DeepAI AI Chat
Log In Sign Up

Scale-aware direct monocular odometry

09/21/2021
by   Carlos Campos, et al.
University of Zaragoza
0

We present a framework for direct monocular odometry based on depth prediction from a deep neural network. In contrast with existing methods where depth information is only partially exploited, we formulate a novel depth prediction residual which allows us to incorporate multi-view depth information. In addition, we propose to use a truncated robust cost function which prevents considering inconsistent depth estimations. The photometric and depth-prediction measurements are integrated in a tightly-coupled optimization leading to a scale-aware monocular system which does not accumulate scale drift. We demonstrate the validity of our proposal evaluating it on the KITTI odometry dataset and comparing it with state-of-the-art monocular and stereo SLAM systems. Experiments show that our proposal largely outperforms classic monocular SLAM, being 5 to 9 times more precise, with an accuracy which is closer to that of stereo systems.

READ FULL TEXT
07/06/2018

Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry

Monocular visual odometry approaches that purely rely on geometric cues ...
03/21/2019

Sparse2Dense: From direct sparse odometry to dense 3D reconstruction

In this paper, we proposed a new deep learning based dense monocular SLA...
10/04/2022

Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry

Monocular visual odometry consists of the estimation of the position of ...
04/22/2020

Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction

Classical monocular Simultaneous Localization And Mapping (SLAM) and the...
05/11/2017

Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect

Monocular visual odometry (VO) has seen tremendous improvements in accur...
12/01/2017

Learning Depth from Monocular Videos using Direct Methods

The ability to predict depth from a single image - using recent advances...
03/01/2021

DF-VO: What Should Be Learnt for Visual Odometry?

Multi-view geometry-based methods dominate the last few decades in monoc...