[2] NISTER D, NARODITSKY O, BERGEN J. Visual odometry[C]Proceedings of 2004 IEEE computer society conference on computer vision pattern recognition. Washington, DC, USA: IEEE, 2004: I I.

[3] RUBLEE E, RABAUD V, KONOLIGE K, et al. B: an efficient alternative to SIFT SURF[C]Proceedings of 2011 international conference on computer vision. Barcelona, Spain: IEEE, 2011: 2564 2571.

[4] GEIGER A, ZIEGLER J, STILLER C. StereoScan: dense 3d reconstruction in real time[C]Proceedings of 2011 IEEE intelligent vehicles symposium (IV). BadenBaden, Germany: IEEE, 2011: 963 968.

[5] MUR-ARTAL R, MONTIEL J M M, TARDÓS J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 31, 1147-1163(2015).

[6] MUR-ARTAL R, TARDÓS J D. ORB-SLAM2: an open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 33, 1255-1262(2017).

[7] ROBERTS R, NGUYEN H, KRISHNAMURTHI N, et al. Memy based learning f visual odometry[C]Proceedings of 2008 IEEE international conference on robotics automation. Pasadena, CA, USA: IEEE, 2008: 47 52.

[8] KONDA K, MEMISEVIC R. Learning visual odometry with a convolutional wk[C]Proceedings of the 10th international conference on computer vision they applications − volume 2. Berlin, Germany, 2015: 486 − 490.

[9] KENDALL A, GRIMES M, CIPOLLA R. Pose: a convolutional wk f real time 6 DOF camera relocalization[C]Proceedings of 2015 IEEE international conference on computer vision. Santiago, Chile: IEEE, 2015: 2938 2946.

[10] WANG S, CLARK R, WEN H K, et al. DeepVO: towards endtoend visual odometry with deep recurrent convolutional neural wks[C]Proceedings of 2017 IEEE international conference on robotics automation. Singape: IEEE, 2017: 2043 2050.

[11] MCCMAC J, CLARK R, BLOESCH M, et al. Fusion++: volumetric objectlevel SLAM[C]Proceedings of 2018 IEEE international conference on 3D vision. Verona, Italy: IEEE, 2018: 32 41.

[12] DOSOVITSKIY A, FISCHER P, ILG E, et al. Flow: learning optical flow with convolutional wks[C]Proceedings of 2015 IEEE international conference on computer vision. Santiago, Chile: IEEE, 2015: 2758 2766.

[13] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]Proceedings of 2015 IEEE conference on computer vision pattern recognition (CVPR). Boston, MA, USA: IEEE, 2015: 1 9.

[14] XU B, WANG N Y, CHEN T Q, et al. Empirical evaluation of rectified activations in convolutional wk[J]. arXiv: 1505.00853, 2015.

[15] GEIGER A, LENZ P, URTASUN R. Are we ready f autonomous driving The KITTI vision benchmark suite[C]Proceedings of 2012 IEEE conference on computer vision pattern recognition (CVPR). Providence, RI, USA: IEEE, 2012: 3354 3361.