Junmin Meng

Ship Classification in SAR Image by Joint Feature and Classifier Selection

Selecting discriminate features and constructing an appropriate classifier are two essential factors for ship classification in a synthetic aperture radar (SAR) image. Unfortunately, these two factors are rarely considered together by existing studies. We propose a joint feature and classifier selection method by integrating the classifier selection strategy into a wrapper feature selection framework. The sequential forward floating searching algorithm is improved to conduct efficient searching for an optimal triplet of feature-scaling-classifier. Comprehensive experiments on two data sets demonstrate that the proposed method can select the optimal combination of a nonredundant complementary feature subset, appropriate scaling, and classifier to improve the performance of ship classification in a SAR image.

A Polarimetric Decomposition Method for Ice in the Bohai Sea Using C-Band PolSAR Data

In recent years, there has been an increased interest in using synthetic aperture radar (SAR) to detect and monitor sea ice in the Bohai Sea for protecting offshore exploration and supporting marine transport. Two important tasks are the classification of sea ice and the determination of sea ice thickness, which can be achieved by considering the specific scattering mechanisms of the different ice types. This paper describes a three-component scattering model to decompose polarimetric SAR (PolSAR) data of sea ice. The total backscatter is modeled as the incoherent summation of surface, double-bounce, volume, and residual components. The proposed model extends the volume scattering contribution of sea ice by considering transmission, extinction, and refraction effects. The model is validated using C-band Radarsat-2 quad-polarization data acquired over sea ice in the Bohai Sea. The results show that the proposed polarimetric decomposition approach helps to distinguish different ice types and offers a proxy for sea ice thickness.

A wave energy resource assessment in the China’s seas based on multi-satellite merged radar altimeter data

Wave energy resources are abundant in both offshore and nearshore areas of the China’s seas. A reliable assessment of the wave energy resources must be performed before they can be exploited. First, for a water depth in offshore waters of China, a parameterized wave power density model that considers the effects of the water depth is introduced to improve the calculating accuracy of the wave power density. Second, wave heights and wind speeds on the surface of the China’s seas are retrieved from an AVISO multi-satellite altimeter data set for the period from 2009 to 2013. Three mean wave period inversion models are developed and used to calculate the wave energy period. Third, a practical application value for developing the wave energy is analyzed based on buoy data. Finally, the wave power density is then calculated using the wave field data. Using the distribution of wave power density, the energy level frequency, the time variability indexes, the total wave energy and the distribution of total wave energy density according to a wave state, the offshore wave energy in the China’s seas is assessed. The results show that the areas of abundant and stable wave energy are primarily located in the north-central part of the South China Sea, the Luzon Strait, southeast of Taiwan in the China’s seas; the wave power density values in these areas are approximately 14.0–18.5 kW/m. The wave energy in the China’s seas presents obvious seasonal variations and optimal seasons for a wave energy utilization are in winter and autumn. Except for very coastal waters, in other sea areas in the China’s seas, the energy is primarily from the wave state with 0.5 m ⩽ Hs ⩽ 4 m, 4 s ⩽ Te ⩽ 10 s where Hs is a significant wave height and Te is an energy period; within this wave state, the wave energy accounts for 80% above of the total wave energy. This characteristic is advantageous to designing wave energy convertors (WECs). The practical application value of the wave energy is higher which can be as an effective supplement for an energy consumption in some areas. The above results are consistent with the wave model which indicates fully that this new microwave remote sensing method altimeter is effective and feasible for the wave energy assessment.

PCA-based sea-ice image fusion of optical data by HIS transform and SAR data by wavelet transform

Sea ice as a disaster has recently attracted a great deal of attention in China. Its monitoring has become a routine task for the maritime sector. Remote sensing, which depends mainly on SAR and optical sensors, has become the primary means for sea-ice research. Optical images contain abundant sea-ice multi-spectral information, whereas SAR images contain rich sea-ice texture information. If the characteristic advantages of SAR and optical images could be combined for sea-ice study, the ability of sea-ice monitoring would be improved. In this study, in accordance with the characteristics of sea-ice SAR and optical images, the transformation and fusion methods for these images were chosen. Also, a fusion method of optical and SAR images was proposed in order to improve sea-ice identification. Texture information can play an important role in sea-ice classification. Haar wavelet transformation was found to be suitable for the sea-ice SAR images, and the texture information of the sea-ice SAR image from Advanced Synthetic Aperture Radar (ASAR) loaded on ENVISAT was documented. The results of our studies showed that, the optical images in the hue-intensity-saturation (HIS) space could reflect the spectral characteristics of the sea-ice types more efficiently than in the red-green-blue (RGB) space, and the optical image from the China-Brazil Earth Resources Satellite (CBERS-02B) was transferred from the RGB space to the HIS space. The principal component analysis (PCA) method could potentially contain the maximum information of the sea-ice images by fusing the HIS and texture images. The fusion image was obtained by a PCA method, which included the advantages of both the sea-ice SAR image and the optical image. To validate the fusion method, three methods were used to evaluate the fused image, i.e., objective, subjective, and comprehensive evaluations. It was concluded that the fusion method proposed could improve the ability of image interpretation and sea-ice identification.

Assessment of C-band compact polarimetry SAR for sea ice classification

The C-band synthetic aperture radar (SAR) data from the Bohai Sea of China, the Labrador Sea in the Arctic and the Weddell Sea in the Antarctic are used to analyze and discuss the sea ice full polarimetric information reconstruction ability under compact polarimetric modes. The type of compact polarimetric mode which has the highest reconstructed accuracy is analyzed, along with the performance impact of the reconstructed pseudo quad-pol SAR data on the sea ice detection and sea ice classification. According to the assessment and analysis, it is recommended to adopt the CTLR mode for reconstructing the polarimetric parameters σHH0, σVV0, H and α, while for reconstructing the polarimetric parameters σHV0, ρH-V, λ1 and λ2, it is recommended to use the π/4 mode. Moreover, it is recommended to use the π/4 mode in studying the action effects between the electromagnetic waves and sea ice, but it is recommended to use the CTLR mode for studying the sea ice classification.

