A robust RGB-D visual odometry with moving object detection in dynamic indoor scenes

作     者：Xianglong Zhang Haiyang Yu Yan Zhuang 

作者机构：College of Mechanical and Electronic EngineeringDalian Minzu UniversityDalianChina School of Control Science and EngineeringDalian University of TechnologyDalianChina 

出 版 物：《IET Cyber-Systems and Robotics》 (智能系统与机器人（英文）)

年 卷 期：2023年第5卷第1期

页      面：79-88页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported in part by the National Natural Science Foundation of China(Grant No.U1913201,U22B2041) Natural Science Foundation of Liaoning Province(Grant No.2019-ZD-0169) 

主　　题：dynamic indoor scenes moving object detection RGB-D SLAM visual odometry 

摘      要：Simultaneous localisation and mapping(SLAM)are the basis for many robotic *** the front end of SLAM,visual odometry is mainly used to estimate camera *** dynamic scenes,classical methods are deteriorated by dynamic objects and cannot achieve satisfactory *** order to improve the robustness of visual odometry in dynamic scenes,this paper proposed a dynamic region detection method based on RGBD ***,all feature points on the RGB image are classified as dynamic and static using a triangle constraint and the epipolar geometric constraint ***,the depth image is clustered using the K-Means *** classified feature points are mapped to the clustered depth image,and a dynamic or static label is assigned to each cluster according to the number of dynamic feature ***,a dynamic region mask for the RGB image is generated based on the dynamic clusters in the depth image,and the feature points covered by the mask are all *** remaining static feature points are applied to estimate the camera ***,some experimental results are provided to demonstrate the feasibility and performance.