A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation

TL;DR

This paper introduces a novel self-supervised monocular visual odometry method tailored for foggy conditions, utilizing robust generative adversarial networks and multi-task learning to improve depth and pose estimation accuracy.

Contribution

It presents a cycled GAN framework with gradient and perceptual losses, and a multi-task depth estimation module, specifically designed for foggy weather navigation.

Findings

Outperforms existing monocular VO methods in foggy conditions

Achieves higher accuracy in depth and pose estimation on synthetic foggy datasets

Demonstrates robustness against complex photometric changes in foggy environments

Abstract

This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. A cycled generative adversarial network is designed to obtain high-quality self-supervised loss via forcing the forward and backward half-cycle to output consistent estimation. Moreover, gradient-based loss and perceptual loss are introduced to eliminate the interference of complex photometric change on self-supervised loss in foggy weather. To solve the ill-posed problem of depth estimation, a self-supervised multi-task learning aided depth estimation module is designed based on the strong correlation between the depth estimation and transmission map calculation of hazy images in foggy weather. The experimental results on the synthetic foggy KITTI dataset show that the proposed self-supervised monocular VO performs better in depth and pose estimation than other state-of-the-art monocular VO in the literature, indicating the designed method is more suitable for foggy weather.