Unsupervised Deep Persistent Monocular Visual Odometry and Depth Estimation in Extreme Environments

TL;DR

This paper introduces an unsupervised deep learning framework for monocular visual odometry and depth estimation that performs well in extreme environments, addressing challenges like perceptual degradation and lack of scale consistency.

Contribution

It presents a novel unsupervised deep VO method that predicts pose and depth with improved accuracy and robustness in challenging scenarios, including subterranean environments.

Findings

Outperforms traditional and state-of-the-art unsupervised methods in pose and depth estimation

Demonstrates robustness in extreme environments like DARPA Subterranean challenge

Achieves better results on KITTI and Cityscapes datasets

Abstract

In recent years, unsupervised deep learning approaches have received significant attention to estimate the depth and visual odometry (VO) from unlabelled monocular image sequences. However, their performance is limited in challenging environments due to perceptual degradation, occlusions and rapid motions. Moreover, the existing unsupervised methods suffer from the lack of scale-consistency constraints across frames, which causes that the VO estimators fail to provide persistent trajectories over long sequences. In this study, we propose an unsupervised monocular deep VO framework that predicts six-degrees-of-freedom pose camera motion and depth map of the scene from unlabelled RGB image sequences. We provide detailed quantitative and qualitative evaluations of the proposed framework on a) a challenging dataset collected during the DARPA Subterranean challenge; and b) the benchmark KITTI and Cityscapes datasets. The proposed approach outperforms both traditional and state-of-the-art unsupervised deep VO methods providing better results for both pose estimation and depth recovery. The presented approach is part of the solution used by the COSTAR team participating at the DARPA Subterranean Challenge.