Acta Geodaetica et Cartographica Sinica ›› 2018, Vol. 47 ›› Issue (6): 770-779.doi: 10.11947/j.AGCS.2018.20170652

Previous Articles     Next Articles

Progress and Applications of Visual SLAM

DI Kaichang1, WAN Wenhui1, ZHAO Hongying2, LIU Zhaoqin1, WANG Runzhi1, ZHANG Feizhou2   

  1. 1. State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China;
    2. Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China
  • Received:2017-11-20 Revised:2018-03-28 Online:2018-06-20 Published:2018-06-21
  • Supported by:
    The National Key Research and Development Program of China (No.2016YFB0502102);The National Natural Science Foundation of China (No.41471388)

Abstract: Visual SLAM provides mapping and self-localization results of a robot in an unknown environment based on visual sensor,which has the advantages of small volume,low power consumption,and richness of information acquisition.Visual SLAM is critical and significant in supporting of robots’ automated and intelligent applications.This paper presents the key techniques of visual SLAM,summarizes the current status of visual SLAM research,and analyzes the new trends of visual SLAM research and development.Finally,status and prospect of visual SLAM application in restricted environments,such as deep space,indoor scene and so on,are discussed.

Key words: visual SLAM, feature extraction, Kalman filter, graph based optimization, loop closure detection

CLC Number: