Forming a sparse representation for visual place recognition using a neurorobotic approach
This addresses visual place recognition for robotics, but it is incremental as it builds on existing bio-inspired models.
The paper tackles large-scale visual localization by introducing an unsupervised neural network model (HSD) for visual information encoding, which improves runtime speed by at least 2 times and localization accuracy by 10% on the KITTI dataset.
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.