Existing 3D reconstruction algorithms face challenges in real-time performance and robustness in complex environments, limiting their applicability in engineering. This paper proposes a tightly coupled fusion method for lidar-visual inertial measurement unit tailored to indoor settings. The method extracts and integrates geometric features from visual odometry and employs a spatial hashing-based incremental voxel structure to deeply fuse lidar point clouds with visual features. This approach optimizes computational efficiency while enabling real-time state estimation and robust mapping in environments with varying lighting and texture. Experiments on public and self-collected datasets demonstrate that the method achieves accurate pose estimation and 3D reconstruction, ensuring reliable performance in complex environments.
AkinlarCTopalC (2021) EDLines: A real-time line segment detector with a false detection control. Pattern Recognition Letters32(13): 1633–1642.
2.
BaiCXiaoTChenY, et al. (2022) Faster-LIO: Lightweight tightly coupled LiDAR-inertial odometry using parallel sparse incremental voxels. IEEE Robotics and Automation Letters7(2): 4861–4868.
3.
ChoiJSonYJeongM (2023) Gaussian kernel with correlated variables for incomplete data. Annals of Operations Research341: 895–910.
4.
ChongYHuangXDaiZ, et al. (2024) MOP-SLAM: A real-time SLAM system based on multi-head optical flow estimation network. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering238(8): 2477–2486.
5.
DwijotomoAAbdul RahmanMMohammed AriffM, et al. (2020) Cartographer slam method for optimization with an adaptive multi-distance scan scheduler. Applied Sciences10(1): 347–362.
6.
FontanAGiubilatoRMazaL, et al. (2023) SID-SLAM: Semi-direct information-driven RGB-D SLAM. IEEE Robotics and Automation Letters8(10): 6387–6394.
7.
GuTFengKCongG, et al. (2023) The RLR-tree: A reinforcement learning based R-tree for spatial data. Proceedings of the ACM on Management of Data1(1): 37–54.
8.
GuoZLiuHShiH, et al. (2023) KD-tree-based Euclidean clustering for tomographic SAR point cloud extraction and segmentation. IEEE Geoscience and Remote Sensing Letters20: 79–94.
9.
JungMYangWLeeD, et al. (2024) HeLiPR: Heterogeneous lidar dataset for inter-LiDAR place recognition under spatiotemporal variations. The International Journal of Robotics Research43(12): 1867–1883.
10.
LiCYanF, et al (2023) A 3D LiDAR odometry for UGVs using coarse-to-fine deep scene flow estimation. Transactions of the Institute of Measurement and Control45(2): 274–286.
11.
Mur-ArtalRMontielJTardosJ (2015) ORB-SLAM: A versatile and accurate monocular SLAM system. IEEE Transactions on Robotics31(5): 1147–1163.
12.
QinTLiPShenS (2018) VINS-mono: A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics34(4): 1004–1020.
13.
ShanTEnglotBMeyersD, et al. (2020) LIO-SAM: Tightly-coupled lidar inertial odometry via smoothing and mapping. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), Las Vegas, NV, 24 October–24 January, pp. 5135–5142. New York: IEEE.
14.
ShanTEnglotBRattiC, et al. (2021) LVI-SAM: Tightly-coupled lidar-visual-inertial odometry via smoothing and mapping. In: IEEE international conference on robotics and automation (ICRA), Xi’an, China, 30 May–05 June, pp. 5692–5698. New York: IEEE.
15.
TianGWangXWangR, et al. (2023) MFF-SC: A multi-feature fusion method for smart contract classification. Intelligent Data Analysis27(6): 1781–1810.
16.
TopalCAkinlarC (2011) Edge drawing: A combined real-time edge and segment detector. Journal of Visual Communication and Image Representation23(6): 862–872.
17.
WangSLiYChenD, et al. (2024) A lightweight method of pose estimation for indoor object. Intelligent Data Analysis28(4): 961–972.
18.
XuWCaiYHeD, et al. (2022) Fast-LIO2: Fast direct LiDAR-inertial odometry. IEEE Transactions on Robotics38(4): 2053–2073.
19.
XuWZhangF (2021) FAST-LIO: A fast, robust LiDAR-inertial odometry package by tightly-coupled iterated Kalman filter. IEEE Robotics and Automation Letters6(2): 3317–3324.
20.
YaoHZhangXSunG, et al. (2024) MUP-LIO: Mapping uncertainty-aware point-wise lidar inertial odometry. In: IEEE/RSJ international conference on intelligent robots and systems, Abu Dhabi, United Arab Emirates, 14–18 October, pp. 10843–10849. New York: IEEE.
21.
YeHChenYLiuM (2019) Tightly coupled 3D lidar inertial odometry and mapping. In: International conference on robotics and automation (ICRA), Montreal, QC, Canada, 20–24 May, pp. 3144–3150. New York: IEEE.
22.
YounesGKhalilDZelekJ, et al. (2024) H-SLAM: Hybrid direct-indirect visual SLAM. Robotics and Autonomous Systems2024: 104729–104743.
23.
ZhaiYLuBLiW, et al. (2021) JD-SLAM: Joint camera pose estimation and moving object segmentation for simultaneous localization and mapping in dynamic scenes. International Journal of Advanced Robotic Systems18(1): 578–592.
24.
ZhangHLuoYQinF, et al. (2021) ELSD: Efficient line segment detector and descriptor. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 10–17 October, pp. 2969–2978. New York: IEEE.
25.
ZhangLZhaoJLangZ, et al. (2024) Vehicle detection algorithm for foggy based on improved AOD-net. Transactions of the Institute of Measurement and Control46(14): 2696–2705.
26.
ZhouZZhangCLiC, et al. (2024) A tightly-coupled LIDAR-IMU SLAM method for quadruped robots. Measurement and Control57(7): 1004–1013.
27.
ZhuGLiBShiW, et al. (2023) Fisheye-based visual aligned regulation for wheeled mobile robots. Transactions of the Institute of Measurement and Control45(12): 2396–2406.
