On the Relation between Optical Aperture and Automotive Object Detection

TL;DR

This paper investigates how optical aperture size and shape influence automotive camera performance in deep learning tasks, proposing a PSF-based simulation method to better model optical distortions and bridge the gap between synthetic and real images.

Contribution

It introduces a novel PSF-based simulation approach to accurately model optical effects in automotive camera systems for deep learning applications.

Findings

Enhanced realism in synthetic images through optical distortion modeling

Improved domain adaptation for traffic sign recognition tasks

Reduction in simulation-to-reality gap for automotive vision systems

Abstract

We explore the impact of aperture size and shape on automotive camera systems for deep-learning-based tasks like traffic sign recognition and light state detection. A method is proposed to simulate optical effects using the point spread function (PSF), enhancing realism and reducing the domain gap between synthetic and real-world images. Computer-generated scenes are refined with this technique to model optical distortions and improve simulation accuracy.