Convolutional Neural Network-based Place Recognition
Abstract
Recently Convolutional Neural Networks (CNNs) have been shown to achieve state-of-the-art performance on various classification tasks. In this paper, we present for the first time a place recognition technique based on CNN models, by combining the powerful features learnt by CNNs with a spatial and sequential filter. Applying the system to a 70 km benchmark place recognition dataset we achieve a 75% increase in recall at 100% precision, significantly outperforming all previous state of the art techniques. We also conduct a comprehensive performance comparison of the utility of features from all 21 layers for place recognition, both for the benchmark dataset and for a second dataset with more significant viewpoint changes.
Keywords
Cite
@article{arxiv.1411.1509,
title = {Convolutional Neural Network-based Place Recognition},
author = {Zetao Chen and Obadiah Lam and Adam Jacobson and Michael Milford},
journal= {arXiv preprint arXiv:1411.1509},
year = {2014}
}
Comments
8 pages, 11 figures, this paper has been accepted by 2014 Australasian Conference on Robotics and Automation (ACRA 2014) to be held in University of Melbourne, Dec 2~4