SAR图像在韩国溢油监测中的应用

利用SAR图像,对2007年12月发生在韩国的溢油事件进行监测。首先分析了SAR图像监测溢油的原理和限制,然后以ENVISAT\|ASAR数据为例,分析SAR数据处理与信息提取过程,其中包括:进行几何精校正、对图像进行增强处理、滤波、分类。最后根据SAR图像综合信息,解译勾画出溢油信息边界,利用GIS系统叠加风场、地形、其它重要要素数据,对溢油的分布、扩散以及对周边环境的影响进行分析评价,为决策者提供决策支持。     

SAR影像海洋表面溢油检测方法与实现

海洋是地球的重要组成部分,它为人类提供了丰富的物质和宝贵的资源,每年海洋都承受着不同程度的侵害,其中油类污染是给海洋造成巨大危害的污染之一。而油类污染又主要来源于轮船破裂漏油以及油井平台或海底输油管道爆炸等。每次事故造成的直接经济损失达几百万至上千万不等,所以对海上溢油进行监测具有重要的意义。选用Envisat的ASAR数据进行海上溢油检测,介绍并分析了SAR图像溢油检测的一般步骤及其实现方法,通过采用单一阈值分割法、最大熵分割法和非监督分类法对影像进行目标检测,从而粗略地将影像区分为前景区域与背景区域,并结合影像的纹理特征进行分类。在纹理特征选取过程中,通过人工选取部分溢油区与非溢油区作为感兴趣区,在感兴趣区上分别统计SAR影像常用的纹理特征,并结合不同目标检测的结果以及原始影像进行基于BP神经网络的分类,得到了良好的效果。最后展望了SAR图像海洋溢油检测的发展方向。     

基于SAR后向散射的海上溢油检测研究

应用海面雷达后向散射系数检测海上溢油是目前海上溢油遥感监测的一个重要方向。本文以南海Envisat-ASAR数据为例,在分析SAR数据的基础上,应用Envisat-ASAR绝对定标计算方法,计算后向散射系数,研究应用SAR进行海上溢油遥感监测的散射特性,计算目标与海面边界后向散射系数梯度均值0σ与目标与海面后向散射系数均值差Δμ,并以两者结合作为区分海面油膜与自然现象的解译标志,从而为溢油识别提供依据。     

基于动态分块闭值去噪和改进的GDNI边缘连接的溢油遥感图像的边缘检测算法

海上溢油图像的边缘检测技术是最重要的海上溢油监测技术之一。无论是溢油的识别、位置的确定或者溢油量的获取,都需要首先确定溢油区域的边界信息。针对溢油图像的特点,提出了一种新颖的边缘检测算法。该算法由3部分组成:“非极大值抑制”实现了溢油图像的候选边缘检测;动态分块阂值算法实现了对噪声、伪边缘的清除,使获得的边缘更连续;改进的GDNI边缘连接算法实现了对去噪后图像中的中断边缘点的准确连接。通过实验结果证明,提出的算法能够得到清晰连续的溢油遥感图像的边界信息,较好地实现了具有低对比度、模糊边界以及噪声问题的溢油遥感图像的边缘检测,且具有很好的实时性。根据本算法得到的边缘检测信息,海上溢油能够更加容易和快速地被识别。     

SAR图像海洋表面油膜检测方法

海洋表面油膜对海洋环境影响极大,因此,及时获取海面油膜信息对保护海洋具有重要意义。目前各国采用的油膜检测方法主要有直接探测法和遥感方法。其中,遥感方法中的合成孔径雷达(SAR)是目前研究的热点。总结了SAR图像应用于海面油膜检测的主要特点,介绍并分析比较了SAR图像油膜检测的一般步骤及其实现方法。最后提出了SAR图像海洋表面油膜检测的发展方向。     

SAR图像海洋表面油膜检测方法

海洋表面油膜对海洋环境影响极大,因此,及时获取海面油膜信息对保护海洋具有重要意义。目前各国采用的油膜检测方法主要有直接探测法和遥感方法。其中,遥感方法中的合成孔径雷达(SAR)是目前研究的热点。总结了SAR图像应用于海面油膜检测的主要特点,介绍并分析比较了SAR图像油膜检测的一般步骤及其实现方法。最后提出了SAR图像海洋表面油膜检测的发展方向。     

