Centre dedocumentation
scientifique

A novel deep learning instance segmentation model for automated marine oil spill detection / Shamsudeen Temitope Yekeen in ISPRS Journal of photogrammetry and remote sensing, vol 167 (September 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 167 (September 2020) . - pp 190 - 200 Titre : A novel deep learning instance segmentation model for automated marine oil spill detection Type de document : Article/Communication Auteurs : Shamsudeen Temitope Yekeen, Auteur ; Abdul‐Lateef Balogun, Auteur ; Khamaruzaman B. Wan Yusof, Auteur Année de publication : 2020 Article en page(s) : pp 190 - 200 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection automatique [Termes IGN] extraction de traits caractéristiques [Termes IGN] hydrocarbure [Termes IGN] image radar moirée [Termes IGN] marée noire [Termes IGN] segmentation sémantique [Termes IGN] vision par ordinateur [Termes IGN] zone d'intérêt Résumé : (auteur) The visual similarity of oil slick and other elements, known as look-alike, affects the reliability of synthetic aperture radar (SAR) images for marine oil spill detection. So far, detection and discrimination of oil spill and look-alike are still limited to the use of traditional machine learning algorithms and semantic segmentation deep learning models with limited accuracy. Thus, this study developed a novel deep learning oil spill detection model using computer vision instance segmentation Mask-Region-based Convolutional Neural Network (Mask R-CNN) model. The model training was conducted using transfer learning on the ResNet 101 on COCO as backbone in combination with Feature Pyramid Network (FPN) architecture for feature extraction at 30 epochs with 0.001 learning rate. Testing of the model was conducted using the least training and validation loss value on the withheld testing images. The model’s performance was evaluated using precision, recall, specificity, IoU, F1-measure and overall accuracy values. Ship detection and segmentation had the highest performance with overall accuracy of 98.3%. The model equally showed a higher accuracy for oil spill and look-alike detection and segmentation although oil spill detection outperformed look-alike with overall accuracy values of 96.6% and 91.0% respectively. The study concluded that the deep learning instance segmentation model performs better than conventional machine learning models and deep learning semantic segmentation models in detection and segmentation. Numéro de notice : A2020-548 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.07.011 date de publication en ligne : 28/07/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.07.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95774 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020093	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Applying the environmental sensitivity index for the assessment of the prospective oil spills along the Nile Delta Coast, Egypt / Rasha M. Abou Samra in Geocarto international, vol 35 n° 6 ([01/05/2020])  

Public [article]  inGeocarto international > vol 35 n° 6 [01/05/2020] . - pp 589 - 601 Titre : Applying the environmental sensitivity index for the assessment of the prospective oil spills along the Nile Delta Coast, Egypt Type de document : Article/Communication Auteurs : Rasha M. Abou Samra, Auteur ; Rasha Eissa, Auteur ; Maie El-Gammal, Auteur Année de publication : 2020 Article en page(s) : pp 589 - 601 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique [Termes IGN] analyse de sensibilité [Termes IGN] environnement [Termes IGN] hydrocarbure [Termes IGN] impact sur l'environnement [Termes IGN] Nil (delta du) [Termes IGN] Nil (fleuve) [Termes IGN] pétrole [Termes IGN] pollution des mers [Termes IGN] rivage [Termes IGN] Suez, canal de Résumé : (auteur) The Nile Delta is located very close to the Suez Canal, the main route for oil transport in the world, makes it prone to pollution from any accidental oil spills in the Mediterranean Sea. The coast of the Nile Delta is generally arcuate and highly exposed to waves and currents. The present study attempted to perform the environmental sensitivity of the shoreline to oil slicks. Six variables were incorporated together in order to determine the environmental sensitivity index (ESI). Data were collected from different resources and from in situ observations. Results showed that the ESI is generally high for the western section of the Nile Delta, particularly along Alexandria region. Low ESI was observed along the shorelines facing the coastal sand dunes at the middle part of the delta coast. The ESI is an effective approach to delineate the vulnerable coastal areas to marine oil pollution. Numéro de notice : A2020-200 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1533592 date de publication en ligne : 06/11/2018 En ligne : https://doi.org/10.1080/10106049.2018.1533592 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94870 [article]

