Face recognition of vehicle occupants through windshields in unconstrained environments poses a number of unique challenges ranging from glare, poor illumination, driver pose and motion blur. In this paper, we further develop the hardware and software components of a custom vehicle imaging system to better overcome these challenges. After the build out of a physical prototype system that performs High Dynamic Range (HDR) imaging, we collect a small dataset of through-windshield image captures of known drivers. We then re-formulate the classical Mertens-Kautz-Van Reeth HDR fusion algorithm as a pre-initialized neural network, which we name the Mertens Unrolled Network (MU-Net), for the purpose of fine-tuning the HDR output of through-windshield images. Reconstructed faces from this novel HDR method are then evaluated and compared against other traditional and experimental HDR methods in a pre-trained state-of-the-art (SOTA) facial recognition pipeline, verifying the efficacy of our approach.
@article{arxiv.2002.12257,
title = {The Mertens Unrolled Network (MU-Net): A High Dynamic Range Fusion Neural Network for Through the Windshield Driver Recognition},
author = {Max Ruby and David S. Bolme and Joel Brogan and David Cornett and Baldemar Delgado and Gavin Jager and Christi Johnson and Jose Martinez-Mendoza and Hector Santos-Villalobos and Nisha Srinivas},
journal= {arXiv preprint arXiv:2002.12257},
year = {2020}
}
Comments
Accepted to SPEI Autonomous Systems: Sensors, Processing and Security for Vehicles & Infrastructure 2020