【摘要】：深度攝像頭的出現(xiàn)和日益完善,獲取物體的三維信息變得方便和快速,點云作為物體三維信息的一種重要表達(dá)形式,以點云為背景的計算機(jī)視覺近年來得到了發(fā)展。在許許多多的領(lǐng)域,三維視覺有著平面信息無法取代的作用,將機(jī)器視覺的應(yīng)用拓展到了新的領(lǐng)域。本文研究了以噴漆機(jī)器人對汽車保險杠的識別和位姿估計相關(guān)的問題,噴漆機(jī)器人對三維信息的依賴決定了三維視覺的必要性,點云的運用使得噴漆機(jī)器人自動完成對零件的識別成為可能,對于計算機(jī)視覺這個領(lǐng)域的進(jìn)一步發(fā)展,也是有著重要的意義。論文提出了三維點云的識別和位姿估計方案,包括點云處理和分割、點云識別、位姿估計三部分。首先決定了獲取點云的設(shè)備選擇,選擇kinect作為機(jī)器人的視覺硬件,并且人工獲取了各個保險杠的全視角的完成點云。針對實驗各個階段得到的三維點云,利用直通濾波和統(tǒng)計離群點濾波方法除去了比較明顯的噪聲點,然后通過進(jìn)一步的稀疏濾波手段,獲得了比較適合后序處理的點云密度,并且由于實驗的需要,提出一種特征點區(qū)別濾波方法,對于Thrift特征點周圍的點云保持比較高的密度,離特征點比較遠(yuǎn)的部分保留比較稀疏的點云,并設(shè)置了對比實驗驗證效果。對全視角點云進(jìn)行模擬單視角采集,并計算這些單視角點云的視點特征直方圖VFH(Viewpoint Feature Histogram)特征計算,利用這些數(shù)據(jù)訓(xùn)練主成分分析SVM(Support Vector Machine)分類器。在識別和位姿估計階段,對于濾波處理后的點云數(shù)據(jù),選擇基于最小歐式距離的聚類分割方法實現(xiàn)了對單視角情況下點云數(shù)據(jù)的分割,并對分割后的各個聚類進(jìn)行提取視點特征直方圖VFH,然后利用已經(jīng)訓(xùn)練好的SVM分類器對這些VFH特征進(jìn)行分類。利用建立kd-tree(kdemention)和BP(Back Propagation)神經(jīng)網(wǎng)絡(luò)識別兩種手段進(jìn)行了位姿估計并進(jìn)行對比。其中,識別和位姿估計部分還分別設(shè)置了應(yīng)用主成分分析PCA(Principal Component Analysis)降維和不降維兩種方式的對比試驗。實驗結(jié)果表明本論文設(shè)計的點云預(yù)處理、分割識別和位姿估計具有可行性,能夠更快速的完成識別和位姿估計功能,有較大的探究價值。
[Abstract]:With the appearance and improvement of depth camera, it becomes more and more convenient and fast to obtain 3D information of objects. As an important expression of 3D information of objects, point cloud has been developed in computer vision with point cloud as the background in recent years. In many fields, 3D vision plays an irreplaceable role in plane information, which extends the application of machine vision to new fields. This paper studies the problems related to the identification and pose estimation of automobile bumper by painting robot. The dependence of painting robot on 3D information determines the necessity of 3D vision. The application of the point cloud makes it possible for the painting robot to recognize the parts automatically, which is of great significance to the further development of the field of computer vision. In this paper, three dimensional point cloud recognition and pose estimation schemes are proposed, including point cloud processing and segmentation, point cloud recognition and pose estimation. First, the selection of the device to obtain the point cloud is determined, and the kinect is chosen as the vision hardware of the robot, and the complete point cloud of the full angle of view of each bumper is obtained manually. For the 3D point cloud obtained in each stage of the experiment, the obvious noise points are removed by means of direct pass filtering and statistical outlier filtering, and the point cloud density suitable for post-sequence processing is obtained by further sparse filtering. Because of the need of experiment, a method of distinguishing feature points is proposed, which keeps a high density for the point cloud around the Thrift feature point, and keeps the sparse point cloud in the far part from the feature point, and sets up a comparative experiment to verify the effect. The full view point cloud is simulated and the view feature histogram (VFH (Viewpoint Feature Histogram) of these single view point clouds is calculated. The principal component analysis (SVM (Support Vector Machine) classifier is trained by these data. In the phase of recognition and pose estimation, the minimum Euclidean distance based clustering segmentation method is used to segment the point cloud data with single view angle. The view feature histogram (VFH,) is extracted from each clustering, and then the trained SVM classifier is used to classify these VFH features. Kd-tree (kdemention) and BP (Back Propagation) neural network recognition are used to estimate the position and pose. In the part of recognition and pose estimation, a comparative experiment of using principal component analysis (PCA) to reduce PCA (Principal Component Analysis) and not to reduce dimension is also carried out. The experimental results show that the point cloud preprocessing, segmentation recognition and pose estimation designed in this paper are feasible, and the functions of recognition and pose estimation can be completed more quickly.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP242

