Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea

Abstract : We 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.
Document type :
Journal articles
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02297235
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Wednesday, September 25, 2019 - 6:52:58 PM
Last modification on : Thursday, September 26, 2019 - 1:26:06 AM

Links full text

Identifiers

Collections

Citation

Mohamad Mazen Hittawe, Shehzad Afzal, Tahira Jamil, Hichem Snoussi, Ibrahim Hoteit, et al.. Abnormal events detection using deep neural networks: application to extreme sea surface temperature detection in the Red Sea. Journal of Electronic Imaging, SPIE and IS&T, 2019, 28 (02), pp.1. ⟨10.1117/1.JEI.28.2.021012⟩. ⟨hal-02297235⟩

Share

Metrics

Record views

10