Fig 2 - uploaded by Anne Schistad Solberg
Content may be subject to copyright.
Oil slick on heterogeneous background. The region classified as oil is shown in the small frame (ESA/TSS/NR).
Source publication
The authors present algorithms for the automatic detection of oil
spills in SAR images. The developed framework consists of first
detecting dark spots in the image, then computing a set of features for
each dark spot, before the spot is classified as either an oil slick or
a “lookalike” (other oceanographic phenomena which resemble
oil slicks). The...
Context in source publication
Context 1
... 2-6 display the detection results in different types of scenes. A correctly classified slick on a very heterogeneous background is shown in Fig. 2. Fig. 3 shows a scene with several slicks connected to point sources. All of the slicks close to point sources were classified as oil, in addition to a small spot in the middle of the scene. Fig. 4 shows two correctly classified oil slicks connected to point sources, while Fig. 5 shows a complex scene with two lookalikes which were ...
Similar publications
Remote sensing images exhibit an enormous amount of information.
In order to extract this information in a robust way and to make it
available as efficient indices for query by image content, the authors
present a scheme of hierarchical stochastic description. The different
levels in this hierarchy are derived from the different levels of
abstracti...
Citations
... In SAR images, oil on the sea surface can be considered a dark area because of the suppression of capillary waves and a reduction in radar backscatter. This results in the depiction of oil spills as black spots, contrasting with the brighter regions of uncontaminated sea areas [5,6]. However, challenges persist, including misclassification of dark spots and the presence of lookalikes such as low wind areas and algae blooms [7][8][9]. ...
... Typically, detection methods are classified into two categories, where the input SAR image is annotated as oil spills or look-alikes. Solberg et al. [5] proposed an automated detection algorithm with a three-phase process to identify oil spills and look-alikes, including prior knowledge, Gaussian density, and rule-based density corrections. Chang et al. [10] proposed a region-based SAR oil spill detection method. ...
Oil spills are a major threat to marine and coastal environments. Their unique radar backscatter intensity can be captured by synthetic aperture radar (SAR), resulting in dark regions in the images. However, many marine phenomena can lead to erroneous detections of oil spills. In addition, SAR images of the ocean include multiple targets, such as sea surface, land, ships, and oil spills and their look-alikes. The training of a multi-category classifier will encounter significant challenges due to the inherent class imbalance. Addressing this issue requires extracting target features more effectively. In this study, a lightweight U-Net-based model, Full-Scale Aggregated MobileUNet (FA-MobileUNet), was proposed to improve the detection performance for oil spills using SAR images. First, a lightweight MobileNetv3 model was used as the backbone of the U-Net encoder for feature extraction. Next, atrous spatial pyramid pooling (ASPP) and a convolutional block attention module (CBAM) were used to improve the capacity of the network to extract multi-scale features and to increase the speed of module calculation. Finally, full-scale features from the encoder were aggregated to enhance the network’s competence in extracting features. The proposed modified network enhanced the extraction and integration of features at different scales to improve the accuracy of detecting diverse marine targets. The experimental results showed that the mean intersection over union (mIoU) of the proposed model reached more than 80% for the detection of five types of marine targets including sea surface, land, ships, and oil spills and their look-alikes. In addition, the IoU of the proposed model reached 75.85 and 72.67% for oil spill and look-alike detection, which was 18.94% and 25.55% higher than that of the original U-Net model, respectively. Compared with other segmentation models, the proposed network can more accurately classify the black regions in SAR images into oil spills and their look-alikes. Furthermore, the detection performance and computational efficiency of the proposed model were also validated against other semantic segmentation models.
... In earlier studies, researchers widely employed traditional image processing methods, including thresholding, edge detection, texture analysis, and region growing. Literature [38] proposed a dual-threshold oil spill image segmentation algorithm, which utilizes high and low thresholds to extract grayscale information at different levels and performs segmentation of oil spill regions based on a feature probability function. Ref. [39] presents a novel oil spill feature selection and classification technique based on a forest of decision trees. ...
