Detection of loop closure in visual SLAM:a stacked assorted auto-encoder based approach
CSTR:
Author:
Affiliation:

1. Key Laboratory of Optoelectronic Information Sensing and Technology, School of Optical Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;2. Engineering Research Center for Information Accessibility and Service Robots, School of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

  • Article
  • | |
  • Metrics
  • |
  • Reference [32]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    The current mainstream methods of loop closure detection in visual simultaneous localization and mapping (SLAM) are based on bag-of-words (BoW). However, traditional BoW-based approaches are strongly affected by changes in the appearance of the scene, which leads to poor robustness and low precision. In order to improve the precision and robustness of loop closure detection, a novel approach based on stacked assorted auto-encoder (SAAE) is proposed. The traditional stacked auto-encoder is made up of multiple layers of the same autoencoder. Compared with the visual BoW model, although it can better extract the features of the scene image, the output feature dimension is high. The proposed SAAE is composed of multiple layers of denoising auto-encoder, convolutional auto-encoder and sparse auto-encoder, it uses denoising auto-encoder to improve the robustness of image features, convolutional auto-encoder to preserve the spatial information of the image, and sparse auto-encoder to reduce the dimensionality of image features. It is capable of extracting low to high dimensional features of the scene image and preserving the spatial local characteristics of the image, which makes the output features more robust. The performance of SAAE is evaluated by a comparison study using data from new college dataset and city centre dataset. The methodology proposed in this paper can effectively improve the precision and robustness of loop closure detection in visual SLAM.

    Reference
    [1] DurrantWhyte Hugh F and Bailey Tim, Simultaneous Localization and Mapping. IEEE Robotics & Amp. Automation Magazine 13,99 (2006).
    [2] Jorge Fuentes-Pacheco, JoséRuiz-Ascencio and Juan Manuel Rendón-Mancha, Artificial Intelligence Review 43, 55 (2015).
    [3] Labbe M and Michaud F, IEEE Transactions on Robotics 29, 734 (2013).
    [4] Shekhar R and Jawahar C V, Word Image Retrieval Using Bag of Visual Words, IEEE 10th IAPR International Workshop on Document Analysis Systems (DAS), 297 (2012).
    [5] Cummins M and Newman P, International Journal of Robotics Research 30, 1100 (2011).
    [6] D. Galvez-López and J. D. Tardos, IEEE Transactions on Robotics 28, 1188 (2012).
    [7] E. Garcia-Fidalgo and A. Ortiz, IEEE Robotics and Automation Letters 3, 3051 (2018).
    [8] Liu Y and Zhang H, Visual Loop Closure Detection with a Compact Image Descriptor, IEEE/RSJ International Conference on Intelligent Robots and Systems, 1051 (2012).
    [9] Zhang G, Lilly M J and Vela P A, Learning Binary Features Online from Motion Dynamics for Incremental Loop-Closure Detection and Place Recognition, IEEE International Conference on Robotics and Automation (ICRA), 765 (2016).
    [10] Loukas Bampis, Angelos Amanatiadis and Antonios Gasteratos, The International Journal of Robotics Research 37, 62 (2018).
    [11] G. Zhang, X. Yan and Y. Ye, Loop Closure Detection Via Maximization of Mutual Information. IEEE Access, 124217 (2019).
    [12] Liu Q and Duan F, Intelligent Service Robotics 12, 303 (2019).
    [13] Azam Rafique Memon, Hesheng Wang and Abid Hussain, Robotics and Autonomous Systems 126, 103470 (2020).
    [14] Gomez-Ojeda R, Lopez-Antequera M, Petkov N and Gonzalez-Jimenez J, Training a Convolutional Neural Network for Appearance-Invariant Place Recognition. Computer Science, 1505 (2015).
    [15] Gao X and Zhang T, Autonomous Robots 41, 1 (2017).
    [16] Merrill N and Huang G Q, Lightweight Unsupervised Deep Loop Closure, arXiv:1805.07703, 2018.
    [17] Burguera A and Bonin-Font F, Journal of Intelligent & Robotic Systems 100, 1157 (2020).
    [18] Fei Wang, Xiaogang Ruan and Jing Huang, IOP Conference Series:Materials Science and Engineering 563, 052082 (2019).
    [19] Aritra Mukherjee, Satyaki Chakraborty and Sanjoy Kumar Saha, Applied Soft Computing 80, 650 (2019).
    [20] Chen B, Yuan D and Liu C, Applied Sciences 9, 1120 (2019).
    [21] Gao Xiang and Zhang Tao, Fourteen Lectures on Visual SLAM:From Theory to Practice (2nd Edition), Beijing:Publishing House of Electronics Industry, 302 (2019).
    [22] S. Lange and M. Riedmiller, Deep Auto-Encoder Neural Networks in Reinforcement Learning, The 2010 International Joint Conference on Neural Networks, 1 (2010).
    [23] Vincent P, Larochelle H and Bengio Y, Extracting and Composing Robust Features with Denoising Autoencoders, Machine Learning, Proceedings of the Twenty-Fifth International Conference, 1096 (2008).
    [24] Masci J, Meier U and Ciresan D, Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction. Artificial Neural Networks and Machine Learning (ICANN), International Conference on Artificial Neural Networks. 52 (2011).
    [25] Zhang L, Lu Y and Wang B, Neural Process Lett 47, 829 (2018).
    [26] Jiang X, Zhang Y, Zhang W and Xiao X, A Novel Sparse Auto-Encoder for Deep Unsupervised Learning, Sixth International Conference on Advanced Computational Intelligence (ICACI), 256 (2013).
    [27] Moacir Ponti, Josef Kittler, Mateus Riva, Teófilo de Campos and Cemre Zor, Pattern Recognition 61, 470 (2017).
    [28] Vincent P, Larochelle H and Lajoie I, Journal of Machine Learning Research 11, 3371 (2010).
    [29] Bordes A, Bottou, Léon and Gallinari P, Journal of Machine Learning Research 10, 1737 (2009).
    [30] Cummins M and Newman P, International Journal of Robotics Research 27, 647 (2008).
    [31] Kejriwal N, Kumar S and Shibata T, Robotics and Autonomous Systems 77, 55 (2016).
    [32] B. Zhou, A. Lapedriza, A. Khosla, A. Oliva and A. Torralba, IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 1452 (2018).
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

LUO Yuan, XIAO Yuting, ZHANG Yi, ZENG Nianwen. Detection of loop closure in visual SLAM:a stacked assorted auto-encoder based approach[J]. Optoelectronics Letters,2021,17(6):354-360

Copy
Share
Article Metrics
  • Abstract:644
  • PDF: 27
  • HTML: 0
  • Cited by: 0
History
  • Received:October 14,2020
  • Revised:October 30,2020
  • Online: July 07,2021
Article QR Code