HM⁴: hidden Markov model with memory management for visual place recognition
Date
2021
Authors
Doan, A.-D.
Latif, Y.
Chin, T.-J.
Reid, I.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
IEEE Robotics and Automation Letters, 2021; 6(1):167-174
Statement of Responsibility
Anh-Dzung Doan, Yasir Latif, Tat-Jun Chin, Ian Reid
Conference Name
Abstract
Visual placerecognition needs to be robust against appearance variability due to natural and man-made causes. Training data collection should thus be an ongoing process to allow continuous appearance changes to be recorded. However, this creates an unboundedly-growing database that poses time and memory scalability challenges for place recognition methods. To tackle the scalability issue for visual place recognition in autonomous driving, we develop a Hidden Markov Model approach with a two-tiered memory management. Our algorithm, dubbed HM 4 , exploits temporal look-ahead to transfer promising candidate images between passive storage and active memory when needed. The inference process takes into account both promising images and a coarse representations of the full database. We show that this allows constant time and space inference for a fixed coverage area. The coarse representations can also be updated incrementally to absorb new data. To further reduce the memory requirements, we derive a compact image representation inspired by Locality Sensitive Hashing (LSH). Through experiments on real world data, we demonstrate the excellent scalability and accuracy of the approach under appearance changes and provide comparisons against state-of-the-art techniques.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2021, IEEE