【摘要】：機(jī)器人同時(shí)定位與地圖構(gòu)建技術(shù)是全自主機(jī)器人的關(guān)鍵技術(shù)。雖然,基于單目視覺的同時(shí)定位與地圖構(gòu)建方法相較于基于激光的有價(jià)格低、能夠構(gòu)建三維地圖等優(yōu)點(diǎn),但其自身存在計(jì)算量大、易產(chǎn)生尺度漂移、建圖精度不高等問題。因此,如何降低基于單目視覺的同時(shí)定位與地圖構(gòu)建算法計(jì)算量,提高地圖構(gòu)建精度已成為當(dāng)今機(jī)器人地圖構(gòu)建領(lǐng)域熱點(diǎn)。針對(duì)基于單目視覺同時(shí)定位與地圖構(gòu)建方法所存在的計(jì)算量大、易產(chǎn)生尺度漂移、建圖精度不高的問題,通過采用基于相似變換的閉環(huán)檢測(cè)與改進(jìn)直接法,結(jié)合優(yōu)化方法,重點(diǎn)開展了半稠密地圖構(gòu)建算法研究,并通過實(shí)驗(yàn)驗(yàn)證了本文所建立算法的正確性與有效性,提高了單目視覺同時(shí)定位與地圖構(gòu)建精度,降低了計(jì)算量。具體進(jìn)行了如下研究:首先,針對(duì)如何提高基于直接法地圖構(gòu)建的快速性問題,開展了基于Lucas-Kanade方法的相機(jī)位姿跟蹤改進(jìn)方法研究。結(jié)合機(jī)器人行走速度指標(biāo),基于Lucas-Kanade方法,利用雅克比矩陣對(duì)該方法的迭代過程進(jìn)行了分析,獲得該方法計(jì)算量大的原因,在此基礎(chǔ)上,通過位姿變換增量矩陣的逆實(shí)現(xiàn)了對(duì)Lucas-Kanade方法的改進(jìn),利用TUM數(shù)據(jù)集實(shí)驗(yàn)驗(yàn)證了改進(jìn)LucasKanade的有效性;通過實(shí)驗(yàn)分析了地圖稠密度對(duì)相機(jī)跟蹤算法快速性的影響,實(shí)驗(yàn)中獲得了算法的時(shí)間代價(jià)隨像素梯度閾值變化曲線,得到了兼顧地圖稠密程度和相機(jī)跟蹤算法快速性的像素梯度閾值。然后,針對(duì)基于單目的地圖構(gòu)建算法尺度漂移和位姿估計(jì)不準(zhǔn)確問題,開展了基于直接法的閉環(huán)檢測(cè)和地圖優(yōu)化研究。借鑒了基于特征點(diǎn)法解決單目SLAM尺度漂移問題的方法,將相機(jī)的位姿變換和場(chǎng)景尺度同作為優(yōu)化變量求解關(guān)鍵幀之間的相似變換,通過最小化像素灰度和深度殘差平方和求得相似變換的最優(yōu)估計(jì)。在此基礎(chǔ)上,將求得的相似變換作為優(yōu)化變量,通過求解最小化代價(jià)方程實(shí)現(xiàn)地圖的全局優(yōu)化。利用TUM數(shù)據(jù)集實(shí)驗(yàn)驗(yàn)證了基于相似變換的閉環(huán)檢測(cè)和地圖優(yōu)化的有效性最后,為驗(yàn)證算法的快速性和準(zhǔn)確性,在室內(nèi)實(shí)驗(yàn)中以激光估計(jì)的軌跡為參照軌跡計(jì)算算法準(zhǔn)確性,實(shí)驗(yàn)中對(duì)比各算法時(shí)間代價(jià)以驗(yàn)證算法快速性;為驗(yàn)證算法在解決單目SLAM尺度漂移問題的有效性,室外實(shí)驗(yàn)中手持相機(jī)進(jìn)行長(zhǎng)距離的閉環(huán)行走,對(duì)比優(yōu)化前后的地圖,驗(yàn)證了基于相似變換的地圖優(yōu)化在解決單目SLAM尺度漂移問題的有效性。
[Abstract]:The technology of simultaneous localization and map building is the key technology of autonomous robot. Although the method of simultaneous location and map construction based on monocular vision has the advantages of low price and ability to construct 3D map compared with that based on laser, it has many problems, such as large amount of calculation, easy to produce scale drift and low precision of mapping. Therefore, how to reduce the amount of computation of simultaneous localization and map construction based on monocular vision and improve the accuracy of map construction has become a hot spot in the field of robot map construction. Aiming at the problems of large computation, easy to produce scale drift and low precision of map building based on monocular vision simultaneous localization and map construction, this paper adopts close-loop detection and improved direct method based on similarity transformation, and combines optimization method. The research of semi-dense map construction algorithm is emphasized, and the correctness and validity of the proposed algorithm are verified by experiments. The accuracy of monocular vision simultaneous location and map construction is improved, and the computational complexity is reduced. The specific research is as follows: firstly, aiming at how to improve the rapidity of map