Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online  

作　　者：Wei LU 

机构地区：[1]Instttute of lnformat:on and Communtcatlon Engineering, Zhejtang Umvers:ty, Hangzhou 310027, China [2]Zhejiang Provincial Key Laboratory of Information Network Technology, Hangzhou 310027, China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2015年第2期152-165,共14页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Natural Science Foundation of China （Nos. 61071219 and 90820306） and the Fundamental Research Funds for the Central Universities, China

摘　　要：Efficient and precise localization is a prerequisite for the intelligent navigation of mobile robots. Traditional visual localization systems, such as visual odometry （VO） and simultaneous localization and mapping （SLAM）, suffer from two shortcomings： a drift problem caused by accumulated localization error, and erroneous motion estimation due to illumination variation and moving objects. In this paper, we propose an enhanced VO by introducing a panoramic camera into the traditional stereo-only VO system. Benefiting from the 360° field of view, the panoramic camera is responsible for three tasks： （1） detect- ing road junctions and building a landmark library online; （2） correcting the robot＇s position when the landmarks are revisited with any orientation; （3） working as a panoramic compass when the stereo VO cannot provide reliable positioning results. To use the large-sized panoramic images efficiently, the concept of compressed sensing is introduced into the solution and an adap- tive compressive feature is presented. Combined with our previous two-stage local binocular bundle adjustment （TLBBA） stereo VO, the new system can obtain reliable positioning results in quasi-real time. Experimental results of challenging long-range tests show that our enhanced VO is much more accurate and robust than the traditional VO, thanks to the compressive panoramic landmarks built online.研究目的:高效精确定位是移动机器人智能导航的先决条件。传统视觉定位系统,如视觉里程计(VO)和同时定位与三维重建(SLAM)算法,存在两点不足:一是由累积定位误差引起的漂移问题,二是由光照变化和移动物体导致的错误运动估计结果。创新要点:通过引入全景相机到传统双目VO系统,提出一种增强型VO,高效利用全景相机360°视场角信息。(1)在线建立路口场景压缩全景路标库;(2)机器人以任意方向重新访问路标时,对定位结果进行全局校正;(3)当双目立体VO不能提供可靠定位信息时对航向角估计结果进行校正;(4)为高效利用信息量较多的全景图像,引入压缩感知概念并提出一种自适应压缩特征。研究方法:首先,在压缩亮度特征基础上,增加压缩SURF特征提高其描述能力,通过分析特征区分度,使压缩特征可以根据具体图像特点自适应调节,最终构建自适应压缩特征(ACF,图2),该特征计算速度快(表3)、描述能力强(图6、7,表1),有效提高全景图像信息利用效率。然后,使用ACF对全景路标图像进行描述,提出一种任意方向的路标图像匹配算法,若当前全景图像与路标图像匹配成功,则对当前定位结果进行全局位姿校正(图4),抑制大范围环境中定位路径漂移问题(图10、11)。最后,介绍基于图像片匹配的航向角鲁棒估计方法,当双目视觉里程计因特征跟踪质量差而导致运动估计结果不稳定时,对局部运动估计结果进行校正,提高运动估计的精度(图9)。重要结论:提出的增强型视觉里程计系统可以准实时提供可靠定位结果,极大抑制大范围挑战性环境中传统VO漂移问题和运动估计错误问题。实验结果显示,所提算法大幅度提高传统VO的准确性和鲁棒性。

关 键 词：Visual odometry Panoramic landmark Landmark matching Compressed sensing Adaptive compressive feature 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]