基于穩(wěn)健特征點(diǎn)的立體視覺測程法
發(fā)布時(shí)間：2018-11-01 17:48
【摘要】：提出一種基于穩(wěn)健特征點(diǎn)的立體視覺測程法完成機(jī)器人自主高精度定位.從可重復(fù)性、精確性和效率3個(gè)方面比較多種局部不變特征算法性能,采用穩(wěn)健特征算法AKAZE(AcceleratedKAZE)提取特征點(diǎn).提出了一個(gè)穩(wěn)定的特征點(diǎn)匹配框架和改進(jìn)的隨機(jī)抽樣一致性算法(Random Sample Consensus,RANSAC)去除外點(diǎn),使文中的視覺測程法可以應(yīng)用于動(dòng)態(tài)環(huán)境中.基于幾何約束的分步自運(yùn)動(dòng)估計(jì)可提供相機(jī)運(yùn)動(dòng)的精確信息.將提出的方法在KITTI(Karlsruhe Institute of Technology and Toyota Technological Institute)數(shù)據(jù)集上和復(fù)雜校園環(huán)境中所采集的立體視覺數(shù)據(jù)集上進(jìn)行測試,與經(jīng)典立體視覺測程方法比較,文中的方法更好地抑制了誤差累計(jì),運(yùn)動(dòng)估計(jì)結(jié)果滿足實(shí)時(shí)高精度定位系統(tǒng)需求.
[Abstract]:A stereo vision method based on robust feature points is proposed to achieve autonomous and high precision localization of robot. The performance of several local invariant feature algorithms is compared from the aspects of repeatability, accuracy and efficiency. The robust feature algorithm AKAZE (AcceleratedKAZE) is used to extract feature points. A stable feature point matching framework and an improved random sampling consistency algorithm (Random Sample Consensus,RANSAC) are proposed to remove the external points, so that the visual log method in this paper can be applied to the dynamic environment. Step-by-step self-motion estimation based on geometric constraints can provide accurate information of camera motion. The proposed method is tested on the KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) dataset and the stereo vision data set collected in the complex campus environment. Compared with the classical stereo vision range method, the method in this paper can better restrain the error accumulation. The result of motion estimation meets the requirement of real-time high-precision positioning system.
【作者單位】： 長安大學(xué)信息工程學(xué)院;
【基金】：國家自然科學(xué)基金(51278058) 國家高等學(xué)校學(xué)科創(chuàng)新引智計(jì)劃項(xiàng)目(B14043) 中央高�；痦�(xiàng)目(310824151033,310824165024,310824173101,310824173307) 交通部基礎(chǔ)應(yīng)用項(xiàng)目基金(2015319812060)資助
【分類號(hào)】：TP391.41
，
本文編號(hào)：2304645
[Abstract]:A stereo vision method based on robust feature points is proposed to achieve autonomous and high precision localization of robot. The performance of several local invariant feature algorithms is compared from the aspects of repeatability, accuracy and efficiency. The robust feature algorithm AKAZE (AcceleratedKAZE) is used to extract feature points. A stable feature point matching framework and an improved random sampling consistency algorithm (Random Sample Consensus,RANSAC) are proposed to remove the external points, so that the visual log method in this paper can be applied to the dynamic environment. Step-by-step self-motion estimation based on geometric constraints can provide accurate information of camera motion. The proposed method is tested on the KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) dataset and the stereo vision data set collected in the complex campus environment. Compared with the classical stereo vision range method, the method in this paper can better restrain the error accumulation. The result of motion estimation meets the requirement of real-time high-precision positioning system.
【作者單位】： 長安大學(xué)信息工程學(xué)院;
【基金】：國家自然科學(xué)基金(51278058) 國家高等學(xué)校學(xué)科創(chuàng)新引智計(jì)劃項(xiàng)目(B14043) 中央高�；痦�(xiàng)目(310824151033,310824165024,310824173101,310824173307) 交通部基礎(chǔ)應(yīng)用項(xiàng)目基金(2015319812060)資助
【分類號(hào)】：TP391.41
，
本文編號(hào)：2304645
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2304645.html
最近更新
教材專著
