馬佳豪, 郭中華
摘要:目前,基于RGB-D攝像頭的視覺(jué)SLAM是該領(lǐng)域的研究熱點(diǎn)之一。傳統(tǒng)視覺(jué)SLAM因精度較差的問(wèn)題,應(yīng)用范圍遠(yuǎn)不如激光SLAM,文中以此構(gòu)建了基于KinectV2.0的視覺(jué)SLAM系統(tǒng)來(lái)驗(yàn)證此問(wèn)題;算法方面,Gmapping算法在RBPF粒子濾波算法基礎(chǔ)上優(yōu)化了提議分布并且選擇性重采樣從而減少了計(jì)算量,因此選用Gmapping算法在三個(gè)不同復(fù)雜程度的場(chǎng)景下進(jìn)行地圖構(gòu)建實(shí)驗(yàn),最后對(duì)三個(gè)場(chǎng)景下的建圖數(shù)據(jù)和實(shí)測(cè)數(shù)據(jù)進(jìn)行誤差分析。實(shí)驗(yàn)結(jié)果表明,基于KinectV2.0構(gòu)建的視覺(jué)SLAM系統(tǒng)在三個(gè)場(chǎng)景下的建圖精度和穩(wěn)定性與激光SLAM相比擬,因此在光照變化較小或不變的場(chǎng)景下可選用視覺(jué)SLAM以降低成本,一定程度上可以減少設(shè)備成本并降低技術(shù)難度。
關(guān)鍵詞:視覺(jué) SLAM;移動(dòng)機(jī)器人;RGB-D;回環(huán)檢測(cè);建圖精度
中圖分類號(hào):TP242? ? ? ?文獻(xiàn)標(biāo)識(shí)碼:A
文章編號(hào):1009-3044(2021)21-0001-03
開(kāi)放科學(xué)(資源服務(wù))標(biāo)識(shí)碼(OSID):
Study and Error Analysis of Visual SLAM Mapping Based on KinectV2.0
MA Jia-hao1, GUO Zhong-hua1,2
(1.School of Physics and Electronic-Electrical Engineering, Yinchuan 750021, China; 2. Ningxia Key Laboratory of Intelligent Sensing for Desert Information, Yinchuan 750021, China)
Abstract:Currently, visual SLAM based on RGB-D camera is one of the research hotspots in this field. Due to the problem of poor accuracy of traditional visual SLAM, the application range is far inferior to laser SLAM. In this paper, a visual SLAM system based on KinectV2.0 is constructed to verify this problem; in terms of algorithm, the Gmapping algorithm optimizes the proposal based on the RBPF particle filter algorithm The distribution and selective resampling reduces the amount of calculation. Therefore, the Gmapping algorithm is selected to conduct map construction experiments in three scenes of different complexity. Finally, the error analysis of the mapping data and the measured data in the three scenes is carried out. The experimental results show that the mapping accuracy and stability of the visual SLAM system based on KinectV2.0 in the three scenes is comparable to that of laser SLAM, so visual SLAM can be used in scenes with small or constant illumination changes to reduce costs , To a certain extent, it can reduce equipment costs and reduce technical difficulties.
Key words: visual SLAM; mobile robot; RGB-D; loop detection; mapping accuracy
1 引言
同時(shí)定位及地圖構(gòu)建(SLAM, simultaneous localization and mapping)出現(xiàn)于機(jī)器人應(yīng)用領(lǐng)域 , SLAM技術(shù)[1]目標(biāo)是使機(jī)器人在一個(gè)未知環(huán)境中使其實(shí)時(shí)重新構(gòu)建當(dāng)前未知環(huán)境的地圖結(jié)構(gòu),同時(shí)對(duì)自身進(jìn)行定位。移動(dòng)機(jī)器人的同步定位和地圖構(gòu)建(SLAM)技術(shù)成了移動(dòng)機(jī)器人發(fā)展進(jìn)程中亟待解決的一個(gè)核心問(wèn)題,在實(shí)現(xiàn)SLAM技術(shù)的基礎(chǔ)之上,才能使移動(dòng)機(jī)器人真正地實(shí)現(xiàn)自動(dòng)化,才能使機(jī)器人在更多領(lǐng)域煥發(fā)出應(yīng)有的活力。SLAM技術(shù)的實(shí)現(xiàn)大致分為兩個(gè)主要方向——激光SLAM技術(shù)和視覺(jué)SLAM(V-SLAM)技術(shù),一般來(lái)說(shuō)激光SLAM精確度較高,但是成本高,采集數(shù)據(jù)量大,對(duì)計(jì)算力要求嚴(yán)苛,只利用相機(jī)作為傳感器的SLAM被稱為視覺(jué)SLAM[3],作為當(dāng)前SLAM框架的主要類型,激光SLAM與視覺(jué)SLAM必將在相互競(jìng)爭(zhēng)和融合中發(fā)展。
文獻(xiàn)[4]構(gòu)建了一個(gè)基于手持 Kinect 的 RGB-D SLAM 系統(tǒng),文獻(xiàn)[5]中首次提出了基于Kinect的SLAM系統(tǒng),文獻(xiàn)[6]中提到視覺(jué)SLAM的傳感器有單目、雙目、RGB-D攝像頭。文獻(xiàn)[7]中在RBPF SLAM基礎(chǔ)上對(duì)提議分布和重采樣進(jìn)行了優(yōu)化,其算法被實(shí)現(xiàn)為開(kāi)源的SLAM功能包Gmapping。為了保證建圖與定位的準(zhǔn)確性,實(shí)驗(yàn)設(shè)備使用RGB-D攝像頭作為數(shù)據(jù)采集設(shè)備,在光照強(qiáng)度一定的前提下,利用基于粒子濾波算法優(yōu)化的Gmapping功能包對(duì)于三種不同復(fù)雜程度的環(huán)境進(jìn)行地圖構(gòu)建,并與環(huán)境實(shí)測(cè)數(shù)據(jù)對(duì)比進(jìn)行誤差分析,最終通過(guò)本實(shí)驗(yàn)的建圖結(jié)果驗(yàn)證與分析,在誤差允許范圍內(nèi)視覺(jué)SLAM在環(huán)境光正常、構(gòu)建小場(chǎng)景地圖時(shí)可以保證建圖精確度,因此基于KinectV2.0的視覺(jué)SLAM在建圖精度和穩(wěn)定性方面可以與激光SLAM的精度與穩(wěn)定性相比擬。