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.

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

References in corpus (2)

• Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
• Neural Codes for Image Retrieval

Cited by in corpus (13)

• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
• Training a Convolutional Neural Network for Appearance-Invariant Place Recognition
• Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions
• Deep Learning Features at Scale for Visual Place Recognition
• Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?
• MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation
• CoPR: Towards Accurate Visual Localization With Continuous Place-descriptor Regression
• ConvSequential-SLAM: A Sequence-based, Training-less Visual Place Recognition Technique for Changing Environments
• Improving Road Segmentation in Challenging Domains Using Similar Place Priors
• Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition
• A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms
• A Machine Learning Framework for Automatic Prediction of Human Semen Motility
• Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition