Enhanced Depth Map Estimation in Low Light Conditions for RGB Cameras
Joseph T. Chang, Truong Q. Nguyen · 2021
Most existing depth estimation methods predict depth for daytime images and do not perform well in low-light situations due to lack of clear environmental features, glare, overexposure, and noise. This is problematic for safe autonomous driving as pedestrian and guardrail detection at night is challenging and poses life-threatening situations. This paper addresses this problem by improving image quality of disparity maps obtained in low-light based on previous work. We introduce an algorithm that combines a defogging method, which enhances night images and improves luminance, with generative adversarial or fully-convolutional networks to accurately learn the correct disparity prediction. The experiments show that the proposed method outperforms state-of-the-art methods which do not use additional preprocessing.