)前的熱點(diǎn)研究問(wèn)題。本文的研究?jī)?nèi)容主要分為點(diǎn)云特征提取、點(diǎn)云聚類(lèi)和點(diǎn)云精簡(jiǎn)三個(gè)方面,具體內(nèi)容如下:首先,在點(diǎn)云特征提取方面,針對(duì)以往散亂點(diǎn)云特征提取算法存在尖銳特征點(diǎn)提取不完整以及無(wú)法保留模型邊界點(diǎn)的問(wèn)題,提出了一種基于多判別參數(shù)混合方法的散亂點(diǎn)云特征提取算法。該方法對(duì)于每個(gè)k鄰域計(jì)算數(shù)據(jù)點(diǎn)曲率、點(diǎn)法向與鄰域點(diǎn)法向夾角的平均值、點(diǎn)到鄰域重心的距離、點(diǎn)到鄰域點(diǎn)的平均距離,據(jù)此四個(gè)參數(shù)定義特征閾值和特征判別參數(shù),特征判別參數(shù)大于閾值的點(diǎn)即為特征點(diǎn)。以上四個(gè)參數(shù)中,曲率、法矢夾角和數(shù)據(jù)點(diǎn)到其鄰域點(diǎn)的平均距離三個(gè)參數(shù)參與檢測(cè)曲面的尖銳點(diǎn),而點(diǎn)到鄰域重心的距離則主要用于識(shí)別邊界數(shù)據(jù)點(diǎn),同時(shí)也能為檢測(cè)曲面尖銳點(diǎn)提供一定的作用。實(shí)驗(yàn)結(jié)果表明,與已有算法相比,該算法不僅可以有效提取尖銳特征點(diǎn),而且能夠識(shí)別邊界點(diǎn)。其次,在點(diǎn)云聚類(lèi)方面,針對(duì)傳統(tǒng)K-means聚類(lèi)算法應(yīng)用于點(diǎn)云數(shù)據(jù)時(shí)存在迭代收斂時(shí)間長(zhǎng)、多次運(yùn)行的聚類(lèi)結(jié)果具有隨機(jī)性以及聚類(lèi)效果較差的問(wèn)題,提出了一種基于自適應(yīng)八叉樹(shù)的點(diǎn)云K-means聚類(lèi)算法。該方法利用自適應(yīng)八叉樹(shù)為K-means聚類(lèi)提供與點(diǎn)云密度分布相關(guān)的初始化聚類(lèi)中心和K值,然后迭代輸出聚類(lèi)結(jié)果。實(shí)驗(yàn)表明該方法在聚類(lèi)的評(píng)價(jià)函數(shù)值和運(yùn)行時(shí)間上都優(yōu)于傳統(tǒng)的K-means聚類(lèi),而且消除了多次運(yùn)行時(shí)聚類(lèi)結(jié)果的隨機(jī)性。最后,在點(diǎn)云精簡(jiǎn)方面,首先利用本文提出的散亂點(diǎn)云特征檢測(cè)方法提取點(diǎn)云特征點(diǎn),然后對(duì)點(diǎn)云進(jìn)行基于自適應(yīng)八叉樹(shù)的K-means聚類(lèi)操作,最后在不包含特征點(diǎn)的聚類(lèi)中以距離聚類(lèi)重心最近的數(shù)據(jù)點(diǎn)代替整個(gè)聚類(lèi),其他數(shù)據(jù)點(diǎn)刪除。為了保留模型的細(xì)節(jié)特征,在包含特征點(diǎn)的聚類(lèi)中,選擇該聚類(lèi)所包含數(shù)據(jù)點(diǎn)中曲率差值最大的兩個(gè)點(diǎn)作為新的初始化聚類(lèi)中心再次進(jìn)行聚類(lèi)細(xì)分,直到聚類(lèi)中數(shù)據(jù)點(diǎn)的最大曲率差小于閾值或者聚類(lèi)中只有一個(gè)數(shù)據(jù)點(diǎn)為止,最終同樣以距離聚類(lèi)重心最近的數(shù)據(jù)點(diǎn)代替整個(gè)聚類(lèi)。通過(guò)實(shí)驗(yàn)對(duì)比,精簡(jiǎn)后的數(shù)據(jù)點(diǎn)分布均勻沒(méi)有空洞,精簡(jiǎn)誤差以及用于片狀點(diǎn)云時(shí)因?yàn)檫吔缡湛s而產(chǎn)生的誤差較小,從而能夠使精簡(jiǎn)算法適用于封閉及片狀的點(diǎn)云數(shù)據(jù)類(lèi)型。
[Abstract]:In recent years, reverse engineering technology has been widely used in the fields of automobile manufacture, aerospace and medicine, but with the progress of 3D scanning technology, the amount of point cloud data obtained by 3D scanning is very large. There is a problem of data redundancy in practical applications, so the reduction of point cloud data has become a hot research issue. The research contents of this paper are mainly divided into three aspects: point cloud feature extraction, point cloud clustering and point cloud reduction. The specific contents are as follows: first, in point cloud feature extraction, Aiming at the problem that the feature extraction of scattered point cloud is incomplete and unable to preserve the boundary points of the model, a new feature extraction algorithm for scattered point cloud based on mixed multi-discriminant parameters is proposed. This method calculates the curvature of data points for each k neighborhood, the average angle between normal point and neighborhood point, the distance from point to center of gravity, and the average distance from point