Object Detection for Autonomous Driving: High-Dynamic Range vs. Low-Dynamic Range Images

Kocdemir I. H., Akyüz A. O., Koz A., Chalmers A., Alatan A. A., Kalkan S.

24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022, Shanghai, China, 26 - 28 September 2022 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/mmsp55362.2022.9949582
  • City: Shanghai
  • Country: China
  • Keywords: Autonomous Driving, Object Detection, High-Dynamic Range (HDR), Low-Dynamic Range (LDR)
  • Middle East Technical University Affiliated: Yes


© 2022 IEEE.An important problem in autonomous driving is to perceive objects even under challenging illumination conditions. Despite this problem, existing solutions use low-dynamic range (LDR) images for object detection for autonomous driving. In this paper, we provide a novel analysis on whether high-dynamic range (HDR) images can provide better performance for object detection for autonomous driving. To this end, we choose a seminal deep object detector and systematically evaluate its performance when trained with (i) LDR images, (ii) HDR images, and (iii) tone-mapped LDR images for scenes with different illuminations. We show that a detector with HDR images pre-processed with normalization and gamma correction can only marginally perform better than a detector with LDR or tone-mapped LDR images. Our analysis of this unexpected finding reveals that a detector with HDR images requires significantly more samples as the space of HDR images is significantly larger than that of LDR images.