SeqSLAM是移动机器人领域广泛使用的一种视觉定位算法,它对光照等因素较鲁棒,但受视角变化影响较大。另外,SeqSLAM采用了蛮力搜索匹配的方式,在较大规模数据集中无法满足实时性要求。针对以上问题,对SeqSLAM算法做了两方面的改进:首先将图像表示为局部聚合描述子向量,提取图像特征;然后采用层次化可导航小世界网络算法搜索相似图像序列,具有更高的搜索效率。测试表明,改进的SeqSLAM算法可以获得更高的精确率和召回率,搜索时间显著降低。
SeqSLAM is a widely used loop closure detection algorithm in mobile robot and autonomous vehicle field. It could recognize revisited places by comparing sequences of images even under dramatic changes of season, illumination, and weather. However, SeqSLAM is vulnerable to viewpoint changes. In addition, SeqSLAM compares sequences of images by brute force method, which prevents its real-time application to large-scale image datasets. To address these problems, we first represent each image by a kind of low dimensional description — vector of locally aggregated descriptors (VLAD) which is robust to viewpoint changes, and then replace the brute force method by an approximate nearest neighbor search algorithm — hierarchical navigable small world graphs (HNSW). Tests on publicly available datasets show that, the improved SeqSLAM with VLAD and HNSW could obtain much better detection results in the respect of precision-recall evaluation and the search time is reduced by orders of magnitude. We make code publicly available at https://github.com/qipengliuNTU/Efficient-SeqSLAM-with-HNSW.
[1] CADENA C, CARLONE L, CARRILLO H, et al. Past, present, and future of simultaneous localization and mapping: toward the robust-perception age[J]. IEEE Transactions on Robotics, 2016, 32(6): 13091332.
[2] 王霞,左一凡. 视觉SLAM研究进展[J]. 智能系统学报, 2020, 15(5): 825834.
WANG X, ZUO Y F. Advances in visual SLAM research[J]. CAAI Transactions on Intelligent Systems, 2020, 15(5): 825834.
[3] 刘强, 段富海, 桑勇, 等. 复杂环境下视觉SLAM闭环检测方法综述[J]. 机器人, 2019, 41(1): 112123.
LIU Q, DUAN F, SANG Y, et al. A survey of loop-closure detection method of visual SLAM in complex environments[J]. Robot, 2019, 41(1): 112123.
[4] 杨淑静, 丛海林, 杨超. 动态运行复杂体系档案信息化管理问题与对策——青岛大学材料学科实训平台[J]. 化学教育(中英文), 2023, 44(4): 115121.
YANG S J, CONG H L, YANG C. Problems and countermeasures of archives information management in dynamic operation complex system: material discipline training platform of Qingdao university[J]. Chinese Journal of Chemical of Education, 2023, 44(4):115121.
[5] MILFORD M, WYETH G. SeqSLAM: visual route-based navigation for sunny summer days and stormy winter nights[C]//Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Saint Paul:IEEE, 2012: 16431649.
[6] MILFORD M, SHEN C, LOWRY S, et al. Sequence searching with deep-learnt depth for condition and viewpoint invariant route-based place recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Boston:IEEE, 2015: 1825.
[7] TSINTOTAS K, BAMPIS L, RALLIS S, et al. SeqSLAM with bag of visual words for appearance based loop closure detection[C]//Proceedings of the International Conference on Robotics in Alpe-Adria Danube Region. Patras: Springer, 2018: 580587.
[8] JEGOU H, DOUZE M, SCHMID C, et al. Aggregating local descriptors into a compact image representation[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco: IEEE, 2010: 33043311.
[9] NASEER T, SPINELLO L, BURGARD W, et al. Robust visual robot localization across seasons using network flows[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Quebec: AAAI, 2014: 25642570.
[10] HANSEN P, BROWNING B. Visual place recognition using HMM sequence matching[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Chicago: IEEE, 2014: 45494555.
[11] SIAM S, ZHANG H. Fast-SeqSLAM: a fast appearance based place recognition algorithm[C]//Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Singapore: IEEE, 2017: 57025708.
[12] MALKOV Y, YASHUNIN D. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(4), 824836.
[13] KLEINBERG J. Navigation in a small world[J]. Nature, 2000, 406(6798): 845.
[14] 周键,董永红.测控实验室内关键节点电压的校正方法仿真[J].计算机仿真,2022,39(7):124127,223.
Zhou J, DONG Y H.Simulation of voltage correction method for pilot nodes in measurement and control laboratory[J].Computer Simulation,2022, 39(7):124127,223.
[15] ARANDJELOVIC R, GRONAT P, TORII A, et al. NetVLAD: CNN architecture for weakly supervised place recognition[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 52975307.
