CoHOG: A Light-Weight, Compute-Efficient, and Training-Free Visual Place Recognition Technique for Changing Environments

• Published in: IEEE robotics and automation letters Vol. 5; no. 2; pp. 1834 - 1841
• Main Authors: Zaffar, Mubariz, Ehsan, Shoaib, Milford, Michael, McDonald-Maier, Klaus
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; autonomous vehicle navigation; Changing environments; computer vision for automation; Convolutional codes; Entropy; Feature extraction; Histograms; Image management; Image retrieval; Matching; Neural networks; Recognition; Robots; SLAM; Training; visual place recognition; Visualization; Weight reduction
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2020.2969917

This letter presents a novel, compute-efficient and training-free approach based on Histogram-of-OrientedGradients (HOG) descriptor for achieving state-of-the-art performance-per-compute-unit in Visual Place Recognition (VPR). The inspiration for this approach (namely CoHOG) is based on the convolutional scanning and regions-based feature extraction employed by Convolutional Neural Networks (CNNs). By using image entropy to extract regions-of-interest (ROI) and regional-convolutional descriptor matching, our technique performs successful place recognition in changing environments. We use viewpointand appearance-variant public VPR datasets to report this matching performance, at lower RAM commitment, zero training requirements and 20 times lesser feature encoding time compared to state-of-the-art neural networks. We also discuss the image retrieval time of CoHOG and the effect of CoHOG's parametric variation on its place matching performance and encoding time.