The efficient and timely identification of oil spill areas is crucial for ocean environmental protection. Synthetic aperture radar (SAR) is widely used in oil spill detection due to its all-weather monitoring capability. Meanwhile, existing deep learning-based oil spill detection methods mainly rely on the classical U-Net framework and have achieved impressive results. However, SAR images exhibit high noise, blurry boundaries, and irregular shapes of target areas, as well as speckles and shadows, which lead to the loss of performance in existing algorithms. In this paper, we propose a novel network architecture to achieve more precise segmentation of oil spill areas by reintroducing rich semantic contextual information before obtaining the final segmentation mask. Specifically, the proposed architecture can re-fuse feature maps from different levels at the decoder end. We design a multi-convolutional layer (MCL) module to extract basic feature information from SAR images, and a feature extraction module (FEM) module further extracts and fuses feature maps generated by the U-Net decoder at different levels. Through these operations, the network can learn rich global and local contextual information, enable sufficient interaction of feature information at different stages, enhance the model’s contextual awareness, and improve its ability to recognize complex textures and blurry boundaries, thereby enhancing the segmentation accuracy of SAR images. Compared to many U-Net based segmentation networks, our method shows promising results and achieves state-of-the-art performance on multiple evaluation metrics.
... Detection of ship targets in SAR imagery has a wide range of applications, and in military applications, SAR imagery ship detection is used for maritime surveillance, target tracking and reconnaissance [15,16]. In civilian applications, SAR image ship detection is used for search and rescue operations, maritime security and environmental monitoring [17][18][19][20]. In maritime surveillance, SAR image ship detection is an important tool for monitoring shipping activities in coastal waters, identifying potential threats, and detecting illegal activities such as smuggling and piracy. ...
Synthetic Aperture Radar (SAR) is a remote sensing technology capable of high-resolution imaging of the ground surface under any weather and light conditions. SAR image ship detection is a technique that uses the ship target features in SAR images to identify and locate ships, which is of great value for applications in the fields of maritime traffic management, marine environment monitoring, and maritime security and defence. However, SAR image ship detection also faces some challenges, such as complex sea surface background, low signal-to-noise ratio, and the diversity and density of ship targets, which lead to the shortcomings of traditional feature extraction and classifier-based detection methods in terms of accuracy and efficiency. To address these challenges, this paper proposes a new method for ship detection in SAR images based on YOLOv7. When dealing with SAR images containing clutter interference and complex backgrounds, many models face the dual challenge of insufficient real-time and accuracy. To address this problem, this study proposes a new PCAN aggregation network, which firstly introduces the SimAM attention mechanism, which significantly enhances the model's ability to identify the differences between ships and background clutter, further improves the ability of focusing on target features, and effectively It further improves the ability to focus on target features, effectively reduces the interference of background noise, and improves the detection accuracy in complex scenes. At the same time, the PConv strategy is added to further lighten the model structure, thus accelerating the computation process and improving the inference efficiency. We trained and tested the model on the SAR-Ship-Dataset dataset, and achieved an accuracy of 91.1%, an F1 score of 92.9, and an FPS of 46, demonstrating its excellent detection capability. By comparing and analysing the model with several classical and cutting-edge methods in the current field, the proposed model in this study demonstrates obvious performance advantages, and in addition, through ablation experiments, we further confirm the effectiveness and contribution of PCAN.
... To distinguish oil slicks and look-alikes, classifiers in previous studies learned different features such as statistical, geometrical, textural, contextual and SAR polarimetric characteristics (Al-Ruzouq et al. 2020). As one of the statistical features, the power-to-mean ratio is commonly applied for defining the homogeneity of either oil slicks or their surroundings (Singha, Bellerby, and Trieschmann 2013;Solberg et al. 1999). Therefore, it could also be employed for detecting the discontinuity of the oil slick and its surroundings. ...
... For example, Bern et al. [14] used a manual single threshold segmentation to detect dark spots, the proposed method had simple principle, but it needed to acquire a large amount of prior knowledge of images and lack of adaptability. Solberg et al. [15] applied an adaptive threshold segmentation method to accomplish dark spot detection; its adaptability had improved, but the threshold might be local optimization. Shu et al. [16] proposed a spatial density threshold segmentation method to detect dark spots, the proposed method solved the problem of local optimal threshold, but it was easily affected by speckle noise. ...