石油平台井喷原油登滩后的遥感探测

海洋石油开发平台井喷溢油事件随海洋石油资源开发力度的加大越来越频繁。对溢油事件的 及时准确的跟踪监测是溢油回收和灾害损失评估的重要保证。分析了1996年年底发生在黄河口外 海域的石油平台井喷溢油事件的LANDSAT TM卫星图像,讨论了各个波段上油膜带的光谱响 应,TM图像的空间分辨率对识别滩涂和潮沟内的油膜带的分布是十分有效的。TM图像的1-4 波段油膜带的光谱特征明显,与周围地物的反差值大。同时,由于受云的覆盖影响,不能得到溢油区 的图像,是这类图像在探测溢油污染事件中的不足之处。     

基于CFAR海上溢油检测研究

在SAR图像处理的基础上,提出一种新的基于恒虚警率( CFAR-Constant False Alarm Rate) 技术,确定SAR 图像中检测溢油整体阈值的方法。该方法采用高斯分布(正态分布) 作为SAR 图像灰度的概率密度函数,由CFAR 技术直接导出用于检测海上溢油整体阈值的计算公式,进行虚警去除。该算法避免了复杂公式迭代和求解形状参数计算过程,也避免了用二分法寻找阈值的循环解算过程,提高了检测速度。使用ENVISAT图像对该算法进行检验,结果显示所提出的算法在检测精度和检测速度上都有明显的改进。     

改进残差网络结合迁移学习的SAR目标识别

合成孔径雷达(SAR)图像的目标识别对地面和海面目标获取具有重大意义。实现SAR图像目标自动解释,提高图像目标识别的准确率成为SAR图像研究的热点问题。为准确获取SAR图像中的目标信息,解决深度神经网络训练小样本SAR图像过程中细节特征丢失严重,网络易出现过拟合等问题,该研究提出一种基于RCF(ResNet101-CBAM-FPN)神经网络模型来提取SAR图像特征。将ResNet101作为主干网络模型用于特征提取,在主干网络模型中加入卷积注意力模块引导神经网络有针对性地提取SAR图像关键特征信息。然后结合特征金字塔网络,实现神经网络高层特征与底层特征融合,丰富特征信息。最后融合迁移学习思想,通过数据相对充足的仿真SAR图像对RCF网络模型进行预训练。将预训练获取的模型参数迁移至目标网络,作为目标网络的初始化参数,并使用目标网络对SAR图像进行迭代训练。实验结果表明,该方法能有效提升小样本数据SAR图像的识别精度,在MSTAR数据集上达到99.60%的识别率。     

利用SAR图像识别海面油膜的方法介绍

利用SAR图像可以有效地识别海上油膜。通过对南海及渤海地区的80多景ASAR数据进行暗区域分析,利用海面烃类油膜雷达遥感图像监测系统(System for Oil Spill Detection 1.0,简称SOSD 1.0)提取出油膜及低风速区等暗目标的特征参数,包括油膜的后向散射系数、均一度、梯度值、面积、复杂度等。通过对这些参数进行统计分析并结合人工解译,找出规律,形成根据这些规律以及其它的经验知识来区分油膜及非油膜的过程,并结合实例进行说明。     

Use of ASAR images to study the evolution of the Prestige oil spill off the Galician coast

Space‐borne synthetic aperture radar has been proven to be a useful tool for ocean oil spill monitoring due to its large coverage, independence of the day–night cycle and all‐weather capability. In this paper, a method for oil spill detection based on a visual interpretation was applied to two consecutive Advanced Synthetic Aperture Radar (ASAR) images acquired during the Prestige oil spill off the Spanish coast. The obtained oil spill information was integrated into a Geographical Information System (GIS) database in order to study the spatial distribution and the evolution of the slicks between both days, in addition to carrying out a comparison with field observations. The results show the great capability of monitoring and forecasting marine oil spills caused by large oil tanker accidents by means of the use of radar imagery jointly with other information, such as wind data or in situ observations.     

