[1] Chen H, Yang K L, Hu W Jet al. Semantic visual odometry based on panoramic annular imaging[J]. Acta Optica Sinica, 41, 2215002(2021).

[2] Macario Barros A, Michel M, YMoline et al. A comprehensive survey of visual SLAM algorithms[J]. Robotics, 11, 24-29(2022).

[3] Hou Y H, Liu Y, LLü H et al. An autonomous navigation system for UAVs based on binocular vision[J]. Journal of Tianjin University (Science and Technology), 52, 1262-1269(2019).

[4] Bergantin L, Harbaoui N, TRaharijaona et al. Oscillations make a self-scaled model for honeybees’ visual odometer reliable regardless of flight trajectory[J]. Journal of the Royal Society, 18, 20210567(2021).

[5] Campos C, Elvira R, GRodríguez J J et al. ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap SLAM[J]. IEEE Transactions on Robotics, 37, 1874-1890(2021).

[6] Lu J X, Fang Z J, Chen J Y et al. RGB-D visual odometry combined with points and lines[J]. Acta Optica Sinica, 41, 0415001(2021).

[7] Wu J, Cui Z M, Sheng V S et al. A comparative study of SIFT and its variants[J]. Measurement Science Review, 13, 122-131(2013).

[8] Oyallon E, Rabin J. An analysis of the SURF method[J]. Image Processing on Line, 5, 176-218(2015).

[9] Aglave P, Kolkure V S. Implementation of a high-performance feature extraction method using an oriented fast and rotated brief algorithm[J]. International Journal of Research in Engineering and Technology, 4, 394-397(2015).

[10] Huang H, Wang X B, Hu Y B et al. Accuracy analysis of the visual odometer for unmanned rollers in tunnels[J]. Electronics, 12, 4202-4212(2023).

[11] Jiang L, Liu Q, Lei B et al. Identifying and constructing semantic maps based on laser and vision fusions for improving localization performance[J]. Chinese Journal of Lasers, 49, 1810003(2022).

[12] Feng L X. Initialization improvement and map reuse based on ORBSLAM3[C](2021).

[13] Zhou F, Zhang L M, Deng C L et al. Improved point-line feature-based visual SLAM method for complex environments[J]. Sensors, 21, 4604(2021).

[14] Pan G F, Fan Y, Guo Y C. A low-texture monocular visual odometer based on point-line feature[C], 216-220(2021).

[15] Farnebäck G. Two-frame motion estimation based on polynomial expansion[M]. Image analysis, 2749, 363-370(2003).

[16] Horn B K P, Schunck B G. Determining the optical flow[J]. Artificial intelligence, 17, 185-203(1981).

[17] Blachut K, Kryjak T. Real-time efficient FPGA implementation of the multiscale Lucas-kanade and horn-schunck optical flow algorithms for a 4 K video stream[J]. Sensors, 22, 5017(2022).

[18] Cheng J Y, Sun Y X, Meng M Q H. Improving monocular visual SLAM in dynamic environments: an optical-flow-based approach[J]. Advanced Robotics, 33, 576-589(2019).

[19] Zhang T W, Zhang H Y, Li Y et al. FlowFusion: dynamic dense RGB-D SLAM based on optical flow[C], 7322-7328(2020).

[20] Pandey T, Pena D, JByrne et al. Leveraging deep learning for visual odometry using optical flow[J]. Sensors, 21, 1313(2021).

[21] Al-Qudah S, Yang M J. Large displacement detection using improved Lucas-kanade optical flow[J]. Sensors, 23, 3152-3165(2023).

[22] Zhu S N, Yang S M, Hu P Y et al. A robust optical flow tracking method based on a prediction model for visual-inertial odometry[J]. IEEE Robotics and Automation Letters, 6, 5581-5588(2021).

[23] Zhou C B, Su S, Chen Q J et al. E3CM: Epipolar-constrained cascade correspondence matching[J]. Neurocomputing, 559, 126788(2023).

[24] Yu Z T, Zhao C X, Wang Z Z et al. Searching central difference convolutional networks for face anti-spoofing[C], 5294-5304(2020).

[25] Theodorou C, Velisavljevic V, Dyo V. Visual SLAM for dynamic environments based on object detection and optical flow for dynamic object removal[J]. Sensors, 22, 7553(2022).

[26] Liu Y B, Miura J. RDMO-SLAM: real-time visual SLAM for dynamic environments using semantic label prediction with optical flow[J]. IEEE Access, 9, 106981-106997(2021).

[27] Liu Y, Zhou Z Y. Optical flow-based stereo visual odometry with dynamic object detection[J]. IEEE Transactions on Computational Social Systems, 10, 3556-3568(2023).

[28] Cao Y J, Zhang X S, Luo F Y et al. Learning generalized visual odometry using position-aware optical flow and geometric bundle adjustment[J]. Pattern Recognition, 136, 109262(2023).

[29] Wang X L, Zhou Y S, Yu G X et al. Lightweight visual odometry based on LK optical flow tracking[J]. Applied Sciences, 13, 11322-11333(2023).

[30] Dosovitskiy A, Fischer P, Ilg E et al. FlowNet: learning optical flow with convolutional networks[C], 2758-2766(2015).

[31] Mayer N, Ilg E, PHausscr et al. A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation[C], 4040-4048(2016).

[32] Popescu M C, Balas V E, LPerescu-Popescu et al. Multilayer perceptron and neural networks[J]. WSEAS Transactions on Circuits and Systems, 8, 579-588(2009).

[33] Sturm J, Burgard W, Cremers D. Evaluating promotion and structure-from-motion approaches using the TUM RGB-D benchmark[EB/OL]. https://cvg.cit.tum.de/_media/spezial/bib/sturm12iros_ws.pdf