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蘇本躍;馬金宇;彭玉升;盛敏;;基于K-means聚類的RGBD點云去噪和精簡算法[J];系統(tǒng)仿真學(xué)報;2016年10期

2 袁華;龐建鏗;莫建文;;基于體素化網(wǎng)格下采樣的點云簡化算法研究[J];電視技術(shù);2015年17期

3 劉輝;王伯雄;任懷藝;李鵬程;;ICP算法在雙目結(jié)構(gòu)光系統(tǒng)點云匹配中的應(yīng)用[J];清華大學(xué)學(xué)報(自然科學(xué)版);2012年07期

4 譚志國;魯敏;胡延平;郭裕蘭;莊釗文;;基于點云-模型匹配的激光雷達(dá)目標(biāo)識別[J];計算機(jī)工程與科學(xué);2012年04期

5 方旭;;基于BP神經(jīng)網(wǎng)絡(luò)人臉識別方法的研究與改進(jìn)[J];電腦知識與技術(shù);2011年04期

6 魏永超;劉長華;杜冬;;基于曲面分割的三維點云物體識別[J];光子學(xué)報;2010年12期

7 宇雪垠;曹拓荒;陳本盛;;基于特征臉的人臉識別及實現(xiàn)[J];河北工業(yè)科技;2009年05期

8 孫亞;;基于粒子群BP神經(jīng)網(wǎng)絡(luò)人臉識別算法[J];計算機(jī)仿真;2008年08期

9 梁新合;宋志真;;改進(jìn)的點云精確匹配技術(shù)[J];裝備制造技術(shù);2008年03期

10 白裔峰;肖建;于龍;黃景春;;基于結(jié)構(gòu)風(fēng)險最小化的加權(quán)偏最小二乘法[J];計算機(jī)應(yīng)用;2007年04期

相關(guān)博士學(xué)位論文 前1條

1 蘇宏濤;基于統(tǒng)計特征的人臉識別技術(shù)研究[D];西北工業(yè)大學(xué);2004年

相關(guān)碩士學(xué)位論文 前6條

1 張楠;鐵路場景下三維點云識別與分類算法研究[D];北京交通大學(xué);2016年

2 常江;基于特征匹配的三維點云配準(zhǔn)算法研究[D];中北大學(xué);2015年

3 林志強(qiáng);面向智能服務(wù)機(jī)器人的物體感知研究[D];中國科學(xué)技術(shù)大學(xué);2014年

4 趙春雷;粗糙空間上結(jié)構(gòu)風(fēng)險最小化原則[D];河北大學(xué);2011年

5 戴永前;基于二維激光雷達(dá)的移動機(jī)器人三維環(huán)境的識別[D];南京理工大學(xué);2007年

6 孫宇;基于激光雷達(dá)的機(jī)器人三維地形構(gòu)建和草叢中障礙物檢測[D];浙江大學(xué);2007年

，

本文編號：2250025