On the co‐polarized phase difference for oil spill observation

In this study dual‐polarized synthetic aperture radar (SAR) measurements were used to enhance oil spill observation. The co‐polarized phase difference (CPD) was modelled and used to characterize the scattering return from oil spills and biogenic slicks. The model predicts, under low to moderate wind conditions, a larger CPD standard deviation (σ) for oil with respect to the sea, while for biogenic slicks a σ value similar to that for the sea is obtained. Experiments accomplished with multilook complex (MLC) C‐ and L‐band SAR data show that the model predictions are confirmed and that the C‐band is, as expected, to be preferred to the L‐band.     

Discrimination between crude-oil spills and monomolecular sea slicks by airborne radar and infrared radiometer—possibilities and limitations

Abstract

The applicability of an X-band (9·4 GHz) real aperture radar (RAR) and an infrared (IR) radiometer to discriminate between crude-oil spills and monomolecular sea slicks is investigated over the same sea area. The results from quasi-simultaneous overflights over a crude-oil spill and three different sea slicks (oleyl alcohol, di-(ethylenglycol)-mono-isostearyletherand methyl oleate)show that the advantage of an imaging radar is its uniequi vocal potential for surveying large sea surfaces and that the advantage of an IR sensor is its ability to determinate quickly the thick centres of crude-oil spills. However, neither the RAR nor the IR radiometer can discriminate between crude-oil spills and sea slicks. Therefore, an airborne coastal patrol with the objective of monitoring oil pollution must comprise a package of additional sensors, e.g. a microwave radiometer and/or a lidar system.     

Coral spawn and bathymetric slicks in Synthetic Aperture Radar (SAR) data from the Timor Sea,north‐west Australia

Annular‐ to crescent‐shaped low backscatter SAR slicks over carbonate reefs and shoals in the Timor Sea that exhibit ‘feathering’, and within the coral spawning period for the region, are interpreted to be caused by a coral spawn event. This represents the first time that such an event has been interpreted through satellite remote sensing. Additionally, ocean current data and detailed swath bathymetry of the sea floor to the south‐east of the coral spawn slicks suggest that elongate repeating slicks in this area are related to current flow over submarine channels. Assessment of these slicks in association with ancillary data, such as bathymetry, current velocities, weather, and timing of SAR acquisition allow a more robust interpretation of their origins. Through differentiating coral spawn and bathymetric slicks from oil and other biological slicks in shallow carbonate systems, such as the Timor Sea, petroleum and environmental assessments for these areas can be improved.     

Automatic detection of oil spills from SAR images

A probabilistic method has been developed that distinguishes oil spills from other similar sea surface features in synthetic aperture radar (SAR) images. It considers both the radiometric and the geometric characteristics of the areas being tested. In order to minimize the operator intervention, it adopts automatic selection criteria to extract the potentially polluted areas from the images. The method has an a priori percentage of correct classification higher than 90% on the training dataset; the performance is confirmed on a different dataset of verified slicks. Some analyses have been conducted using images with different radiometric and geometric resolutions to test its suitability with SAR images different from European Remote Sensing (ERS) satellite ones. The system and its ability to detect and classify oil and non‐oil surface features are described. Starting from a set of verified oil spills detected offshore and over the coastline, the ability of SAR to reveal oil spills is tested by analysing wind intensity, deduced from the image itself, and the distance from the coast.     

A forecasting solution to the oil spill problem based on a hybrid intelligent system

Oil spills represent one of the most destructive environmental disasters. Predicting the possibility of finding oil slicks in a certain area after an oil spill can be critical in reducing environmental risks. The system presented here uses the Case-Based Reasoning (CBR) methodology to forecast the presence or absence of oil slicks in certain open sea areas after an oil spill. CBR is a computational methodology designed to generate solutions to certain problems by analysing previous solutions given to previously solved problems. The proposed CBR system includes a novel network for data classification and retrieval. This type of network, which is constructed by using an algorithm to summarize the results of an ensemble of Self-Organizing Maps, is explained and analysed in the present study. The Weighted Voting Superposition (WeVoS) algorithm mainly aims to achieve the best topographically ordered representation of a dataset in the map. This study shows how the proposed system, called WeVoS-CBR, uses information such as salinity, temperature, pressure, number and area of the slicks, obtained from various satellites to accurately predict the presence of oil slicks in the north-west of the Galician coast, using historical data.