to neighborhood point. According to the four parameters, the characteristic threshold and characteristic discriminant parameters are defined. The point at which the feature parameter is greater than the threshold is the feature point. Among the above four parameters, curvature, normal vector angle and the average distance from the data point to its neighborhood point participate in the detection of sharp points of the surface, while the distance from the point to the center of gravity of the neighborhood is mainly used to identify the boundary data points. At the same time, it can also provide a certain role for the detection of sharp points of surfaces. Experimental results show that the proposed algorithm can not only extract sharp feature points effectively, but also recognize boundary points. Secondly, in the aspect of point cloud clustering, the traditional K-means clustering algorithm has the problems of long iterative convergence time, randomness and poor clustering effect when it is applied to point cloud data. A point cloud K-means clustering algorithm based on adaptive octree is proposed. In this method, the adaptive octree is used to provide the initial cluster center and K value related to the point cloud density distribution for the K-means clustering, and then the clustering results are output iteratively. The experimental results show that the proposed method is superior to the traditional K-means clustering in evaluation function and running time, and the randomness of the clustering results at multiple runs is eliminated. Finally, in the aspect of point cloud reduction, the point cloud feature points are extracted by using the scattered point cloud feature detection method proposed in this paper, and then the point cloud is extracted by K-means clustering operation based on adaptive octree. Finally, in the clustering without feature points, the nearest data point is replaced by the whole cluster, and the other data points are deleted. In order to preserve the detailed features of the model, the two points with the largest curvature difference among the data points included in the cluster are selected as the new initialization clustering center to subdivide the cluster again. Until the maximum curvature difference of the data points in the clustering is less than the threshold or there is only one data point in the clustering, the data points closest to the center of gravity of the clustering are also replaced by the data points of the whole clustering. The experimental results show that there are no holes in the uniform distribution of the reduced data points, and the reduction error and the error caused by the boundary contraction when used in the flake point cloud are smaller, so that the reduced algorithm can be applied to the closed and flaky point cloud data types.
【學(xué)位授予單位】：西南科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP311.13

