Light Robust Monocular Depth Estimation For Outdoor Environment Via Monochrome And Color Camera Fusion

TL;DR

This paper introduces a cost-effective monocular depth estimation method for outdoor environments that fuses monochrome and color images at the pixel level, outperforming state-of-the-art techniques without requiring expensive sensors.

Contribution

Proposes a novel pixel-level fusion and stereo matching approach that enhances depth prediction efficiency and accuracy while reducing hardware and computational costs.

Findings

Outperforms state-of-the-art methods across all metrics

Efficient in cost, memory, and computation

Validated with ablation studies

Abstract

Depth estimation plays a important role in SLAM, odometry, and autonomous driving. Especially, monocular depth estimation is profitable technology because of its low cost, memory, and computation. However, it is not a sufficiently predicting depth map due to a camera often failing to get a clean image because of light conditions. To solve this problem, various sensor fusion method has been proposed. Even though it is a powerful method, sensor fusion requires expensive sensors, additional memory, and high computational performance. In this paper, we present color image and monochrome image pixel-level fusion and stereo matching with partially enhanced correlation coefficient maximization. Our methods not only outperform the state-of-the-art works across all metrics but also efficient in terms of cost, memory, and computation. We also validate the effectiveness of our design with an ablation study.