Semantic Loopback Detection Method Based on Instance Segmentation and Visual SLAM in Autonomous Driving

被引:2
作者
Huang, Li [1 ]
Zhu, Zhe [1 ]
Yun, Juntong [2 ,3 ,4 ]
Xu, Manman [2 ,3 ,4 ]
Liu, Ying [2 ,4 ]
Sun, Ying [2 ,3 ,4 ]
Hu, Jun [2 ,3 ,4 ]
Li, Fazeng [2 ,3 ,4 ]
机构
[1] Wuhan Univ Sci & Technol, Coll Comp Sci & Technol, Hubei Prov Key Lab Intelligent Informat Proc & Rea, Wuhan 430081, Peoples R China
[2] Wuhan Univ Sci & Technol, Precis Mfg Res Inst, Res Ctr Biomimet Robot & Intelligent Measurement &, Key Lab Met Equipment & Control Technol,Minist Edu, Wuhan 430081, Peoples R China
[3] Wuhan Univ Sci & Technol, Hubei Key Lab Mech Transmiss & Mfg Engn, Wuhan 430081, Peoples R China
[4] Hubei Longzhong Lab, Xiangyang 441000, Peoples R China
基金
中国国家自然科学基金;
关键词
Visual SLAM; image segmentation; semantic information; data association; loopback detection; autonomous driving; IMAGE; PERCEPTION;
D O I
10.1109/TITS.2023.3315231
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Autonomous driving has gradually become a research hotspot in recent years, but the robustness of loopback detection in complex environments such as dynamic and weak textures needs to be improved. A semantic loopback detection method is proposed based on instance segmentation and visual SLAM to make sufficient use of semantic information in autonomous driving. The proposed method combines image segmentation and visual SLAM (Simultaneous Localization and Mapping) to construct a semantic SLAM system. What's more, a data association method that combines semantic and geometric information is proposed to improve the traditional loopback detection method by using semantic information to increase the accuracy of loopback detection. The result of experiment on the TUM public dataset shows that the loopback detection accuracy of the improved loopback detection method is higher than that of the bag-of-words method in all four datasets, and our proposed algorithm can effectively improve the accuracy of loopback detection of the SLAM system in general.
引用
收藏
页码:3118 / 3127
页数:10
相关论文
共 50 条
  • [31] Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
    Yao, Shanliang
    Guan, Runwei
    Huang, Xiaoyu
    Li, Zhuoxiao
    Sha, Xiangyu
    Yue, Yong
    Lim, Eng Gee
    Seo, Hyungjoon
    Man, Ka Lok
    Zhu, Xiaohui
    Yue, Yutao
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2024, 9 (01): : 2094 - 2128
  • [32] Semantic Segmentation of Road Profiles for Efficient Sensing in Autonomous Driving
    Cheng, Guo
    Zheng, Jiang Yu
    Kilicarslan, Mehmet
    2019 30TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV19), 2019, : 564 - 569
  • [33] Improvement of Semantic Segmentation with DC-GAN in Autonomous driving
    Moghadas, Seyed Mohammad
    Hamian, Mohamad Hossein
    Ahmadi, Ali
    2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 1162 - 1166
  • [34] Loop Closure Detection Based on Local Semantic Topology for Visual SLAM System
    Zhang K.
    Zhang Y.
    Lü G.
    Gong Y.
    Jiqiren/Robot, 2019, 41 (05): : 649 - 659
  • [35] YS-SLAM: YOLACT plus plus based semantic visual SLAM for autonomous adaptation to dynamic environments of mobile robots
    Li, Jiajie
    Luo, Jingwen
    COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (04) : 5771 - 5792
  • [36] OMS-SLAM: dynamic scene visual SLAM based on object detection with multiple geometric feature constraints and statistical threshold segmentation
    Tang, Jialiang
    Feng, Zhengyong
    Liao, Peng
    Chen, Liheng
    Xiao, Xiaomei
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (10)
  • [37] Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
    Feng, Di
    Haase-Schutz, Christian
    Rosenbaum, Lars
    Hertlein, Heinz
    Glaser, Claudius
    Timm, Fabian
    Wiesbeck, Werner
    Dietmayer, Klaus
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 22 (03) : 1341 - 1360
  • [38] Semantic segmentation of autonomous driving scenes based on multi-scale adaptive attention mechanism
    Liu, Danping
    Zhang, Dong
    Wang, Lei
    Wang, Jun
    FRONTIERS IN NEUROSCIENCE, 2023, 17
  • [39] EPNet: An Efficient Postprocessing Network for Enhancing Semantic Segmentation in Autonomous Driving
    Sun, Libo
    Xia, Jiatong
    Xie, Hui
    Sun, Changming
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [40] Semantic Segmentation using Modified U-Net for Autonomous Driving
    Sugirtha, T.
    Sridevi, M.
    2022 IEEE INTERNATIONAL IOT, ELECTRONICS AND MECHATRONICS CONFERENCE (IEMTRONICS), 2022, : 831 - 837