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孫殿柱;朱昌志;李延瑞;;散亂點(diǎn)云邊界特征快速提取算法[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2009年01期

2 梁新合;梁晉;郭成;曹巨名;王永信;;散亂點(diǎn)云的補(bǔ)償濾波[J];西安交通大學(xué)學(xué)報(bào);2011年11期

3 孫殿柱;朱昌志;李延瑞;田中朝;;散亂點(diǎn)云局部型面參考數(shù)據(jù)的快速查詢(xún)算法[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2009年05期

4 黃文明;彭希為;溫佩芝;吳曉軍;;保留幾何特征的散亂點(diǎn)云簡(jiǎn)化方法[J];計(jì)算機(jī)工程與應(yīng)用;2009年28期

5 孫殿柱;朱昌志;范志先;李延瑞;;基于型面特征的三維散亂點(diǎn)云精簡(jiǎn)算法[J];中國(guó)機(jī)械工程;2009年23期

6 孫永偉;孫殿柱;朱昌志;朱宗偉;;散亂點(diǎn)云切片數(shù)據(jù)快速獲取與優(yōu)化[J];哈爾濱工程大學(xué)學(xué)報(bào);2010年11期

7 周學(xué)禮;萬(wàn)旺根;;心內(nèi)膜散亂點(diǎn)云邊界點(diǎn)檢測(cè)算法研究[J];計(jì)算機(jī)應(yīng)用研究;2012年10期

8 王偉;唐民麗;吳恒玉;;大規(guī)模散亂點(diǎn)云數(shù)據(jù)的曲率估算及計(jì)算機(jī)實(shí)現(xiàn)[J];蘇州市職業(yè)大學(xué)學(xué)報(bào);2011年03期

9 趙燦;湯春瑞;劉丹丹;;基于表面波變換的散亂點(diǎn)云去噪方法[J];組合機(jī)床與自動(dòng)化加工技術(shù);2009年02期

10 倪敏敏;何雪明;薛瑩;鄧楊;;散亂點(diǎn)云的拓?fù)浣Y(jié)構(gòu)重建算法的研究[J];機(jī)械設(shè)計(jì)與制造;2010年08期

相關(guān)會(huì)議論文 前1條

1 孫殿柱;孫肖霞;李延瑞;范志先;;散亂點(diǎn)云內(nèi)外邊界的自動(dòng)提取技術(shù)[A];全國(guó)先進(jìn)制造技術(shù)高層論壇暨制造業(yè)自動(dòng)化、信息化技術(shù)研討會(huì)論文集[C];2005年

相關(guān)博士學(xué)位論文 前4條

1 賀美芳;基于散亂點(diǎn)云數(shù)據(jù)的曲面重建關(guān)鍵技術(shù)研究[D];南京航空航天大學(xué);2006年

2 張連偉;散亂點(diǎn)云三維表面重建技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2009年

3 錢(qián)歸平;散亂點(diǎn)云網(wǎng)格重建及修補(bǔ)研究[D];浙江大學(xué);2008年

4 劉宇;基于微分信息的散亂點(diǎn)云拼合和分割[D];華中科技大學(xué);2008年

相關(guān)碩士學(xué)位論文 前10條

1 白晨;基于線(xiàn)性約束的散亂點(diǎn)云配準(zhǔn)技術(shù)的研究[D];西安建筑科技大學(xué);2015年

2 俞濤;散亂點(diǎn)云精簡(jiǎn)與自動(dòng)拼接技術(shù)研究[D];南昌大學(xué);2015年

3 劉詠梅;基于三維散亂點(diǎn)云的三角網(wǎng)格重構(gòu)關(guān)鍵技術(shù)研究[D];北京理工大學(xué);2015年

4 張戈弋;散亂點(diǎn)云自修復(fù)重建與錯(cuò)誤拓?fù)湫拚芯縖D];西安電子科技大學(xué);2014年

5 陳達(dá)梟;散亂點(diǎn)云數(shù)據(jù)預(yù)處理的研究[D];西南科技大學(xué);2016年

6 張蓉;散亂點(diǎn)云的數(shù)據(jù)分割與特征提取技術(shù)研究[D];南昌大學(xué);2016年

7 王妮;散亂點(diǎn)云自修復(fù)重建與3D打印分層算法研究[D];西安電子科技大學(xué);2015年

8 王雅男;基于局部表面凸性的散亂點(diǎn)云分割算法研究[D];中國(guó)科學(xué)院長(zhǎng)春光學(xué)精密機(jī)械與物理研究所;2016年

9 陳龍;散亂點(diǎn)云特征提取和聚類(lèi)精簡(jiǎn)技術(shù)研究[D];西南科技大學(xué);2017年

10 聶建輝;大規(guī)模散亂點(diǎn)云數(shù)據(jù)后處理技術(shù)研究[D];大連海事大學(xué);2009年

，

本文編號(hào)：2154982