Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation

TL;DR

This paper introduces a deep sensor fusion framework combining multiple cameras with uncertainty estimation to improve visual odometry accuracy and robustness in autonomous driving scenarios.

Contribution

It presents a novel deep learning-based fusion method that integrates pose and uncertainty estimates from multiple cameras for enhanced vehicle odometry.

Findings

Outperforms state-of-the-art single-camera methods

Provides more robust and accurate vehicle trajectories

Demonstrates effectiveness on the nuScenes dataset

Abstract

Visual Odometry (VO) estimation is an important source of information for vehicle state estimation and autonomous driving. Recently, deep learning based approaches have begun to appear in the literature. However, in the context of driving, single sensor based approaches are often prone to failure because of degraded image quality due to environmental factors, camera placement, etc. To address this issue, we propose a deep sensor fusion framework which estimates vehicle motion using both pose and uncertainty estimations from multiple on-board cameras. We extract spatio-temporal feature representations from a set of consecutive images using a hybrid CNN - RNN model. We then utilise a Mixture Density Network (MDN) to estimate the 6-DoF pose as a mixture of distributions and a fusion module to estimate the final pose using MDN outputs from multi-cameras. We evaluate our approach on the publicly available, large scale autonomous vehicle dataset, nuScenes. The results show that the proposed fusion approach surpasses the state-of-the-art, and provides robust estimates and accurate trajectories compared to individual camera-based estimations.