[1] [1] JIA K,CHAN T H,ZENG Z,et al.ROML:a robust feature correspondence approach for matching objects in a set of images［J］.International Journal of Computer Vision, 2016,117(2):173-197.

[2] [2] LU Y,SONG D.Visual navigation using heterogeneous landmarks and unsupervised geometric constraints［J］.IEEE Transactions on Robotics,2015,31(3):736-749.

[3] [3] CHEN J,BAUTEMBACH D,IZADI S.Scalable real-time volumetric surface reconstruction［J］.ACM Transactions on Graphics,2013,32(4): 113-124.

[4] [4] ABATE A F,NAPPI M,RICCIO D,et al.2D and 3D face recognition:a survey［J］.Pattern Recognition Letters, 2007,28(14):1885-1906.

[5] [5] RUBLEE E，RABAUD V，KONOLIGE K，et al．ORB: an efficient alternative to SIFT or SURF［C］//International Conference on Computer Vision,2011: 2564-2571.

[6] [6] BIAN J W，LIN W Y，YEUNG S K．GMS: grid-based motion statistics for fast，ultra-robust feature correspon-dence［C］//IEEE Conference on Computer Vision & Pattern Recognition，2017: 24-31.

[7] [7] TRAN Q H,CHIN T J,CARNEIRO G,et al.In defence of RANSAC for outlier rejection in deformable registration［C］//Proceedings of the European Conference on Computer Vision,Berlin:Springer,2012:274-287.

[9] [9] YUAN X P,ZHANG Y,ZHANG X,et al．ORB feature matching algorithm based on improved FAST detection［J］．Science Technology and Engineering,2019,19(21):233-239.

[11] [11] ZHAO P P,DING D R,WANG Y X,et al.An improved GMS-PROSAC algorithm for image mismatch elimination［J］.Systems Science & Control Engineering,2018,6(1):220-229.