Show simple item record

dc.contributor.authorBazrafkan, Shabab
dc.contributor.authorJavidnia, Hossein
dc.contributor.authorLemley, Joseph
dc.contributor.authorCorcoran, Peter
dc.date.accessioned2018-10-08T13:59:07Z
dc.date.available2018-10-08T13:59:07Z
dc.date.issued2018-08-07
dc.identifier.citationBazrafkan, Shabab , Javidnia, Hossein , Lemley, Joseph , & Corcoran, Peter (2018). Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera. Journal of Electronic Imaging, 27(4), 19. doi: 10.1117/1.JEI.27.4.043041en_IE
dc.identifier.issn1560-229X
dc.identifier.urihttp://hdl.handle.net/10379/14585
dc.description.abstractDeep neural networks have been applied to a wide range of problems in recent years. Convolutional neural network is applied to the problem of determining the depth from a single camera image (monocular depth). Eight different networks are designed to perform depth estimation, each of them suitable for a feature level. Networks with different pooling sizes determine different feature levels. After designing a set of networks, these models may be combined into a single network topology using graph optimization techniques. This "semiparallel deep neural network (SPDNN)" eliminates duplicated common network layers and can be further optimized by retraining to achieve an improved model compared to the individual topologies. Four SPDNN models are trained and have been evaluated at two stages on the KITTI dataset. The ground truth images in the first part of the experiment are provided by the benchmark, and for the second part, the ground truth images are the depth map results from applying a state-of-the-art stereo matching method. The results of this evaluation demonstrate that using postprocessing techniques to refine the target of the network increases the accuracy of depth estimation on individual mono images. The second evaluation shows that using segmentation data alongside the original data as the input can improve the depth estimation results to a point where performance is comparable with stereo depth estimation. The computational time is also discussed in this study. (C) 2018 SPIE and IS&Ten_IE
dc.formatapplication/pdfen_IE
dc.language.isoenen_IE
dc.publisherSociety of Photo-optical Instrumentation Engineers (SPIE)en_IE
dc.relation.ispartofJournal Of Electronic Imagingen
dc.subjectDeep neural networksen_IE
dc.subjectDepth estimationen_IE
dc.subjectMonocular cameraen_IE
dc.subjectMachine learningen_IE
dc.subjectIMAGEen_IE
dc.subjectRECOGNITIONen_IE
dc.titleSemiparallel deep neural network hybrid architecture: first application on depth from monocular cameraen_IE
dc.typeArticleen_IE
dc.date.updated2018-09-27T13:44:16Z
dc.identifier.doi10.1117/1.JEI.27.4.043041
dc.local.publishedsourcehttps://dx.doi.org/10.1117/1.JEI.27.4.043041en_IE
dc.description.peer-reviewedpeer-reviewed
dc.internal.rssid14961886
dc.local.contactPeter Corcoran, Electrical & Electronic Eng, Room 3041, Engineering Building, Nui Galway. 2764 Email: peter.corcoran@nuigalway.ie
dc.local.copyrightcheckedYes
dc.local.versionSUBMITTED
nui.item.downloads126


Files in this item

Attribution-NonCommercial-NoDerivs 3.0 Ireland
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. Please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

The following license files are associated with this item:

Thumbnail

This item appears in the following Collection(s)

Show simple item record