BAI Dongdong, WANG Chaoqun, ZHANG Bo, YI Xiaodong, YANG Xuejun. CNN Feature Boosted SeqSLAM for Real-Time Loop Closure Detection[J]. Chinese Journal of Electronics, 2018, 27(3): 488-499. doi: 10.1049/cje.2018.03.010
Citation: BAI Dongdong, WANG Chaoqun, ZHANG Bo, YI Xiaodong, YANG Xuejun. CNN Feature Boosted SeqSLAM for Real-Time Loop Closure Detection[J]. Chinese Journal of Electronics, 2018, 27(3): 488-499. doi: 10.1049/cje.2018.03.010

CNN Feature Boosted SeqSLAM for Real-Time Loop Closure Detection

doi: 10.1049/cje.2018.03.010
Funds:  This work is supported by the National Natural Science Foundation of China (No.615307, No.916484, No.61601486), Research Programs of National University of Defense Technology (No.ZDYYJCYJ140601), and State Key Laboratory of High Performance Computing Project Fund (No.1502-02).
More Information
  • Corresponding author: ZHANG Bo (corresponding author) received the B.E. degree in information engineering from NUDT in 2010 and the Ph.D. degree in wireless communications from the University of Southampton in 2015. He is currently an assistant professor in National Institute of Defense Technology Innovation. His research interests in wireless communications include the design and analysis of cooperative communications, MIMO systems, and network-robotic systems. (Email:zhangbo10@nudt.edu.cn)
  • Received Date: 2016-12-12
  • Rev Recd Date: 2017-12-27
  • Publish Date: 2018-05-10
  • This paper proposes an efficient and robust Loop closure detection (LCD) method based on Convolutional neural network (CNN) feature. The primary method is called SeqCNNSLAM, in which both the outputs of the intermediate layer of a pre-trained CNN and the outputs of traditional sequence-based matching procedure are incorporated, making it possible to handle the viewpoint and condition variance properly. An acceleration algorithm for SeqCNNSLAM is developed to reduce the search range for the current image, resulting in a new LCD method called A-SeqCNNSLAM. To improve the applicability of A-SeqCNNSLAM to new environments, O-SeqCNNSLAM is proposed for online parameters adjustment in A-SeqCNNSLAM. In addition to the above work, we further put forward a promising idea to enhance SeqSLAM by integrating the both CNN features and VLAD's advantages called patch based SeqCNNSLAM (P-SeqCNNSLAM), and provide some preliminary experimental results to reveal its performance.
  • loading
  • Y. Wu, B. Zhang, X. Yi, et al., "Communication-motion planning for wireless relay-assisted multi-robot system", IEEE Wireless Communication Letters, Vol.5, No.6, pp.568-571, 2016.
    X. Zhu, X. Ruan, Z. Chen, et al., "Electromagnetic force balanced single-wheel robot", Chinese Journal of Electronics, Vol.25, No.3, pp.441-447, 2016.
    H. Wu, Y. Wu, C. Liu, et al., "Visual data driven approach for metric localization in substation", Chinese Journal of Electronics, Vol.24, No.4, pp.795-801, 2015.
    G. Zhu, C. Cheng, Y. Cai, et al., "A novel dynamic obstacle avoidance algorithm based on collision time histogram", Chinese Journal of Electronics, Vol.26, No.3, pp.552-529, 2017.
    M. Milford and G. Wyeth, "SeqSLAM:Visual route-based navigation for sunny summer days and stormy winter nights", Proc. of IEEE International Conference on Robotics and Automation, St. Paul, Minnesota, USA, pp.1643-1649, 2012.
    M. Cummins and P. Newman, "FAB-MAP:Probabilistic localization and mapping in the space of appearance", International Journal of Robotics Research, Vol.27, No.6, pp.647-665, 2008.
    S. Lowry and M. Milford, "Change removal:Robust online learning for changing appearance and changing viewpoint", Proc. of IEEE International Conference on Robotics and Automation Workshops, Seattle, Washington, USA, 2015.
    H. Jegou, M. Douze, C. Schmid, et al., "Aggregating local descriptors into a compact image representation", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, California, USA, pp.3304-3311, 2010.
    H. Bay, T. Tuytelaars and L. Gool, "SURF:Speeded up robust features", Proc. of European Conference on Computer Vision, Graz, Austria, pp.404-417, 2006.
    S. Niko, P. Neubert and P. Protzel, "Are we there yet? challenging SeqSLAM on a 3000 km journey across all four seasons", Proc. of IEEE International Conference on Robotics and Automation Workshops, Karlsruhe, Germany, 2013.
    A. Krizhevsky, I. Sutskever and G. Hinton, "Imagenet classification with deep convolutional neural networks", Proc. of Advances in Neural Information Processing Systems, Lake Tahoe, Nevada, USA, pp.1097-1105, 2012.
    A. Babenko, A. Slesarev, A. Chigorin, et al., "Neural codes for image retrieval", Proc. of European Conference on Computer Vision, Zurich, Switzerland, Vol.8689, pp.584-599, 2014.
    J. Wan, D. Wang, S. Hoi, et al., "Deep learning for contentbased image retrieval:A Comprehensive Study", Proc. of ACM International Conference on Multimedia, Orlando, Florida, USA, pp.157-166, 2014.
    Y. Hou, H. Zhang and S. Zhou, "Convolutional neural networkbased image representation for visual loop closure detection", Proc. of IEEE International Conference on Information and Automation, Lijiang, China, pp.2238-2245, 2015.
    N. Sunderhauf, S. Shirazi, F. Dayoub, et al., "On the performance of convnet features for place recognition", Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, Hamburg, Germany, pp.4297-4304, 2015.
    S. Lowry, S. Niko, P. Newman, et al., "Visual place recognition:A survey", IEEE Transactions on Robotics, Vol.32, No.1, pp.1-19, 2016.
    B. Zhou, A. Lapedriza, J. Xiao, et al., "Learning deep features for scene recognition using places database", Proc. of Advances in Neural Information Processing Systems, Montreal, Quebec, Canada, pp.487-495, 2014.
    X. Liu, J. Yin, L. Wang, et al., "An adaptive approach to learning optimal neighborhood kernels", IEEE Transactions on Cybernetics, Vol.43, No.1, pp.371-384, 2013.
    S. Zhou, J. Yin and J. Zhang, "Local binary pattern (LBP) and local phase quantization (LBQ) based on gabor filter for face representation", Neurocomputing, Vol.116, No.10, pp.260-264, 2013.
    M. Magnusson, H. Andreasson, A. Nuchter, et al., "Appearancebased loop detection from 3D laser data using the normal distributions transform", Proc. of IEEE International Conference on Information and Automation, Kobe, Japan, pp.23-28, 2009.
    R. Murartal, J. Montiel and J. Tardós, "ORB-SLAM:A versatile and accurate monocular SLAM system", IEEE Transactions on Robotics, Vol.31, No.5, pp.1147-1163, 2015.
    David. Lowe, "Distinctive image features from scale-invariant keypoints", International Journal of Computer Vision, Vol.60, No.2, pp.91-110, 2004.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (207) PDF downloads(354) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return