【摘要】：提出一種基于離散選取機(jī)制的改進(jìn)特征點(diǎn)ICP算法,并設(shè)計(jì)了基于該算法的三維地圖創(chuàng)建方法.該方法分為3個(gè)階段,首先提取并匹配相機(jī)運(yùn)動(dòng)過程中采集的RGB彩色圖像中的SURF特征點(diǎn);然后結(jié)合RANSAC算法進(jìn)行初始配準(zhǔn),優(yōu)化特征點(diǎn)集初始位姿、去除誤匹配,并結(jié)合基于離散選取機(jī)制的特征點(diǎn)ICP算法進(jìn)行精確配準(zhǔn);最后利用g2o圖優(yōu)化算法結(jié)合關(guān)鍵幀實(shí)現(xiàn)對相機(jī)運(yùn)動(dòng)軌跡的優(yōu)化,減少累計(jì)誤差,并將相機(jī)采集到的點(diǎn)云數(shù)據(jù)根據(jù)相機(jī)當(dāng)前位姿構(gòu)建三維點(diǎn)云地圖.經(jīng)過在5個(gè)公開數(shù)據(jù)集環(huán)境下進(jìn)行實(shí)驗(yàn)對比,證明本方法的可行性和有效性,在相機(jī)運(yùn)動(dòng)長度為15.989m的情況下誤差僅為0.059m,且能夠準(zhǔn)確地創(chuàng)建實(shí)驗(yàn)環(huán)境的三維地圖.
[Abstract]:An improved feature point ICP algorithm based on discrete selection mechanism is proposed, and a 3D map creation method based on the algorithm is designed. The method is divided into three stages. Firstly, the SURF feature points in RGB color image collected during camera motion are extracted and matched, then the initial registration is carried out with RANSAC algorithm, the initial pose of feature point set is optimized, the mismatching is removed, and the feature point ICP algorithm based on discrete selection mechanism is used for accurate registration. Finally, the g2o graph optimization algorithm and key frame are used to optimize the camera motion trajectory, reduce the cumulative error, and the point cloud data collected by the camera is constructed according to the camera's current position and pose to construct a three-dimensional point cloud map. The feasibility and effectiveness of the method are proved by experimental comparison in five open data set environments. The error is only 0.059 m when the camera motion length is 15.989 m, and the 3D map of the experimental environment can be accurately created.
【作者單位】： 武漢工程大學(xué)計(jì)算機(jī)科學(xué)與工程學(xué)院;武漢工程大學(xué)智能機(jī)器人湖北省重點(diǎn)實(shí)驗(yàn)室;
【基金】：國家863計(jì)劃項(xiàng)目(2013AA12A202) 國家自然科學(xué)基金項(xiàng)目(41501505)
【分類號】：TP391.41;TP242

【相似文獻(xiàn)】

相關(guān)期刊論文 前9條

1 李必卿;蔡勇;;一種改進(jìn)的ICP算法在多視配準(zhǔn)中的應(yīng)用[J];機(jī)械工程師;2009年02期

2 李策;羅欣穎;杜少毅;;面向地圖點(diǎn)集的多尺度層級ICP算法[J];計(jì)算機(jī)應(yīng)用與軟件;2012年04期

3 程俊廷;趙燦;王從軍;莫健華;;基于參考點(diǎn)和ICP算法的點(diǎn)云數(shù)據(jù)重定位研究[J];計(jì)算機(jī)測量與控制;2006年09期

4 王勇;曲學(xué)軍;樊龍欣;;利用三點(diǎn)法對多視測量數(shù)據(jù)的配準(zhǔn)及ICP算法優(yōu)化的研究[J];數(shù)字技術(shù)與應(yīng)用;2012年06期

5 楊現(xiàn)輝;王惠南;;ICP算法在3D點(diǎn)云配準(zhǔn)中的應(yīng)用研究[J];計(jì)算機(jī)仿真;2010年08期

6 劉繁明,屈昊;ICP算法的魯棒性改進(jìn)[J];儀器儀表學(xué)報(bào);2004年S1期

7 張為;肖玉朝;;基于配準(zhǔn)元素選擇的改進(jìn)ICP算法研究[J];計(jì)算機(jī)光盤軟件與應(yīng)用;2012年19期

8 袁建英;劉先勇;劉偉;郭進(jìn);;改進(jìn)ICP算法實(shí)現(xiàn)多視點(diǎn)云精確配準(zhǔn)研究[J];傳感器與微系統(tǒng);2008年05期

9 ;[J];;年期

相關(guān)會(huì)議論文 前2條

1 徐萬鑫;許宏麗;;改進(jìn)的ICP算法在點(diǎn)云配準(zhǔn)中的應(yīng)用[A];Proceedings of 14th Chinese Conference on System Simulation Technology & Application(CCSSTA’2012)[C];2012年

2 劉繁明;屈昊;;ICP算法的魯棒性改進(jìn)[A];第二屆全國信息獲取與處理學(xué)術(shù)會(huì)議論文集[C];2004年

，

本文編號：2514692