Show simple item record

dc.contributor.authorHittawe, Mohamad
dc.contributor.authorAfzal, Shehzad
dc.contributor.authorJamil, Tahira
dc.contributor.authorSnoussi, Hichem
dc.contributor.authorHoteit, Ibrahim
dc.contributor.authorKnio, Omar
dc.date.accessioned2019-05-13T11:35:39Z
dc.date.available2019-05-13T11:35:39Z
dc.date.issued2019-03-13
dc.identifier.citationHittawe MM, Afzal S, Jamil T, Snoussi H, Hoteit I, et al. (2019) Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea. Journal of Electronic Imaging 28: 1. Available: http://dx.doi.org/10.1117/1.JEI.28.2.021012.
dc.identifier.issn1017-9909
dc.identifier.doi10.1117/1.JEI.28.2.021012
dc.identifier.urihttp://hdl.handle.net/10754/652843
dc.description.abstractWe present a method based on deep learning for detecting and localizing abnormal/extreme events in sea surface temperature (SST) of the Red Sea images using training samples of normal events only. The method operates in two stages; the first one involves features extraction from each patch of the SST input image using the first two convolutional layers extracted from a pretrained convolutional neural network. In the second stage, two methods are used for training the model from the normal training data. The first method uses one-class support vector machine (1-SVM) classifier that allows a fast and robust abnormal detection in the presence of outliers in the training dataset. In the second method, a Gaussian model is defined on the Mahalanobis distances between all normal training data. Experimental tests are conducted on satellite-derived SST data of the Red Sea spanning for a period of 31 years (1985-2015). Our results suggest that the Gaussian model of Mahalanobis distances outperformed 1-SVM by providing better performance in terms of sensitivity and specificity.
dc.publisherSPIE-Intl Soc Optical Eng
dc.relation.urlhttps://www.spiedigitallibrary.org/journals/journal-of-electronic-imaging/volume-28/issue-02/021012/Abnormal-events-detection-using-deep-neural-networks--application-to/10.1117/1.JEI.28.2.021012.full
dc.rightsCopyright 2019 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
dc.subjectabnormal events detection
dc.subjectdeep neural networks
dc.subjectextreme temperature
dc.subjectRed Sea
dc.titleAbnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea
dc.typeArticle
dc.contributor.departmentApplied Mathematics and Computational Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentEarth Fluid Modeling and Prediction Group
dc.contributor.departmentEarth Science and Engineering Program
dc.contributor.departmentKing Abdullah Univ. of Science and Technology
dc.contributor.departmentPhysical Science and Engineering (PSE) Division
dc.identifier.journalJournal of Electronic Imaging
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionInstitute Charles Delaunay, Univ. de Technologie Troyes, CNRS
kaust.personHittawe, Mohamad
kaust.personAfzal, Shehzad
kaust.personJamil, Tahira
kaust.personHoteit, Ibrahim
kaust.personKnio, Omar
refterms.dateFOA2019-05-14T06:20:50Z


Files in this item

Thumbnail
Name:
021012_1.pdf
Size:
3.281Mb
Format:
PDF
Description:
Published version

This item appears in the following Collection(s)

Show simple item record