Dr. Anthony Credoz Profile

Dr. Anthony Credoz

at Pôle d’Etudes et de Recherche de Lacq

SPIE Involvement:

Author

Publications (3)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 12 September 2021 Presentation + Paper

Deep learning based automatic detection of offshore oil slicks using SAR data and contextual information

Emna Amri, Hermann Courteille, Alexandre Benoit, Philippe Bolon, Dominique Dubucq, Gilles Poulain, Anthony Credoz

Proceedings Volume 11857, 1185707 (2021) https://doi.org/10.1117/12.2598032

KEYWORDS: Synthetic aperture radar, Image segmentation, Neural networks, Radar, Artificial intelligence, Artificial neural networks

Read Abstract +

Ocean surface monitoring, especially oil slick detection, has become mandatory due to its importance for oil exploration and risk prevention on ecosystems. For years, the detection task has been performed manually by photo-interpreters using Synthetic Aperture Radar (SAR) images with the help of contextual data such as wind. This tedious manual work cannot handle the increasing amount of data collected by the available sensors and thus requires automation. Literature reports conventional and semi-automated detection methods that generally focus either on oil slicks originating from anthropogenic (spills) or natural (seeps) sources on limited data collections. As an extension, this paper presents the automation of offshore oil slicks on an extensive database with both kinds of slicks. It builds upon the slick annotations of specialized photo-interpreters on Sentinel-1 SAR data for 6 years over 3 exploration and monitoring areas worldwide. All the considered SAR images and related annotation relate to real oil slick monitoring scenarios. Further, wind estimation is systematically computed to enrich the data collection. Paper contributions are the following : (i) a performance comparison of two deep learning approaches: semantic segmentation using FC-DenseNet and instance segmentation using Mask-RCNN. (ii) the introduction of meteorological information (wind speed) is deemed valuable for oil slick detection in the performance evaluation. The main results of this study show the effectiveness of slick detection by deep learning approaches, in particular FC-DenseNet, which captures more than 92% of oil instances in our test set. Furthermore, a strong correlation between model performances and contextual information such as slick size and wind speed is demonstrated in the performance evaluation. This work opens perspectives to design models that can fuse SAR and wind information to reduce the false alarm rate.

Proceedings Article | 5 October 2017 Paper

Hyperspectral signature analysis of three plant species to long-term hydrocarbon and heavy metal exposure

Guillaume Lassalle, Anthony Credoz, Sophie Fabre, Rémy Hédacq, Dominique Dubucq, Arnaud Elger

Proceedings Volume 10428, 104280Z (2017) https://doi.org/10.1117/12.2277709

KEYWORDS: Vegetation, Soil contamination, Reflectivity, Short wave infrared radiation, Metals, Remote sensing

Read Abstract +

Recent studies aim to exploit vegetation hyperspectral signature as an indicator of pipeline leakages and natural oil seepages by detecting changes in reflectance induced by oil exposure. In order to assess the feasibility of the method at larger spatial scale, a study has been carried out in a greenhouse on two tropical (Cenchrus alopecuroides and Panicum virgatum) and a temperate (Rubus fruticosus) species. Plants were grown on contaminated soil during 130 days, with concentrations up to 4.5 and 36 g.kg^-1 for heavy metals and C₁₀-C₄₀ hydrocarbons respectively. Reflectance data (350-2500 nm) were acquired under artificial light from 1 to 60 days. All species showed an increase of reflectance in the visible (VIS, 400-750 nm) and short-wave infrared (SWIR, 1300-2500 nm) under experimental contaminants exposure. However, the responses were contrasted in the near-infrared (NIR, 750-1300 nm). 47 normalized vegetation indices were compared between treatments, and the most sensitive to contamination were retained. Same indices showed significant differences between treatments at leaf and plant scales. Indices related to plant pigments, plant water content and red-edge reflectance were particularly sensitive to soil contamination. In order to validate the selection of indices, hyperspectral measurements were performed outdoor at plant scale at the end of the experiment (130 days). Leaf samples were also collected for pigment analysis. Index selected at day 60 were still sensitive to soil contamination after 130 days. Significant changes in plant pigment composition were also observed. This study demonstrates the interest of hyperspectral data for oil exploration and environmental diagnosis.

Proceedings Article | 18 October 2016 Paper

Experimental study of hyperspectral responses of plants grown on mud pit soil

Anthony Credoz, Rémy Hédacq, Christophe Barreau, Dominique Dubucq

Proceedings Volume 10005, 100051E (2016) https://doi.org/10.1117/12.2239606

KEYWORDS: Soil contamination, Reflectivity, Metals, Contamination, Absorption, Soil science, Remote sensing, Near infrared, Short wave infrared radiation, Vegetation

Read Abstract +

On-shore, hyperspectral imagery is currently used to detect and measure remotely oil spill extension for environmental purpose and hydrocarbon seepage for petroleum exploration. In this study, variations of hyperspectral signatures of vegetal species have been analyzed at the laboratory scale to detect indirectly the potential impacts on the plants of crude oil seepage and spills in the soil. Experimental study has been performed under greenhouse to simulate the exposure of two species of plants to a co-contamination of hydrocarbons and heavy metals contained in sludge from mud pit. Maize and bramble have been selected for this study since they are cultivated and spontaneous species respectively located in the region of interest. Five levels of exposure were performed over a period of 100 days. Reflectance evolution of each plant was measured with a spectroradiometer from 350 nm to 2500 nm with a dedicated leaf clip. Net morphological impacts were observed for maize with a global reduction of plants and leaves sizes correlated to the level of cocontamination. Hyperspectral measurement on maize revealed a higher reflectance in the absorption wavelength of water at 1450 and 1900 nm due to contamination and water stress. Reflectance in the visible increased at 600 nm (red interval) for bramble plants exposed to co-contamination. Then, the level of reflectance in the NIR decreased between 700 and 800 nm (red-edge) and absorption of water also decreased at 1450 and 1900 nm as described previously for the maize.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years