This letter addresses the feature detection design for the target embedded in sea clutter. Three polarization features (the relative surface scattering power, the relative volume scattering power, and the relative dihedral scattering power) are obtained based on the observed multipolarization channel returns. Then, 3-D feature detector is constructed to detect the sea-surface small floating target based on the three polarization features. The experiments based on the measured radar data show that the proposed method attains better detection performance and better robustness than do several existed feature-class detectors.

In this paper, a multi-feature detector based on isolation forest (iForest) algorithm is developed to detect floating small targets in sea clutter. The conventional multi-feature detector can only process three features or less. The proposed detector aims to break the limitation of feature dimensions' number of the existed feature-based detectors and to improve the detection performance. It transforms the detection of floating small target into an anomaly detection problem in a high-dimensional feature space, breaking the limitation of the number of features. Firstly, a modified isolation forest is constructed from multiple features extracted from sea clutter. Meanwhile, the relative Doppler coefficient of variation (RCV) is proposed and added into the feature library. Then, taking the average path length as detection statistic, the detection threshold is obtained by Monte-Carlo technique at the given false alarm probability (PFA). Finally, the final decision is made by comparing the path length calculated from the cell under test (CUT) of radar returns with the detection threshold. Detection performances are evaluated based on twenty measured IPIX radar data sets. The experiment results show that the multi-feature detector based on isolation forest can obtain a significant performance improvement and has lower computation cost compared with the existed detectors.

A forest fire susceptibility map generated with the fire susceptibility model is the basis of fire prevention resource allocation. A more reliable susceptibility map helps improve the effectiveness of resource allocation. Thus, further improving the prediction accuracy is always the goal of fire susceptibility modeling. This paper developed a forest fire susceptibility model based on an ensemble learning method, namely light gradient boosting machine (LightGBM), to produce an accurate fire susceptibility map. In the modeling, a subtropical national forest park in the Jiangsu province of China was used as the case study area. We collected and selected eight variables from the fire occurrence driving factors for modeling based on correlation analysis. These variables are from topographic factors, climatic factors, human activity factors, and vegetation factors. For comparative analysis, another two popular modeling methods, namely logistic regression (LR) and random forest (RF) were also applied to construct the fire susceptibility models. The results show that temperature was the main driving factor of fire in the area. In the produced fire susceptibility map, the extremely high and high susceptibility areas that were classified by LR, RF, and LightGBM were 5.82%, 18.61%, and 19%, respectively. The F1-score of the LightGBM model is higher than the LR and RF models. The accuracy of the model of LightGBM, RF, and LR is 88.8%, 84.8%, and 82.6%, respectively. The area under the curve (AUC) of them is 0.935, 0.918, and 0.868, respectively. The introduced ensemble learning method shows better ability on performance evaluation metrics.

The conventional methods for target detection and discrimination in high-resolution synthetic aperture radar (SAR) images usually have low accuracy and slow speed, especially for large complex scenes. To overcome these drawbacks, in this paper, we propose a target detection and discrimination method based on visual attention model. In the detection stage, to pop out the targets and suppress the background clutter in the saliency map, we select the task-dependent scales from the Gaussian pyramid of the original SAR image. Moreover, we adopt the clustering algorithm to remerge several isolated focus of attention areas, which are obtained from the saliency map, into a complete target region. The candidate target SAR image chips are extracted with relative high accuracy and low time cost in this stage. Since there may be single target, multiple targets, or partial targets with complex clutter in each SAR image chip, it is hard to acquire accurate target-shaped blob via segmentation. Some classical discrimination features which are extracted based on target segmentation may lose effectiveness. In the discrimination stage of our method, to solve the above problem, based on the saliency and gist (SG) features for optical satellite images, we propose the modified SG (MSG) features for SAR target discrimination. The MSG features are complementary to each other and can provide a more complete description of the extracted SAR image chips without segmentation, which also reduces the computation burden. The experimental results on the synthetic images and miniSAR real SAR image data set demonstrate that the proposed target detection and discrimination method can detect and discriminate the targets from the complex background clutter with high accuracy and fast speed in high-resolution SAR images.

In this article, we propose optimum and near-optimum adaptive coherent detectors of radar targets in compound-Gaussian clutter with generalized inverse Gaussian texture (CG-GIG clutter). The target amplitude and the speckle covariance matrix are modeled as unknown quantities to be estimated. On the basis of the two-step generalized likelihood ratio test (GLRT) and the estimate of the speckle covariance matrix, the optimum coherent detector and its adaptive version are designed in this article. It is demonstrated that the proposed optimum coherent detector contains three common detectors, which are the optimum K detector, the generalized likelihood ratio test linear-threshold detector (GLRT-LTD), and the GLRT detector for compound-Gaussian clutter with inverse Gaussian texture. Due to the existence of the modified Bessel function depending on data, the optimum coherent detector is computationally unrealizable. Therefore, a near-optimum coherent detector with a new structure named $\alpha$ matched filter ($\alpha$-MF) detector and its adaptive version are proposed, which decreases the computational cost. The proposed near-optimum coherent detector contains two common detectors, the GLRT-LTD and the $\alpha$-MF detector in K-distributed clutter, and has a comparable detection performance of the near-optimum detector in compound-Gaussian clutter with inverse Gaussian texture, which was proposed before. Theoretical analysis and numerical experiments illustrate that the proposed two detectors for CG-GIG clutter have the constant false alarm ratio property relative to the estimate of the speckle covariance matrix and the Doppler steering vector. Moreover, the detection performance of the two coherent detectors are evaluated by the simulated and real data.

In this letter, we focus on the statistical modeling of sea clutter amplitudes. Due to its non-Gaussian nature, the existing statistical models are sometimes difficult to represent well the heavy-tailed portion of amplitude distribution. To address this problem, we propose a compound Gaussian (CG) model with a generalized inverse Gaussian (GIG) texture to describe sea clutter amplitudes. In this regard, the probability density function and the cumulative distribution function of the clutter amplitudes for the proposed model are derived. Moreover, we provide an approach to estimate the unknown parameters of the proposed CG-GIG distribution. The experimental results indicate that the CG-GIG distribution is more suitable to describe the amplitudes of non-Gaussian sea clutter than its competitors.