Unsupervised learning of depth and ego-motion with absolutely global scale recovery from visual and inertial data sequences

Yanwen Meng, Qiyu Sun, Chongzhen Zhang and Yang Tang

Cyber-Physical Systems, 2021, vol. 7, issue 3, 133-158

Abstract: In this paper, we propose an unsupervised learning method for jointly estimating monocular depth and ego-motion, which is capable to recover the absolute scale of global camera trajectory. In order to solve the general problems of scale drift and scale ambiguity of monocular camera, we fuse geometric movement data from inertial measurement unit (IMU), and use Bi-directional Long Short-Term Memory (BiLSTM) to extract temporal features. Besides, we add a lightweight and efficient attention mechanism, Convolutional Block Attention Module (CBAM), to Convolutional Neural Networks (CNNs) to complete the extraction of image features. Considering the scenes with severe illumination changes, ambiguous structures, moving objects and occlusions, especially scenes with progressively-variant textures, the geometric features can provide adaptive estimation results in the case of the degeneration of visual features. Experiments on the KITTI driving dataset reveal that our scheme achieves promising results in the estimation of camera pose and depth. Moreover, the absolute scale recovery for the global camera trajectory is effective.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/23335777.2020.1811386 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tcybxx:v:7:y:2021:i:3:p:133-158

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tcyb20

DOI: 10.1080/23335777.2020.1811386

Access Statistics for this article

Cyber-Physical Systems is currently edited by Yang Xiao

More articles in Cyber-Physical Systems from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().