Convolutional Neural Network-based Place Recognition

2014/11/06 by Zetao Chen, Obadiah Lam, Chen, Zetao +5 · 7 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Indoor and Outdoor Localization Technologies #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.1411.1509

openalex publication_date 2014/11/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• OverFeat: Integrated Recognition, Localization and Detection using\n Convolutional Networks
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual\n Recognition
• Visualizing and Understanding Convolutional Networks
• CNN Features off-the-shelf: an Astounding Baseline for Recognition

Cited by

• Omnidirectional CNN for Visual Place Recognition and Navigation
• Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?
• Lightweight Unsupervised Deep Loop Closure
• A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Deep Learning Features at Scale for Visual Place Recognition
• Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization

Related

• Spatio-Semantic ConvNet-Based Visual Place Recognition
• Deep Learning Features at Scale for Visual Place Recognition
• Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration
• Point-cloud-based place recognition using CNN feature extraction
• NetVLAD: CNN architecture for weakly supervised place recognition