计算机工程 ›› 2018, Vol. 44 ›› Issue (9): 15-21,27.doi: 10.19678/j.issn.1000-3428.0048325

所属专题: 智能机器人专题

• 智能机器人专题 • 上一篇    下一篇

基于Inliers跟踪统计的RGB-D室内定位与地图构建

牛小宁 1,刘宏哲 1,袁家政 2,宣寒宇 1   

  1. 1.北京联合大学 北京市信息服务工程重点实验室,北京 100101; 2.北京开放大学,北京 100081
  • 收稿日期:2017-08-11 出版日期:2018-09-15 发布日期:2018-09-15
  • 作者简介:牛小宁(1991—),男,硕士研究生,主研方向为移动机器人、图像处理;刘宏哲(通信作者)、袁家政,教授、博士;宣寒宇,硕士研究生。
  • 基金项目:

    国家自然科学基金“跨媒体社群图像语义理解”(61372148);国家自然科学基金“面向视频社交网站的视频内容理解与挖掘”(61571045);国家科技支撑项目“多彩贵州文化资源集成与文化旅游综合服务应用示范”(2015BAH55F03)。

RGB-D Indoor Location and Map Building Based on Inliers Tracking Statistics

NIU Xiaoning 1,LIU Hongzhe 1,YUAN Jiazheng 2,XUAN Hanyu 1   

  1. 1.Beijing Key Laboratory of Information Service Engineering,Beijing Union University,Beijing 100101,China; 2.Beijing Open University,Beijing 100081,China
  • Received:2017-08-11 Online:2018-09-15 Published:2018-09-15

摘要:

室内移动机器人同时定位与地图构建(SLAM)的前端位姿估计与后端优化容易受运动模糊的干扰。为此,提出一种基于Inliers跟踪统计的室内定位与地图构建算法。对RGB图像进行特征提取和匹配,运用RANSAC算法得到Inliers后,通过对Inliers数量的跟踪与统计剔除受相机 运动影响的模糊图像,然后利用最近邻迭代的非线性优化方法求解相机位姿。在此基础上,通过闭环检测和优化后的全局位姿拼接出运动轨迹和三维稠密点云图。实验结果表明,相对RGB-D SLAM算法,该算法能够有效提高SLAM系统的建图鲁棒性与精度。

关键词: RGB-D相机, 同时定位与地图构建, 特征匹配, Inliers匹配内点, 非线性优化, 最近邻迭代算法

Abstract:

The front pose estimation and back-end optimization of indoor mobile robot Simultaneous Localization and Mapping (SLAM) are susceptible to motion blur.To solve this problem,an indoor location and map building algorithm based on Inliers tracking statistics is proposed.After extracting and matching the features of RGB images and using the RANSAC algorithm to get Inliers,the fuzzy images which are affected by the motion of the camera are eliminated by tracking and statistics of the number of Inliers,and then the position of the camera is solved by the nonlinear optimization method of the Iterative Closest Point (ICP).On this basis,the trajectory and 3D dense point cloud images are obtained through closed loop detection and optimized global pose.Experimental results show that,compared with RGB-D SLAM algorithm,the proposed algorithm can effectively improve the robustness and accuracy of SLAM system map building.

Key words: RGB-D camera, Simultaneous Localization and Mapping(SLAM), feature matching, Inliers matching interior point, nonlinear optimization, Iterative Closest Point(ICP) algorithm

中图分类号: