摘要
为减小动态物体对视觉SLAM的干扰,提出一种基于运动概率筛选和加权位姿估计的鲁棒动态RGB-D SLAM。首先,利用实例分割网络Yolact获取场景的语义信息,结合语义信息和深度信息对动态掩膜边界修复,根据先验运动概率的大小计算语义动态概率。然后,采用基于语义引导的方法,计算特征点的几何动态概率,将语义动态概率和几何动态概率及其置信度,通过加权融合的方式构造特征点的运动概率模型,并设计具有自适应概率阈值的特征点筛选策略。最后,在系统的位姿跟踪、局部地图优化、全局优化过程中,设计基于特征点运动概率的加权代价函数,以区分不同特征点对位姿优化的贡献。此外,在移除动态物体之后,对静态场景建立全局点云地图。公开数据集的实验结果表明,相较于ORB-SLAM2,所提算法在TUM RGB-D和Bonn数据集上的绝对轨迹误差的均方根误差分别平均降低69.16%和91.94%;与其他先进的动态SLAM算法相比,所提算法的位姿估计精度和鲁棒性均有一定程度的提升。在真实场景实验中,相较于ORB-SLAM2、Dyna-SLAM,轨迹端点漂移误差分别平均降低52.20%、19.15%。
In order to reduce the interference of dynamic objects on visual SLAM,a robust dynamic RGB-D SLAM that combines the motion probability of feature point and weighted pose estimation is proposed.First,the instance segmentation network Yolact is used to obtain semantic information of scene,combine semantic information and depth information to restore the dynamic mask boundaries,and calculate the semantic dynamic probability according to the magnitude of the prior motion probability.Then,a semantically guided method is used to calculate the geometric dynamic probability of feature point,and the semantic dynamic probability,the geometric dynamic probability and their confidence are combined to construct the motion probability of the feature point,and a feature point screening strategy with adaptive probability threshold is designed.Finally,in the process of pose tracking,local map optimization,and global optimization of the system,a weighted cost function based on the motion probability of feature point is designed to distinguish the contribution of different feature points to pose optimization.In addition,after removing the dynamic objects,a global point cloud map is established for static scenes.Experimental results on the public datasets demonstrate that,compared with ORB-SLAM2,the Root Mean Square Error of Absolute Trajectory Error of the proposed algorithm on the TUM RGB-D and Bonn datasets is reduced on average by 69.16%and 91.94%,respectively.Moreover,compared with other state-of-the-art dynamic SLAM algorithms,the proposed method exhibits noticeable improvements in both pose estimation accuracy and robustness.In real-world experiments,compared with ORB-SLAM2 and Dyna-SLAM,the trajectory endpoint drift error is reduced by an average of 52.20%and 19.15%respectively.
作者
于兴云
程向红
刘丰宇
钟志伟
Yu Xingyun;Cheng Xianghong;Liu Fengyu;Zhong Zhiwei(School of Instrument Science&Engineering,Southeast University,Nanjing 210096,China;Key Laboratory of Micro-inertial Instrument and Advanced Navigation Technology,Ministry of Education,Nanjing 210096,China)
出处
《电子测量技术》
北大核心
2025年第15期1-10,共10页
Electronic Measurement Technology
基金
国家自然科学基金(62273091)
国网江苏省电力有限公司省管产业单位科技项目(JC2024074)资助。
作者简介
于兴云,硕士研究生,主要研究方向为视觉SLAM、组合导航。E-mail:220223262@seu.edu.cn;通信作者:程向红,教授,博士生导师,主要从事导航、制导与控制方面的研究。E-mail:101005578@seu.edu.cn;刘丰宇,博士研究生,主要研究方向为激光/视觉/惯性多传感器融合定位。E-mail:liufengyu@seu.edu.cn;钟志伟,硕士研究生,主要研究方向为视觉SLAM、组合导航。E-mail:220223246@seu.edu.cn。
