Robust Visual SLAM Algorithm for Dynamic Indoor Environments
作者单位：School of Robot Science and EngineeringNortheastern University
会议名称：《第40届中国控制会议》
会议日期：2021年
学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
关 键 词：simultaneous localization and mapping dynamic environment object detection motion removal
摘 要：In real scenes,traditional visual SLAM algorithm is limited by the assumption of static *** to the influence of moving objects,the traditional visual odometry makes a large number of mismatches and makes the system unable to run statically in real *** this paper,a robust visual SLAM algorithm for indoor dynamic environment is proposed based on deep ***,the object detection network is used to detect the dynamic objects and determine the moving objects in the surrounding ***,a semantic data association method and key-frame selection strategy are proposed for the tracking thread and the local graph thread to reduce the influence of moving objects on the algorithm ***,the TUM open datasets is *** results show that the proposed method reduces the mean root mean square error（RMSE） of ORB-SLAM2 by more than 94% in dynamic scenarios compared to the previous improved *** addition,compared to other deep learning based SLAM systems,the proposed method has a better balance of speed and accuracy in dynamic environments.