The Mertens Unrolled Network (MU-Net): A High Dynamic Range Fusion Neural Network for Through the Windshield Driver Recognition
This addresses face recognition challenges for vehicle occupants in unconstrained environments, but it is incremental as it builds on existing HDR methods.
The paper tackled face recognition through windshields by developing a custom imaging system and reformulating a classical HDR fusion algorithm as a neural network (MU-Net) for fine-tuning, resulting in improved performance verified in a SOTA facial recognition pipeline.
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.