Self-supervised monocular image depth learning and confidence estimation
dc.contributor.author | Chen, L. | |
dc.contributor.author | Tang, W. | |
dc.contributor.author | Wan, Tao Ruan | |
dc.contributor.author | John, N.W. | |
dc.date.accessioned | 2020-06-17T11:24:46Z | |
dc.date.accessioned | 2020-07-07T12:54:56Z | |
dc.date.available | 2020-06-17T11:24:46Z | |
dc.date.available | 2020-07-07T12:54:56Z | |
dc.date.issued | 2020-03-14 | |
dc.identifier.citation | Chen L, Tang W, Wan TR et al (2020) Self-supervised monocular image depth learning and confidence estimation. Neurocomputing. 381: 272-281. | en_US |
dc.identifier.uri | http://hdl.handle.net/10454/17908 | |
dc.description | No | en_US |
dc.description.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. | en_US |
dc.language.iso | en | en_US |
dc.relation.isreferencedby | https://doi.org/10.1016/j.neucom.2019.11.038 | en_US |
dc.subject | Confidence map | en_US |
dc.subject | Deep convolutional neural networks | en_US |
dc.subject | Monocular depth estimation | en_US |
dc.title | Self-supervised monocular image depth learning and confidence estimation | en_US |
dc.status.refereed | Yes | en_US |
dc.date.Accepted | 2019-11-23 | |
dc.date.application | 2019-12-04 | |
dc.type | Article | en_US |
dc.type.version | No full-text in the repository | en_US |
dc.date.updated | 2020-06-17T10:24:47Z |