Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods

Abstract

Typical attempts to improve the capability of visual place recognition techniques include the use of multi-sensor fusion and integration of information over time from image sequences. These approaches can improve performance but have disadvantages including the need for multiple physical sensors and calibration processes, both for multiple sensors and for tuning the image matching sequence length. In this paper we address these shortcomings with a novel "multi-sensor" fusion approach applied to multiple image processing methods for a single visual image stream, combined with a dynamic sequence matching length technique and an automatic processing method weighting scheme. In contrast to conventional single method approaches, our approach reduces the performance requirements of a single image processing methodology, instead requiring that within the suite of image processing methods, at least one performs well in any particular environment. In comparison to static sequence length techniques, the dynamic sequence matching technique enables reduced localization latencies through analysis of recognition quality metrics when re-entering familiar locations. We evaluate our approach on multiple challenging benchmark datasets, achieving superior performance to two state-of-the-art visual place recognition systems across environmental changes including winter to summer, afternoon to morning and night to day. Across the four benchmark datasets our proposed approach achieves an average F1 score of 0.96, compared to 0.78 for NetVLAD and 0.49 for SeqSLAM. We provide source code for the multi-fusion method and present analysis explaining how superior performance is achieved despite the multiple, disparate, image processing methods all being applied to a single source of imagery, rather than to multiple separate sensors.

Pre-print version of article published in Robotics and Automation Letters

References in corpus (2)

• On the Performance of ConvNet Features for Place Recognition
• Look No Further: Adapting the Localization Sensory Window to the Temporal Characteristics of the Environment

Cited by in corpus (22)

• The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection
• VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change
• A Hybrid Compact Neural Architecture for Visual Place Recognition
• Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
• Augmenting Visual Place Recognition with Structural Cues
• Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions
• Probabilistic Visual Place Recognition for Hierarchical Localization
• Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments
• STA-VPR: Spatio-temporal Alignment for Visual Place Recognition
• Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems
• Online Visual Place Recognition via Saliency Re-identification
• Applications of Spiking Neural Networks in Visual Place Recognition
• Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion
• EchoVPR: Echo State Networks for Visual Place Recognition
• Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness
• AirCode: A Robust Object Encoding Method
• Filter Early, Match Late: Improving Network-Based Visual Place Recognition
• MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation
• Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
• CoPR: Towards Accurate Visual Localization With Continuous Place-descriptor Regression
• A Benchmark Comparison of Visual Place Recognition Techniques for Resource-Constrained Embedded Platforms
• Place recognition survey: An update on deep learning approaches