基于RGB-D的同步定位與構(gòu)圖算法研究
發(fā)布時(shí)間：2018-11-03 06:52
【摘要】：SLAM(Simultaneous Localization and Mapping)作為機(jī)器人實(shí)現(xiàn)自主化的基礎(chǔ),能夠在未知環(huán)境下實(shí)現(xiàn)機(jī)器人定位與環(huán)境地圖構(gòu)建的同步進(jìn)行,近年來受到了越來越多的關(guān)注。按照選用的傳感器不同可將SLAM分為三種:基于聲吶、基于雷達(dá)和基于視覺的SLAM。本文主要研究視覺SLAM中的RGB-D SLAM,即以RGB-D相機(jī)為視覺傳感器的同步定位與構(gòu)圖。KINECT作為RGB-D傳感器價(jià)格便宜,且所獲得的圖片質(zhì)量也較好,因此本文在KINECT的基礎(chǔ)上進(jìn)行研究與實(shí)驗(yàn)。本文首先對(duì)SLAM的發(fā)展現(xiàn)狀與研究內(nèi)容進(jìn)行了分析介紹,將SLAM分為以圖像處理為目的的前端和以優(yōu)化為目的的后端,并對(duì)前端與后端的各個(gè)環(huán)節(jié)進(jìn)行了詳細(xì)闡述與推導(dǎo)。隨后,針對(duì)各環(huán)節(jié)存在的問題提出了相應(yīng)的改進(jìn)方法。在特征提取環(huán)節(jié),通過對(duì)主流提取算法的仿真分析,提出以FAST-SIFT的結(jié)合方式進(jìn)行特征提取,不僅加快了計(jì)算速度,而且保證了提取的穩(wěn)定性。另外,打破了傳統(tǒng)算法中將特征點(diǎn)視為一體的方式,對(duì)特征點(diǎn)進(jìn)行分類,并說明了平面點(diǎn)的優(yōu)勢(shì),繼而提出以“先面后點(diǎn)”的方式提取出更多的平面點(diǎn)。在特征匹配中,同樣采取先匹配面后匹配面上的點(diǎn)的方式,通過平面參數(shù)對(duì)點(diǎn)云深度進(jìn)行修正,減小了深度噪聲的影響。隨后又提出一套完整嚴(yán)格的誤匹配剔除規(guī)則,避免了因?yàn)檎`匹配導(dǎo)致的不良結(jié)果。在運(yùn)動(dòng)估計(jì)環(huán)節(jié)中,用經(jīng)過修正后的點(diǎn)云進(jìn)行配準(zhǔn),提出基于PROSAC((Progressive Sample Consensus))的ICP(Iterative Closest Point)算法,相比與傳統(tǒng)算法更為快速、準(zhǔn)確。最后,在后端算法中,制訂了合理的環(huán)回檢測(cè)策略,并以G2O為仿真工具,驗(yàn)證了添加了回環(huán)后的結(jié)果更為精確。本文首先以網(wǎng)上公開數(shù)據(jù)集freiburg2_pioneer_slam作為仿真數(shù)據(jù),對(duì)改進(jìn)算法進(jìn)行了仿真分析,隨后采用手持KINECT的方式,在實(shí)驗(yàn)室環(huán)境中進(jìn)行實(shí)驗(yàn)。最終仿真與實(shí)驗(yàn)結(jié)果表明了改進(jìn)算法的優(yōu)越性。
[Abstract]:As the basis of autonomous robot, SLAM (Simultaneous Localization and Mapping) can realize the synchronization of robot localization and environment map construction in unknown environment. In recent years, more and more attention has been paid to SLAM (Simultaneous Localization and Mapping). SLAM can be divided into three types according to the sensors selected: sonar based, radar based and visual based SLAM. This paper mainly studies the RGB-D SLAM, in visual SLAM, that is, the synchronous location and composition of RGB-D camera as visual sensor. KINECT is cheap as RGB-D sensor, and the image quality is good. Therefore, this paper based on the KINECT research and experiment. In this paper, the development status and research contents of SLAM are analyzed and introduced. The SLAM is divided into the front end for image processing and the back end for optimization, and each link between the front end and the back end is described and deduced in detail. Then, according to the existing problems of each link, the corresponding improvement methods are put forward. In the part of feature extraction, through the simulation analysis of the mainstream extraction algorithm, it is proposed that the combination of FAST-SIFT can not only speed up the calculation speed, but also ensure the stability of the extraction. In addition, it breaks the traditional method of treating feature points as a whole, classifies feature points, explains the advantages of plane points, and then proposes to extract more plane points by "first face and then point". In feature matching, the point on the surface is matched first and then the point on the surface is matched. The depth of the point cloud is modified by plane parameters to reduce the influence of depth noise. Then a complete set of strict rules for eliminating mismatch is proposed to avoid the bad results caused by mismatch. In motion estimation, the modified point cloud is used to register, and the ICP (Iterative Closest Point) algorithm based on PROSAC (Progressive Sample Consensus) is proposed, which is faster and more accurate than the traditional algorithm. Finally, in the back-end algorithm, a reasonable loopback detection strategy is worked out, and G2O is used as a simulation tool to verify that the results after adding the loop are more accurate. In this paper, the improved algorithm is simulated and analyzed by using the open data set (freiburg2_pioneer_slam) on the Internet as simulation data, and then the experiment is carried out in the laboratory environment by handheld KINECT. The simulation and experimental results show the superiority of the improved algorithm.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP242
