CSNR and JMIM Based Spectral Band Selection for Reducing Metamerism in Urban Driving
Open Access
- 3 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Intelligent Transportation Systems
- Vol. 7, 1021-1033
Abstract
Protecting Vulnerable Road Users (VRU) remains a key challenge in automotive perception, particularly when RGB imagery exhibits metameric ambiguity under challenging illumination. Hyperspectral Imaging (HSI) can provide material-dependent cues beyond RGB, including in the Near-Infrared (NIR), but its high dimensionality limits deployment in automotive systems. This paper proposes a compact band-selection pipeline that combines joint mutual information maximization with a patch-based contrast signal-to-noise ratio criterion to select a practical 3-band HSI subset for VRU perception. On the Hyperspectral City V2 dataset, the proposed pipeline selects a VIS-NIR triplet at 521 nm, 753 nm, and 903 nm. We evaluate VRU-Road separability under higher-illumination scenes and an objectively defined low-illumination subset using per-scene distributions, and bootstrap confidence intervals. Results are reported in both a metric-ready representation (for direct comparison with co-registered RGB) and a sensor-native representation. Downstream utility is further evaluated by semantic segmentation using U-Net, DeepLabV3+, and PSPNet over three random seeds. The selected triplet improves VRU-Road separability on key criteria, remains robust under low illumination, and yields competitive downstream performance among the evaluated HSI-derived inputs. Overall, the proposed approach reduces spectral dimensionality from 128 bands to 3 (97.7% reduction) and supports compact multispectral sensing as a practical complement to RGB for robust VRU perception.Keywords
All Related Versions
Funding Information
- Research Ireland (13/RC/2094_P2)
- Research Ireland (18/SP/5942)
- European Regional Development Fund through Southern and Eastern Regional Operational Programme to Lero–the Research Ireland Centre for Software
This publication has 49 references indexed in Scilit:
- Feature selection techniques for machine learning: a survey of more than two decades of researchKnowledge and Information Systems, 2023
- SOCF: A correlation filter for real-time UAV tracking based on spatial disturbance suppression and object saliency-awareExpert Systems with Applications, 2023
- Perception and sensing for autonomous vehicles under adverse weather conditions: A surveyISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Praznik: High performance information-based feature selectionSoftwareX, 2021
- Feature selection using Joint Mutual Information MaximisationExpert Systems with Applications, 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Statistical Pattern Recognition2011
- Feature Extraction2006
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004
- How strong metamerism disturbs color spacesColor Research & Application, 1998