Self-supervised monocular image depth learning and confidence estimation
Chen, L. Tang, W. Wan, Tao Ruan John, N.W.
Chen, L.
Tang, W.
Wan, Tao Ruan
John, N.W.
Publication Date
2020-03-14
End of Embargo
Supervisor
Rights
Peer-Reviewed
Yes
Open Access status
Accepted for publication
2019-11-23
Institution
Department
Awarded
Embargo end date
Additional title
Abstract
We present a novel self-supervised framework for monocular image depth learning and confidence estimation. Our framework reduces the amount of ground truth annotation data required for training Convolutional Neural Networks (CNNs), which is often a challenging problem for the fast deployment of CNNs in many computer vision tasks. Our DepthNet adopts a novel fully differential patch-based cost function through the Zero-Mean Normalized Cross Correlation (ZNCC) to take multi-scale patches as matching and learning strategies. This approach greatly increases the accuracy and robustness of the depth learning. Whilst the proposed patch-based cost function naturally provides a 0-to-1 confidence, it is then used to self-supervise the training of a parallel network for confidence map learning and estimation by exploiting the fact that ZNCC is a normalized measure of similarity which can be approximated as the confidence of the depth estimation. Therefore, the proposed corresponding confidence map learning and estimation operate in a self-supervised manner and is a parallel network to the DepthNet. Evaluation on the KITTI depth prediction evaluation dataset and Make3D dataset show that our method outperforms the state-of-the-art results.
Version
No full-text in the repository
Citation
Chen L, Tang W, Wan TR et al (2020) Self-supervised monocular image depth learning and confidence estimation. Neurocomputing. 381: 272-281.
Link to publisher’s version
Link to published version
Link to Version of Record
Type
Article