SS-SFR: Synthetic Scenes Spatial Frequency Response on Virtual KITTI and Degraded Automotive Simulations for Object Detection

TL;DR

This study evaluates how optical degradations like Gaussian blur affect image quality and object detection performance in automotive simulations, finding detection remains robust despite significant sharpness reduction.

Contribution

It introduces a systematic analysis of image sharpness impact on object detection in automotive simulation environments, highlighting the resilience of state-of-the-art models.

Findings

Object detection performance remains stable despite sharpness degradation.

Sharpness (MTF50) decreases from 0.245 to 0.119 cy/px.

Detection accuracy drops less than 2% across models.

Abstract

Automotive simulation can potentially compensate for a lack of training data in computer vision applications. However, there has been little to no image quality evaluation of automotive simulation and the impact of optical degradations on simulation is little explored. In this work, we investigate Virtual KITTI and the impact of applying variations of Gaussian blur on image sharpness. Furthermore, we consider object detection, a common computer vision application on three different state-of-the-art models, thus allowing us to characterize the relationship between object detection and sharpness. It was found that while image sharpness (MTF50) degrades from an average of 0.245cy/px to approximately 0.119cy/px; object detection performance stays largely robust within 0.58\%(Faster RCNN), 1.45\%(YOLOF) and 1.93\%(DETR) across all respective held-out test sets.