A monocular visual SLAM system augmented by lightweight deep local feature extractor using in-house and low-cost LIDAR-camera integrated device

作     者：Jing Li Chenhui Shi Jun Chen Ruisheng Wang Zhiyuan Yang Fan Zhang Jianhua Gong 

作者机构：National Engineering Research Center for GeoinformaticsAerospace Information Research InstituteChinese Academy of SciencesBeijingPeople’s Republic of China National Geomatics Center of ChinaBeijingPeople’s Republic of China Department of Geomatics EngineeringUniversity of CalgaryCalgaryCanada Department of Urban Studies and PlanningMassachusetts Institute of TechnologyCambridgeMAUSA 

出 版 物：《International Journal of Digital Earth》 (国际数字地球学报（英文）)

年 卷 期：2022年第15卷第1期

页      面：1929-1946页

核心收录：

学科分类：0710[理学-生物学] 0810[工学-信息与通信工程] 08[工学] 0804[工学-仪器科学与技术] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key Research and Development Program of China under[Grant number 2019YFC1511304] supported by the Pilot Fund of Frontier Science and Disruptive Technology of Aerospace Information Research Institute,Chinese Academy of Sciences under[Grant number E0Z21101]. 

主　　题：Deep local features lightweight network visual localization SLAM LiDAR 

摘      要：Simultaneous Localization and Mapping(SLAM)has been widely used in emergency response,self-driving and city-scale 3D mapping and navigation.Recent deep-learning based feature point extractors have demonstrated superior performance in dealing with the complex environmental challenges(e.***.extreme lighting)while the traditional extractors are struggling.In this paper,we have successfully improved the robustness and accuracy of a monocular visual SLAM system under various complex scenes by adding a deep learning based visual localization thread as an augmentation to the visual SLAM framework.In this thread,our feature extractor with an efficient lightweight deep neural network is used for absolute pose and scale estimation in real time using the highly accurate georeferenced prior map database at 20cm geometric accuracy created by our in-house and low-cost LiDAR and camera integrated device.The closed-loop error provided by our SLAM system with and without this enhancement is 1.03m and 18.28m respectively.The scale estimation of the monocular visual SLAM is also significantly improved(0.01 versus 0.98).In addition,a novel camera-LiDAR calibration workflow is also provided for large-scale 3D mapping.This paper demonstrates the application and research potential of deep-learning based vision SLAM with image and LiDAR sensors.