Dark spot detection is an important and fundamental step in oil spill detection, which affects the accuracy of oil spill detection. In this paper, a Multiple-Try Markov Chain Monte Carlo (MTMCMC)-based dark spot detection method is presented under the energy function framework. Firstly, subregions, which are partitioned by geometric tessellation, replace pixels as detection units to overcome the influence of speckle noise on dark spot detection of Synthetic Aperture Radar (SAR) image. Based on the partitioned subregions, the model of characteristic random field is defined by K-S distance, and the model of label random field is established by Markov Random Field and improved Potts model. A dark spot detection model based on the partitioned subregions, that is, a regionalized dark spot detection model, is established by combining the models of characteristic random field and label random field under the energy function framework. Further, a MTMCMC algorithm is applied to simulate from the dark spot detection model to identify dark spots; In the MTMCMC algorithm, multiple try strategy is realized by defining the weight probabilities according to the detection model and proposal distribution. The proposed and three comparison methods are tested on Sentinel-1A SAR images. The average Producer's, User's and Overall accuracies of the proposed method are 97.5%, 97.9% and 98.3%, and its average Kappa coefficient is up to 0.954. Compared with the test results of three comparison methods, it can be found the defined weight probabilities of the MTMCMC can select more suitable candidate parameters of the dark spot detection model to improve the detection accuracy, and the proposed method can detect dark spots more precisely. Finally, dark spot detection results by the proposed method are used to extract the statistic and geometric features.
... These algorithms were produced by training those SAR images to detect, extract, and classify dark spots as oil spills or look-alikes. Solberg et al. (1999) also tested statistical modeling with a rule-based approach to automatic detection of oil spills in SAR images. This model was incorporated with prior knowledge of oil slicks and the algorithm managed to classify oil slicks with an accuracy of 94%. ...
Oil spills on the ocean from ships have a strong impact on the environment as well as on human societies. The MV X-Press Pearl container ship incident in 2021 became the worst marine environmental disaster in Sri Lanka due to its powerful impact. Oil leakage from the ship to the ocean continued for months. Synthetic Aperture Radar (SAR) imagery has the advantage of penetrating cloud cover, as well as day and night operating capabilities. Therefore, SAR imagery can be used to detect as well as observe the temporal changes of oil spills. The study in this article aimed to detect the oil spill caused by the MV X-Press Pearl container ship on Sri Lanka’s west coast from May to August 2021 using Sentinel-1 SAR data and measure the temporal changes of the oil slick. Three SAR imageries with Vertical-Vertical (VV) and Vertical-Horizontal (VH) polarization from June, July, and August of 2021 have been processed by applying the orbit file, running the multi-looking algorithm, and making the ellipsoid correction. The possible oil spills have been identified from each set of imagery as dark linear shapes with lengths of 3.1 ±0.012 km with an average reflectance of 15.6 decibels for June and 3.6 ±0.012 km with an average reflectance of 16.5 decibels for the other two months, and the shapes correspond with the oil slick classifications from other literature. The results indicate that the VV polarization is the most suitable to detect oil spills and that the oil spill from the X-Press Pearl continued from June to the end of August 2021.
... The adequacy of this choice was subsequently verified by evaluating the CNN performance with real data extracted from ERS images. The scientific literature provides many applications of ERS data to the maritime context [33,34], and this allows the easy identification of case studies to be used for the test of the proposed CNN in real scenarios. ...
Synthetic Aperture Radar (SAR) is a well-established 2D imaging technique employed as a consolidated practice in several oil spill monitoring services. In this scenario, onboard detection undoubtedly represents an interesting solution to reduce the latency of these services, also enabling transmission to the ground segment of alert signals with a notable reduction in the required downlink bandwidth. However, the reduced computational capabilities available onboard require alternative approaches with respect to the standard processing flows. In this work, we propose a feasibility study of oil spill detection applied directly to raw data, which is a solution not sufficiently addressed in the literature that has the advantage of not requiring the execution of the focusing step. The study is concentrated only on the accuracy of detection, while computational cost analysis is not within the scope of this work. More specifically, we propose a complete framework based on the use of a Residual Neural Network (ResNet), including a simple and automatic simulation method for generating the training data set. The final tests with ERS real data demonstrate the feasibility of the proposed approach showing that the trained ResNet correctly detects ships with a Signal-to-Clutter Ratio (SCR) > 10.3 dB.
... Polarimetric images have gained popularity in the last decade. Prematurely, Solberg et al. [24] based oil spill detection (OSD) on texture analysis of single polarimetric images. They used a Bayesian classifier to extract (12) texture features from the dark spots of oil films. ...
