Automatic decision support system based on SAR data for oil spill detection

Mera, David; Cotos, José M.; Varela-Pet, José; Rodríguez, Pilar Vega; Caro, Andrés

doi:10.1016/j.cageo.2014.07.015

Cited by 29 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers tried to study the relative importance of features for feature selection, but their conclusions are not in consistency due to their different experiment settings. For example, Karathanassi et al [19] grouped 13 features into sea state dependent features and sea state independent features; Topouzelis et al [7,8] examined 25 most commonly used features based on neural networks and decision tree forest, and selected several feature-subsets that are of most importance; Mera et al [15] applied principal component analysis (PCA) to 17 shape related features and finally selected 5 principal components for their automatic oil spill detection system; and Xu et al [22] implemented the permutation-based variable accuracy importance (PVAI) technique to evaluate feature's importance relative to different criteria and they found that different types of classifier tended to present different patterns on feature ranking and PVAI values.…”

Section: Datasetmentioning

confidence: 99%

“…The class label of a test sample is predicted by applying the decision criteria from the root to the leaves to determine which leaf it falls in. Because of its capability of easily providing an intelligible model of the data, decision tree is very popular and widely used for classification purpose either directly [3,15] or as the elemental classifier of state-of-the-art ensemble techniques such as bagging, bundling and boosting for achieving better generality performance [8,22,[54][55][56]. Here, we use the DT supported by the classification and regression tree (CART) algorithm [53].…”

Section: Decision Treementioning

confidence: 99%

See 1 more Smart Citation

Exploring the Potential of Active Learning for Automatic Identification of Marine Oil Spills Using 10-Year (2004–2013) RADARSAT Data

Cao

Clausi

2017

Remote Sensing

View full text Add to dashboard Cite

This paper intends to find a more cost-effective way for training oil spill classification systems by introducing active learning (AL) and exploring its potential, so that satisfying classifiers could be learned with reduced number of labeled samples. The dataset used has 143 oil spills and 124 look-alikes from 198 RADARSAT images covering the east and west coasts of Canada from 2004 to 2013. Six uncertainty-based active sample selecting (ACS) methods are designed to choose the most informative samples. A method for reducing information redundancy amongst the selected samples and a method with varying sample preference are considered. Four classifiers (k-nearest neighbor (KNN), support vector machine (SVM), linear discriminant analysis (LDA) and decision tree (DT)) are coupled with ACS methods to explore the interaction and possible preference between classifiers and ACS methods. Three kinds of measures are adopted to highlight different aspect of classification performance of these AL-boosted classifiers. Overall, AL proves its strong potential with 4% to 78% reduction on training samples in different settings. The SVM classifier shows to be the best one for using in the AL frame, with perfect performance evolving curves in different kinds of measures. The exploration and exploitation criterion can further improve the performance of the AL-boosted SVM classifier but not of the other classifiers.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Decision Treementioning

confidence: 99%

Exploring the Potential of Active Learning for Automatic Identification of Marine Oil Spills Using 10-Year (2004–2013) RADARSAT Data

Cao

Clausi

2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…There are two ways in which to approach the oil-spill detection problem: studying the characterization of the slick by means of the multi-polarization features of SAR techniques, as occurs in [ 5 , 6 , 7 ], or using the brightness image obtained from the backscatter signal without considering the parameters of the processes of image acquisition and formation, as in [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. Our work falls within the second category.…”

Section: Introductionmentioning

confidence: 99%

Oil Spill Detection in Terma-Side-Looking Airborne Radar Images Using Image Features and Region Segmentation

Gil

Alacid

2018

Sensors

View full text Add to dashboard Cite

This work presents a method for oil-spill detection on Spanish coasts using aerial Side-Looking Airborne Radar (SLAR) images, which are captured using a Terma sensor. The proposed method uses grayscale image processing techniques to identify the dark spots that represent oil slicks on the sea. The approach is based on two steps. First, the noise regions caused by aircraft movements are detected and labeled in order to avoid the detection of false-positives. Second, a segmentation process guided by a map saliency technique is used to detect image regions that represent oil slicks. The results show that the proposed method is an improvement on the previous approaches for this task when employing SLAR images.

show abstract

“…Oil spills are environmental disasters that most often lead to negative important factors on aquaculture, sea grasses, coral reefs, desalination plants, fish industrial, seashell and crab farms, and tourism activities [30]. Many studies on oil spills detection and analysis have been conducted in most of the main seas and oceans with different satellites and methods: Li [30], Simecek-Beatty [31], Lardner [32], Guo [33], Mera [34], Romero [35].…”

Section: Introductionmentioning

confidence: 99%

Mapping Sea Water Surface in Persian Gulf, Oil Spill Detection Using Sentinal-1 Images

Nezhad¹,

Groppi²,

Marzialetti³

et al. 2018

Proceedings of the 4th World Congress on New Technologies

View full text Add to dashboard Cite

The present study investigates an oil spill event in the Al Khafji region using Sentinel 1 SAR images. Al Khafji is on the border between Saudi Arabia and Kuwait in the Persian Gulf and it is considered a neutral zone. Al Khafji region has the potential to produce more than 470,000 barrels of oil per day (Mbbl/d). Methods based on multi sensor satellite images (Sentinel-2, Landsat 8, Terra, Cosmo_SkyMed, RADARSAT, etc.) analysis have been developed for detecting oil slicks from known natural seeps as well as oil spill events. In this paper, one of these methods is applied to Sentinel 1 images of a known area of natural oil outflow and of a recent oil spill event in Al Khafji zone. The Synthetic Aperture Radar (SAR) is recognized as the most important remote sensing tool for sea and ocean waters oil spill monitoring, recording, documentation and dissemination. Oil spills have been detected and characterized by using the SAR images over the Persian Gulf. In particular, this paper discusses oil spills detection in the Persian Gulf assessed by using Sentinel 1 (SAR) images. Results showed the suitability of the VV polarization of the Sentinel-1 for detecting oil-spills as well as the reduced utility of the VH polarization in this context.

show abstract

Automatic decision support system based on SAR data for oil spill detection

Cited by 29 publications

References 29 publications

Exploring the Potential of Active Learning for Automatic Identification of Marine Oil Spills Using 10-Year (2004–2013) RADARSAT Data

Exploring the Potential of Active Learning for Automatic Identification of Marine Oil Spills Using 10-Year (2004–2013) RADARSAT Data

Oil Spill Detection in Terma-Side-Looking Airborne Radar Images Using Image Features and Region Segmentation

Mapping Sea Water Surface in Persian Gulf, Oil Spill Detection Using Sentinal-1 Images

Contact Info

Product

Resources

About