本文編號(hào)：2307020
[Abstract]:As the basis of autonomous robot, SLAM (Simultaneous Localization and Mapping) can realize the synchronization of robot localization and environment map construction in unknown environment. In recent years, more and more attention has been paid to SLAM (Simultaneous Localization and Mapping). SLAM can be divided into three types according to the sensors selected: sonar based, radar based and visual based SLAM. This paper mainly studies the RGB-D SLAM, in visual SLAM, that is, the synchronous location and composition of RGB-D camera as visual sensor. KINECT is cheap as RGB-D sensor, and the image quality is good. Therefore, this paper based on the KINECT research and experiment. In this paper, the development status and research contents of SLAM are analyzed and introduced. The SLAM is divided into the front end for image processing and the back end for optimization, and each link between the front end and the back end is described and deduced in detail. Then, according to the existing problems of each link, the corresponding improvement methods are put forward. In the part of feature extraction, through the simulation analysis of the mainstream extraction algorithm, it is proposed that the combination of FAST-SIFT can not only speed up the calculation speed, but also ensure the stability of the extraction. In addition, it breaks the traditional method of treating feature points as a whole, classifies feature points, explains the advantages of plane points, and then proposes to extract more plane points by "first face and then point". In feature matching, the point on the surface is matched first and then the point on the surface is matched. The depth of the point cloud is modified by plane parameters to reduce the influence of depth noise. Then a complete set of strict rules for eliminating mismatch is proposed to avoid the bad results caused by mismatch. In motion estimation, the modified point cloud is used to register, and the ICP (Iterative Closest Point) algorithm based on PROSAC (Progressive Sample Consensus) is proposed, which is faster and more accurate than the traditional algorithm. Finally, in the back-end algorithm, a reasonable loopback detection strategy is worked out, and G2O is used as a simulation tool to verify that the results after adding the loop are more accurate. In this paper, the improved algorithm is simulated and analyzed by using the open data set (freiburg2_pioneer_slam) on the Internet as simulation data, and then the experiment is carried out in the laboratory environment by handheld KINECT. The simulation and experimental results show the superiority of the improved algorithm.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP242
【參考文獻(xiàn)】
相關(guān)期刊論文 前3條
1 劉浩敏;章國鋒;鮑虎軍;;基于單目視覺的同時(shí)定位與地圖構(gòu)建方法綜述[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2016年06期
2 閔華松;楊杰;;融合IMU的RGBD-SLAM算法改進(jìn)研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2015年01期
3 石杏喜;趙春霞;郭劍輝;;基于PF/CUKF/EKF的移動(dòng)機(jī)器人SLAM框架算法[J];電子學(xué)報(bào);2009年08期
相關(guān)碩士學(xué)位論文 前3條
1 辛冠希;基于RGB-D攝像機(jī)的同步定位與建圖研究[D];哈爾濱工業(yè)大學(xué);2016年
2 徐冬云;基于Kinect的視覺同步定位與建圖研究[D];哈爾濱工業(yè)大學(xué);2016年
3 李洪臣;單目視覺移動(dòng)機(jī)器人SLAM方法建模與仿真分析[D];電子科技大學(xué);2014年
，本文編號(hào)：2307020
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2307020.html
最近更新
教材專著