Several oil spill disasters have been reported in the last decade, posing a major threat to the marine ecosystem, damaging marine life, vital for protecting the environment, and reducing economic losses. In order to reduce or clean the oil spill, one needs to create a cost-effective oil spill detection system, including its source, the spill extent, the quantity estimate, the range of probable transport paths, and weather and sea conditions. Thermal and polarimetric imagery are emerging sensing modalities that show the potential for enhanced contrast in situations where conventional imaging, such as microwave, hyper-spectral, and visible imaging, has recently been researched. There is a need to compare existing thermal and polarimetric images since there is little work and data in this area. Current studies have shown some improvement in oil spill technique development. Even with the additional availability of new techniques, these steps are limited by cloud cover and lack of contrast. This article will investigate thermal and polarimetric cameras' usage for tracking 3-D oil spills in the sea by developing robust unsupervised oil sensing algorithms. It involves introducing: 1) an oil spill segmentation framework designed for thermal and polarimetric imagery; 2) a multidensity oil spill region enhancement and 3-D thickness visualization algorithm; and 3) a qualitative and quantitative oil spill analysis approach. Comparisons with existing algorithms demonstrate the effectiveness of the proposed algorithms.
... The directional diagram of such an antenna allows you to get the desired form of coverage on the angle of location, at which the received power does not depend on the range of the target at a constant target height. This achieves a greater uniformity of signal level at the receiver input when the target is moving at a constant height within the beam [12][13][14]. ...
... All processes of mathematical modelling were made with the help of PTC Mathcad Express Prime 8.0.0.0. In the beginning there were written basic and auxiliary formulas for the construction of the cosecant diagram (11)(12)(13)(14)(15)(16). ...
Due to the accelerated development of the offshore method of oil production in recent decades, especially in the Arctic region, the risks of crude oil pollution of the waters of the World Ocean are inevitably increasing. These oil spills during the exploitation of shelf deposits, transportation of oil from production sites and other anthropogenic impacts have a devastating impact on the marine biosphere, economy and life of coastal regions. For operative monitoring of water surface and fixation of oil spills it is necessary to use modern, effective and reliable methods, remote monitoring tools. One of such methods is radar. This article deals with increasing the efficiency of the radar method of water surface monitoring by means of constructive modification of the radar antenna array and changing the shape of the radio signal. As a result of the literature review, theoretical analysis of radar and conducted mathematical modeling it is substantiated the increase of radar monitoring efficiency by using phased active antenna array and construction of the cosecant-squared pattern diagram of the radio signal.
... Solberg et al. [10] proposed an automated framework that classifies dark spots into three categories: high probability, medium probability, and low probability. However, prior knowledge of the presence of oil spills around ships and oil rigs should be incorporated into the model. ...
Oil spills are the main threats to marine and coastal environments. Due to the increase in the marine transportation and shipping industry, oil spills have increased in recent years. Moreover, the rapid spread of oil spills in open waters seriously affects the fragile marine ecosystem and creates environmental concerns. Effective monitoring, quick identification, and estimation of the volume of oil spills are the first and most crucial steps for a successful cleanup operation and crisis management. Remote Sensing observations, especially from Synthetic Aperture Radar (SAR) sensors, are a very suitable choice for this purpose due to their ability to collect data regardless of the weather and illumination conditions and over far and large areas of the Earth. Owing to the relatively complex nature of SAR observations, machine learning (ML) based algorithms play an important role in accurately detecting and monitoring oil spills and can significantly help experts in faster and more accurate detection. This paper uses SAR images from ESA's Copernicus Sentinel-1 satellite to detect and locate oil spills in open waters under different environmental conditions. To this end, a deep learning framework has been presented to identify oil spills automatically. The SAR images were segmented into two classes, the oil slick and the background, using convolutional neural networks (CNN) and vision transformers (ViT). Various scenarios for the proposed architecture were designed by placing ViT networks in different parts of the CNN backbone. An extensive dataset of oil spill events in various regions across the globe was used to train and assess the performance of the proposed framework. After the detection performance assessments, the F1-score values for the standard DeepLabV3+, FC-DenseNet, and U-Net networks were 75.08 %, 73.94 %, and 60.85, respectively. In the combined networks models (combination of CNN and ViT), the best F1-score results were obtained as 78.48 %. Our results showed that these hybrid models could improve detection accuracy and have a high ability to distinguish oil spill borders even in noisy images. Evaluation metrics are increased in all the combined networks compared to the original CNN networks.
