Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Simultaneous monocular visual odometry and depth reconstruction with scale recovery

Luo, Yong, Liu, Guoliang, Liu, Hanjie, Liu, Tiantian, Tian, Guohui and Ji, Ze ORCID: 2019. Simultaneous monocular visual odometry and depth reconstruction with scale recovery. Presented at: IEEE Robio 2019, Dali, China, 6-8 December 2019. 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, pp. 682-687. 10.1109/ROBIO49542.2019.8961701

[thumbnail of Ji Z - 457.pdf] PDF - Accepted Post-Print Version
Download (6MB)


In this paper, we propose a deep neural net-work that can estimate camera poses and reconstruct thefull resolution depths of the environment simultaneously usingonly monocular consecutive images. In contrast to traditionalmonocular visual odometry methods, which cannot estimatescaled depths, we here demonstrate the recovery of the scaleinformation using a sparse depth image as a supervision signalin the training step. In addition, based on the scaled depth,the relative poses between consecutive images can be estimatedusing the proposed deep neural network. Another novelty liesin the deployment of view synthesis, which can synthesize anew image of the scene from a different view (camera pose)given an input image. The view synthesis is the core techniqueused for constructing a loss function for the proposed neuralnetwork, which requires the knowledge of the predicted depthsand relative poses, such that the proposed method couples thevisual odometry and depth prediction together. In this way,both the estimated poses and the predicted depths from theneural network are scaled using the sparse depth image as thesupervision signal during training. The experimental results onthe KITTI dataset show competitive performance of our methodto handle challenging environments.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Engineering
Publisher: IEEE
ISBN: 9871728163222
Date of First Compliant Deposit: 20 November 2019
Date of Acceptance: 1 November 2019
Last Modified: 07 Dec 2022 14:20

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics