Through the windshield driver recognition

Biometric recognition of vehicle occupants in unconstrained environments is rife with a host of challenges. In particular, the complications arising from imaging through vehicle windshields provide a significant hurdle. Distance to target, glare, poor lighting, head pose of occupants, and speed of v...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cornett, David, Yen, Alec, Nayola, Grace, Montez, Diane, Johnson, Christi R., Baird, Seth T., Santos-Villalobos, Hector, Bolme, David S.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Biometric recognition of vehicle occupants in unconstrained environments is rife with a host of challenges. In particular, the complications arising from imaging through vehicle windshields provide a significant hurdle. Distance to target, glare, poor lighting, head pose of occupants, and speed of vehicle are some of the challenges. We explore the construction of a multi-unit computational camera system to mitigate these challenges in order to obtain accurate and consistent face recognition results. This paper documents the hardware components and software design of the computational imaging system. Also, we document the use of Region-based Convolutional Neural Network (RCNN) for face detection and Generative Adversarial Network (GAN) for machine learning-inspired High Dynamic Range Imaging, artifact removal, and image fusion.
ISSN:2470-1173
2470-1173
DOI:10.2352/ISSN.2470-1173.2019.13.COIMG-140