A novel nonlinear hyperspectral unmixing approach for images of oil spills at sea / Ying Li in International Journal of Remote Sensing IJRS, vol 41 n°12 (20 - 30 March 2020)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 41 n°12 (20 - 30 March 2020) . - pp 4684 - 4701 Titre : A novel nonlinear hyperspectral unmixing approach for images of oil spills at sea Type de document : Article/Communication Auteurs : Ying Li, Auteur ; Huimin Lu, Auteur ; Zhenduo Zhang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 4684 - 4701 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse des mélanges spectraux [Termes IGN] équation polynomiale [Termes IGN] hydrocarbure [Termes IGN] image hyperspectrale [Termes IGN] marée noire [Termes IGN] modèle non linéaire [Termes IGN] pollution des mers [Termes IGN] trigonométrie Résumé : (auteur) Hyperspectral remote sensing is currently being used to detect and monitor marine oil spills that cause damage to the environment. However, nonlinear interactions of oil and water make it difficult to extract their fractional abundances from the spectral response. Improving the modelling of nonlinear hyperspectral mixtures, which is required for a thorough and reliable characterization of the materials in an image, remains a challenging yet fundamental task. This study proposes a new model that combines polynomial and trigonometric systems to understand the nonlinear effects of oil and water spectral response. Although the model is nonlinear, unmixing is performed by solving a linear problem, thus allowing fast computation. Compared to classic polynomial models, the details of nonlinear interactions are better expressed and quantified, and the reconstruction accuracy and endmember abundance estimation are improved for both synthetic and real datasets. Both the polynomial and trigonometric parts of the model play important roles in characterizing nonlinearities, with statistically linear dependence areas covering more than 90% and 30%, respectively, in oil spill images sampled after the Deepwater Horizon explosion. Analysis of the experimental results suggests that the proposed model provides an efficient and accurate unmixing method that can be used to help design oil spill response plans. Numéro de notice : A2020-452 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431161.2020.1723179 date de publication en ligne : 27/02/2020 En ligne : https://doi.org/10.1080/01431161.2020.1723179 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95540 [article]

Monitoring of marine pollution / Houma Bachari Fouzia (2019)  

Public Titre : Monitoring of marine pollution Type de document : Monographie Auteurs : Houma Bachari Fouzia, Editeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2019 Importance : 168 p. Format : 19 x 27 cm ISBN/ISSN/EAN : 978-1-83880-812-9 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] capteur optique [Termes IGN] hydrocarbure [Termes IGN] lutte contre la pollution [Termes IGN] métal lourd [Termes IGN] milieu marin [Termes IGN] pétrole [Termes IGN] pollution des mers [Termes IGN] protection de l'environnement [Termes IGN] surveillance du littoral [Termes IGN] surveillance écologique Résumé : (éditeur) Many of the pollutants discharged into the sea are directly or indirectly the result of human activities. Some of these substances are biodegradable, while others are not. This study is devoted to monitoring areas of the environment. Methods assessment is based on monitoring data and an evaluation of the impact of pollution.Surveillance provides a scientific basis for standards development and application. The methodology of marine pollution control is governed by algorithms and models. A monitoring strategy should be put in place, coupled with an environmental assessment concept, through targeted research activities in areas identified at local and regional levels. This concept will make it possible to diagnose the state of "health" of these zones and consequently to correct any anomalies. Monitoring of the marine and coastal environment is based on recent methods and validated after experiments in the field of marine pollution. Note de contenu : 1- Introductory chapter: Marine monitoring pollution 2- Detection and monitoring of marine pollution using remote sensing technologies 3- The hazards of monitoring ecosystem ocean health in the Gulf of Mexico: A Mexican perspective 4- Sediment and organisms as marker for metal pollution 5- Nitrogen and phosphorus eutrophication in marine ecosystems 6- Decadal pollution assessment and monitoring along the Kenya Coast 7- Oil spill dispersion forecasting models 8- Response of benthic foraminifera to environmental variability: Importance of benthic foraminifera in monitoring studies Numéro de notice : 25968 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.76739 En ligne : https://doi.org/10.5772/intechopen.76739 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96590

