A visual localization and dense mapping algorithm based on the ORB-SLAM2 algorithm architecture is proposed to address the practical problems of low accuracy and poor real-time performance in sparse mapping of classic visual ORB-SLAM2.The algorithm is deployed on an embedded platform with Jetson Xavier NX as the core board for mapping accuracy and real-time verification,which can meet the construction requirements of clear and complete map information in high-risk scenarios that making it easy for people to quickly identify risk points Devel-op rescue plans and avoid secondary accidents.
维普
万方数据