DeepVO: A Deep Learning approach for Monocular Visual Odometry

TL;DR

This paper introduces a deep learning framework for monocular visual odometry, replacing traditional feature-based methods, and demonstrates promising real-time pose estimation results in known environments.

Contribution

It proposes a CNN architecture tailored for monocular visual odometry, highlighting its effectiveness in estimating motion and scale without additional sensors.

Findings

Deep learning can effectively estimate camera motion from monocular images.

The proposed CNN performs well in known environments for real-time pose estimation.

Pre-trained features influence the network's ability to estimate motion accurately.

Abstract

Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these approaches, they have not yet been exploited largely for solving the standard perception related problems encountered in autonomous navigation such as Visual Odometry (VO), Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM). This paper analyzes the problem of Monocular Visual Odometry using a Deep Learning-based framework, instead of the regular 'feature detection and tracking' pipeline approaches. Several experiments were performed to understand the influence of a known/unknown environment, a conventional trackable feature and pre-trained activations tuned for object classification on the network's ability to accurately estimate the motion trajectory of the camera (or the vehicle). Based on these observations, we propose a Convolutional Neural Network architecture, best suited for estimating the object's pose under known environment conditions, and displays promising results when it comes to inferring the actual scale using just a single camera in real-time.