Progress in marine oil spill optical remote sensing: Detected targets, spectral response characteristics, and theories / Lu yingcheng in Marine geodesy, vol 36 n° 3 (September - November 2013)  

Public [article]  inMarine geodesy > vol 36 n° 3 (September - November 2013) . - pp 334 - 346 Titre : Progress in marine oil spill optical remote sensing: Detected targets, spectral response characteristics, and theories Type de document : Article/Communication Auteurs : Lu yingcheng, Auteur ; Xiang Li, Auteur ; Qingjiu Tian, Auteur ; et al., Auteur Année de publication : 2013 Article en page(s) : pp 334 - 346 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] détection automatique [Termes IGN] détection d'objet [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] marée noire [Termes IGN] pollution des mers [Termes IGN] réponse spectrale [Termes IGN] volume (grandeur) Résumé : (Auteur) Different oil spill pollution types could be produced in oil transport and weathering processes. Investigation of these pollution types is beneficial for oil spill recovery and processing. Optical remote sensing techniques play an important role in marine oil spill monitoring and have the ability to identify different oil spill pollution types. Recently, research on oil spill optical remote sensing has made much progress in detecting targets, identifying spectral response characteristics, and formulating theories. Floating black oil, oil slicks, and oil-water mixture in marine oil spill accidents are the main targets to be investigated by optical remote sensors. The visible spectral response differences of these targets are the base of oil spill optical remote sensing research. Bi-directional reflectance distribution function, light interference, absorption, and scattering of targets produce different spectra. Therefore, oil spill optical remote sensing could be used to identify the main oil spill pollution types and estimate oil spill volume. Numéro de notice : A2013-713 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/01490419.2013.793633 date de publication en ligne : 14/12/2009 En ligne : https://doi.org/10.1080/01490419.2013.793633 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32849 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
230-2013031	SL	Revue	Centre de documentation	Revues en salle	Disponible

On the degree of polarization for SAR sea oil slick observation / Ferdinando Nunziata in ISPRS Journal of photogrammetry and remote sensing, vol 78 (April 2013)

Permalink

Le développement durable à découvert / Agathe Euzen (2013)

Permalink

A multifrequency polarimetric SAR processing chain to observe oil fields in the Gulf of Mexico / M. Migliaccio in IEEE Transactions on geoscience and remote sensing, vol 49 n° 12 Tome 1 (December 2011)  

Permalink

Vigisat surveille l'océan depuis la Bretagne / J. Brami in CNESMAG, n° 44 (01/01/2010)

Permalink

Du naufrage de l'Amoco Cadiz à Litto3D / G. Bessero in XYZ, n° 119 (juin - août 2009)  

Permalink

Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes / Konstantinos Topouzelis in Geocarto international, vol 24 n° 3 (June - July 2009)  

Permalink

Multisensor satellite monitoring of seawater state and oil pollution in the northeastern coastal zone of the Black Sea / S. Shcherbak in International Journal of Remote Sensing IJRS, vol 29 n° 21 (October 2008)

Permalink

Accès à l'information : expérimentation d'un nouvel outil / Benoit Chanavas in Info DFCI, n° 59 (décembre 2007)

Permalink

Detection and discrimination between oil spills and look-alike phenomena through neural networks / Konstantinos Topouzelis in ISPRS Journal of photogrammetry and remote sensing, vol 62 n° 4 (September 2007)

Permalink

Procès de l'Erika : compte-rendu des débats / Alexandre Faro in La lettre du Hérisson, n° 226 (avril 2007)

Permalink