Analysis of multi-dimensional SAR for determining the thickness of thin sea ice in the Bohai Sea

Flat thin ice (<30 cm thick) is a common ice type in the Bohai Sea, China. Ice thickness detection is important to offshore exploration and marine transport in winter. Synthetic aperture radar (SAR) can be used to acquire sea ice data in all weather conditions, and it is a useful tool for monitoring sea ice conditions. In this paper, we combine a multi-layered sea ice electromagnetic (EM) scattering model with a sea ice thermodynamic model to assess the determination of the thickness of flat thin ice in the Bohai Sea using SAR at different frequencies, polarization, and incidence angles. Our modeling studies suggest that co-polarization backscattering coefficients and the co-polarized ratio can be used to retrieve the thickness of flat thin ice from C- and X-band SAR, while the co-polarized correlation coefficient can be used to retrieve flat thin ice thickness from L-, C-, and X-band SAR. Importantly, small or moderate incidence angles should be chosen to avoid the effect of speckle noise.

Exploitable wave energy assessment based on ERA-Interim reanalysis data--A case study in the East China Sea and the South China Sea

Wave energy resources assessment is a very important process before the exploitation and utilization of the wave energy. At present, the existing wave energy assessment is focused on theoretical wave energy conditions for interesting areas. While the evaluation for exploitable wave energy conditions is scarcely ever performed. Generally speaking, the wave energy are non-exploitable under a high sea state and a lower sea state which must be ignored when assessing wave energy. Aiming at this situation, a case study of the East China Sea and the South China Sea is performed. First, a division basis between the theoretical wave energy and the exploitable wave energy is studied. Next, based on recent 20 a ERA-Interim wave field data, some indexes including the spatial and temporal distribution of wave power density, a wave energy exploitable ratio, a wave energy level, a wave energy stability, a total wave energy density, the seasonal variation of the total wave energy and a high sea condition frequency are calculated. And then the theoretical wave energy and the exploitable wave energy are compared each other; the distributions of the exploitable wave energy are assessed and a regional division for exploitable wave energy resources is carried out; the influence of the high sea state is evaluated. The results show that considering collapsing force of the high sea state and the utilization efficiency for wave energy, it is determined that the energy by wave with a significant wave height being not less 1 m or not greater than 4 m is the exploitable wave energy. Compared with the theoretical wave energy, the average wave power density, energy level, total wave energy density and total wave energy of the exploitable wave energy decrease obviously and the stability enhances somewhat. Pronounced differences between the theoretical wave energy and the exploitable wave energy are present. In the East China Sea and the South China Sea, the areas of an abundant and stable exploitable wave energy are primarily located in the north-central part of the South China Sea, the Luzon Strait, east of Taiwan, China and north of Ryukyu Islands; annual average exploitable wave power density values in these areas are approximately 10–15 kW/m; the exploitable coefficient of variation (COV) and seasonal variation (SV) values in these areas are less than 1.2 and 1, respectively. Some coastal areas of the Beibu Gulf, the Changjiang Estuary, the Hangzhou Bay and the Zhujiang Estuary are the poor areas of the wave energy. The areas of the high wave energy exploitable ratio is primarily in nearshore waters. The influence of the high sea state for the wave energy in nearshore waters is less than that in offshore waters. In the areas of the abundant wave energy, the influence of the high sea state for the wave energy is prominent and the utilization of wave energy is relatively difficult. The developed evaluation method may give some references for an exploitable wave energy assessment and is valuable for practical applications.

The Application of Two-Dimensional EMD to Extracting Internal Waves in SAR Images

SAR (synthetic aperture radar) is imaged by resonant interaction between radar wave and micro scale sea-surface waves. All ocean processes that affect the distribution of micro scale wave spectrum can be found in SAR images, such as ocean wave, internal waves, mesoscale eddies, fronts, etc. Thus a SAR image of sea surface often mingles with different scale ocean processes. Internal waves are often manifested in SAR images with other signals simultaneously, such as ocean wave. In this paper, 2D-EMD (two-dimensional empirical mode decomposition) algorithm is used to extract internal wave from SAR image. This algorithm produces a fully two dimensional decomposition of a SAR image into a series of IMF (intrinsic mode functions) and residual images with the same size as the original image. By combining IMF images, internal waves and ocean waves are separated. Comparing with the wavelet analysis, one can find that the 2D-EMD is more effective. The results preliminarily show that 2D-EMD provides a significant way to extract internal wave from an aliasing SAR image.

Sea Ice Classification Using Cryosat-2 Altimeter Data by Optimal Classifier–Feature Assembly

Sea ice type is one of the most sensitive variables in Arctic ice monitoring and detailed information about it is essential for ice situation evaluation, vessel navigation, and climate prediction. Many machine-learning methods including deep learning can be employed for ice-type detection, and most classifiers tend to prefer different feature combinations. In order to find the optimal classifier–feature assembly (OCF) for sea ice classification, it is necessary to assess their performance differences. The objective of this letter is to make a recommendation for the OCF for sea ice classification using Cryosat-2 (CS-2) data. Six classifiers including convolutional neural network (CNN), Bayesian,

Estimating significant wave height from SAR imagery based on an SVM regression model

K