Condition-Invariant Multi-View Place Recognition

Abstract

Visual place recognition is particularly challenging when places suffer changes in its appearance. Such changes are indeed common, e.g., due to weather, night/day or seasons. In this paper we leverage on recent research using deep networks, and explore how they can be improved by exploiting the temporal sequence information. Specifically, we propose 3 different alternatives (Descriptor Grouping, Fusion and Recurrent Descriptors) for deep networks to use several frames of a sequence. We show that our approaches produce more compact and best performing descriptors than single- and multi-view baselines in the literature in two public databases.

Project website: http://webdiis.unizar.es/~jmfacil/cimvpr/ In submission

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Training a Convolutional Neural Network for Appearance-Invariant Place Recognition

Cited by in corpus (6)

• Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
• Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions
• DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
• Comparison of camera-based and 3D LiDAR-based loop closures across weather conditions
• SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition
• A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms