Show simple item record

dc.contributor.authorChen, L.
dc.contributor.authorTang, W.
dc.contributor.authorWan, Tao Ruan
dc.contributor.authorJohn, N.W.
dc.date.accessioned2020-06-17T11:24:46Z
dc.date.accessioned2020-07-07T12:54:56Z
dc.date.available2020-06-17T11:24:46Z
dc.date.available2020-07-07T12:54:56Z
dc.date.issued2020-03-14
dc.identifier.citationChen 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.urihttp://hdl.handle.net/10454/17908
dc.descriptionNoen_US
dc.description.abstractWe 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.isoenen_US
dc.relation.isreferencedbyhttps://doi.org/10.1016/j.neucom.2019.11.038en_US
dc.subjectConfidence mapen_US
dc.subjectDeep convolutional neural networksen_US
dc.subjectMonocular depth estimationen_US
dc.titleSelf-supervised monocular image depth learning and confidence estimationen_US
dc.status.refereedYesen_US
dc.date.Accepted2019-11-23
dc.date.application2019-12-04
dc.typeArticleen_US
dc.type.versionNo full-text in the repositoryen_US
dc.date.updated2020-06-17T10:24:47Z


This item appears in the following Collection(s)

Show simple item record