农业场景下移动机器人的双目视觉定位与地图构建方法  

Stereo Visual Localization and Mapping for Mobile Robot in Agricultural Environments

作　　者：余涛[1] 熊盛武[1,2] YU Tao;XIONG Shengwu(School of Computer Science and Artificial Intelligence,Wuhan University of Technology,Wuhan 430070,China;Sanya Science and Education Innovation Park of Wuhan University of Technology,Sanya,Hainan 572000,China)

机构地区：[1]武汉理工大学计算机科学与人工智能学院,武汉430070 [2]武汉理工大学三亚科教创新园,海南三亚572000

出　　处：《计算机科学》2023年第12期185-191,共7页Computer Science

基　　金：国家自然科学基金(62176194,62101393);车联网重大项目(2020AAA001);三亚崖州湾科技城项目(SCKJ-JYRC-2022-76);武汉理工大学三亚科教创新园项目(2021KF0031);重庆市自然科学基金(cstc2021jcyj-msxmX1148)。

摘　　要：视觉定位与地图构建是实现移动机器人自主导航的关键技术。针对农业场景下特征跟踪困难、场景规模大、运动不稳定引起系统精度和鲁棒性下降的问题,提出了一种适用于农业场景的双目视觉定位与地图构建方法。该方法首先利用静态立体匹配点来增加跟踪阶段地图点的数量和覆盖范围,从而增加了深度计算的准确率,同时提出一种点选择算法对密集地图点进行采样并移除离群点,进一步提高了系统的准确率和运行效率;然后通过显式尺度估计来减小大规模场景下定位与地图构建的尺度误差,并结合场景特点改进关键帧判别策略,避免了远处大目标导致关键帧稀疏的问题;最后提出新的运动假设构建位姿估计失败时的恢复策略,提高了系统在颠簸运动时的鲁棒性。在农业场景数据集上的评估结果表明,相比于当前先进的视觉定位与地图构建系统,提出的方法在困难序列上的轨迹误差降低幅度超过50%,其中3个序列上的尺度误差下降了一个数量级,取得了更高的精度和鲁棒性,能有效地应对农业场景下视觉定位与地图构建的挑战。Visual-based localization and mapping is the key technology for autonomous robots.Visual localization and mapping in agricultural environments faces more challenges,including few distinguishable landmarks for tracking,large-scale scene,unstable movements.To address these problems,a stereo visual localization and mapping method is proposed.Static stereo matching points are used to increase the number andcoverage of map points,which improve the accuracy of depth calculation.A point selection method is proposed to further improve the accuracy and efficiency by sampling the dense map points and removing outliers.Then scale estimation is proposed to reduce the scale error of localization and mapping in large scale agricultural scenes.Keyframe criteria is adapted to avoid the impact of large far-away objects that could cause abnormal keyframe distribution.Finally,a new motion assumption is proposed to recover the system from failure tracking,which improves the system's robustness at the case of unstable movements.Experimental results show that the proposed method achieves better performance than other state-of-the-art vi-sual localization and mapping systems.By addressing the challenges individually,the proposed visual localization and mapping system is more accurate and robust in agricultural environments.

关 键 词：农业场景 视觉定位与地图构建 直接法 双目视觉 尺度估计 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]