construction based on direct method, the improved method of camera pose tracking based on Lucas-Kanade method is studied. Based on Lucas-Kanade method, the iterative process of this method is analyzed by using Jacobian matrix, and the reasons for the large amount of calculation are obtained, based on Lucas-Kanade method. The Lucas-Kanade method is improved by the inverse of the incremental matrix of pose transformation, the effectiveness of the improved LucasKanade is verified by the TUM dataset experiment, and the influence of the density of the map on the fast tracking algorithm is analyzed. In the experiment, the time cost of the algorithm varies with the pixel gradient threshold, and the pixel gradient threshold, which takes into account the density of the map and the rapidity of camera tracking algorithm, is obtained. Then, aiming at the inaccuracy of scale drift and pose estimation based on single-destination graph construction algorithm, the closed-loop detection and map optimization research based on direct method are carried out. Based on the feature point method, the camera pose transformation and scene scale are used as optimization variables to solve the similarity transformation between the key frames. The optimal estimation of similar transformation is obtained by minimizing the sum of gray and depth residuals of pixels. On this basis, the obtained similarity transformation is regarded as the optimization variable, and the global optimization of the map is realized by solving the minimization cost equation. The validity of close-loop detection and map optimization based on similarity transformation is verified by TUM dataset experiment. Finally, in order to verify the speed and accuracy of the algorithm, the laser estimated trajectory is used as the reference trajectory calculation accuracy in indoor experiments. In order to verify the effectiveness of the algorithm in solving the problem of single-eye slam scale drift, the hand-held camera carries out long distance closed-loop walking in outdoor experiments, and compares the map before and after optimization. The validity of map optimization based on similarity transformation in solving the problem of single scale drift of slam is verified.
【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(guó)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 梁明杰;閔華清;羅榮華;;基于圖優(yōu)化的同時(shí)定位與地圖創(chuàng)建綜述[J];機(jī)器人;2013年04期

3 張鴻燕;耿征;;Levenberg-Marquardt算法的一種新解釋[J];計(jì)算機(jī)工程與應(yīng)用;2009年19期

相關(guān)博士學(xué)位論文 前3條

1 苑全德;基于視覺的多機(jī)器人協(xié)作SLAM研究[D];哈爾濱工業(yè)大學(xué);2016年

2 吳俊君;移動(dòng)機(jī)器人視覺同時(shí)定位與地圖構(gòu)建關(guān)鍵算法研究[D];華南理工大學(xué);2013年

3 羅桂娥;雙目立體視覺深度感知與三維重建若干問題研究[D];中南大學(xué);2012年

相關(guān)碩士學(xué)位論文 前2條

1 張明明;基于Kinect2的光伏清洗機(jī)器人實(shí)時(shí)環(huán)境重建與自主導(dǎo)航技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2016年

2 梁瀟;基于激光與單目視覺融合的機(jī)器人室內(nèi)定位與制圖研究[D];哈爾濱工業(yè)大學(xué);2016年

，

本文編號(hào)：2123977