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.
@article{arxiv.2109.14916,
title = {Forming a sparse representation for visual place recognition using a neurorobotic approach},
author = {Sylvain Colomer and Nicolas Cuperlier and Guillaume Bresson and Olivier Romain},
journal= {arXiv preprint arXiv:2109.14916},
year = {2021}
}