This paper introduces a novel unsupervised neural network model for visual information encoding which aims to address the problem of large-scale visual localization. Inspired by the structure of the visual cortex, the model (namely HSD) alternates layers of topologic sparse coding and pooling to build a more compact code of visual information. Intended for visual place recognition (VPR) systems that use local descriptors, the impact of its integration in a bio-inpired model for self-localization (LPMP) is evaluated. Our experimental results on the KITTI dataset show that HSD improves the runtime speed of LPMP by a factor of at least 2 and its localization accuracy by 10%. A comparison with CoHog, a state-of-the-art VPR approach, showed that our method achieves slightly better results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Forming a sparse representation for visual place recognition using a neurorobotic approach


    Contributors:


    Publication date :

    2021-09-19


    Size :

    1482871 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Brain-Inspired Spiking Neural Network Controller for a Neurorobotic Whisker System

    Antonietti A. / Geminiani A. / Negri E. et al. | BASE | 2022

    Free access

    Robust face recognition using sparse representation in LDA space

    Adamo, A. | British Library Online Contents | 2015


    Multi-View Automatic Target Recognition using Joint Sparse Representation

    Haichao Zhang, / Nasrabadi, N. M. / Zhang, Y. et al. | IEEE | 2012


    BLOCK-SPARSE REPRESENTATION CLASSIFICATION BASED GESTURE RECOGNITION APPROACH FOR A ROBOTIC WHEELCHAIR

    Boyali, A. / Hashimoto, N. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2014


    Visual Place Recognition in Changing Environments

    Vysotska, Olga | BASE | 2019

    Free access