Oil spill detection plays an important role in marine environment protection. Quad-polarimetric Synthetic Aperture Radar (SAR) has been proved to have great potential for this task, and different SAR polarimetric features have the advantages to recognize oil spill areas from other look-alikes. In this paper we proposed an oil spill detection method based on convolutional neural network (CNN) and Simple Linear Iterative Clustering (SLIC) superpixel. Experiments were conducted on three Single Look Complex (SLC) quad-polarimetric SAR images obtained by Radarsat-2 and Spaceborne Imaging Radar-C/X-Band Synthetic Aperture Radar (SIR-C/X-SAR). Several groups of polarized parameters, including H/A/Alpha decomposition, Single-Bounce Eigenvalue Relative Difference (SERD), correlation coefficients, conformity coefficients, Freeman 3-component decomposition, Yamaguchi 4-component decomposition were extracted as feature sets. Among all considered polarimetric features, Yamaguchi parameters achieved the highest performance with total Mean Intersection over Union (MIoU) of 90.5%. It is proved that the SLIC superpixel method significantly improved the oil spill classification accuracy on all the polarimetric feature sets. The classification accuracy of all kinds of targets types were improved, and the largest increase on mean MIoU of all features sets was on emulsions by 21.9%.

As synthetic aperture radar (SAR) is playing an increasingly important role in Earth observations, many new methods and technologies have been proposed for change detection using multi-temporal SAR images. Especially with the development of deep learning, numerous methods have been proposed in recent years. However, the requirement to have a certain number of high-quality samples has become one of the main reasons for the limited development of these methods. Thus, in this paper, we propose an unsupervised SAR change detection method that is based on stochastic subspace ensemble learning. The proposed method consists of two stages: The first stage involves the automatic determination of high-confidence samples, which includes a fusion strategy and a refinement process; and the second stage entails using the stochastic subspace ensemble learning module, which contains three steps: obtaining the subsample sets, establishing and training a two-channel network, and applying the prediction results and an ensemble strategy. The subsample sets are used to solve the problem of imbalanced samples. The two-channel networks are used to extract high-dimensional features and learn the relationship between the neighborhood of the pixels in the original images and the labels. Finally, by using an ensemble strategy, the results predicted by all patches reclassified in each network are integrated as the detection result. The experimental results of different SAR datasets prove the effectiveness and the feasibility of the proposed method.

Synthetic Aperture Radar (SAR) ship detection is an important maritime application. However, azimuth ambiguities caused by the finite sampling of the Doppler spectrum are often visible in SAR images and are always mistaken as ships by classic detection techniques, like the Constant False Alarm Rate (CFAR). It is known that radar targets and azimuth ambiguities have different characteristics in polarimetric SAR (PolSAR) data, i.e., first ambiguities usually have strong odd- or double-bounce scattering and the maximum amplitude of the first ambiguity in S_HV is always considerably smaller than that of the corresponding target for zero or high velocity. On the basis of this characteristics, this paper finds that first ambiguities usually have low volume scattering power relative to ships and almost have no helix scattering by Yamaguchi decomposition. But some residual ambiguities still exit in the volume scattering power and have similar scattering intensity to small ships, and some parts of a ship also have zero helix scattering owing to some physical factors (e.g., ship structure, radar incidence angle, etc.). Thus, for high-precision ship detection, a new ship detection method based on cross-correlation between the volume and helix scattering mechanisms derived from Yamaguchi decomposition is proposed to avoid false alarms caused by azimuth ambiguities and enhance Target-to-Clutter Ratio (TCR) for improving the miss detection rate of small ships. By experiments, it is proved that our method can work effectively and has high detection accuracy.

The existing fire scar detection methods based on multi-temporal analysis only used the difference in either backscattering intensity or polarimetric characteristics between the pre- and post-fire PolSAR data to calculate the difference image (DI), and then applied an object-based image analysis approach (OBIA) to generate the fire scar binary map. These methods all ignored the polarimetric correlation between both the pre- and post-fire PolSAR data. And many parameters of the OBIA method were determined empirically. Therefore, this study proposes a new detection method, which integrates the Hotelling–Lawley trace (HLT) statistic with a hierarchical automatic image segmentation method (GGKI-MRF). The HLT can simultaneously capture changes in both polarimetry and intensity, which helps to distinguish between burned and unburned areas. And the GGKI-MRF method is developed by combining the generalized Gaussian-based Kittler–Illingworth (GG-KI) thresholding with Markov Random Field (MRF) model, which has a good performance in reducing the isolate points (false alarms) and the omission errors. The experimental results from multi-temporal and polarimetric PALSAR PolSAR data show that the proposed method can achieve high detection accuracy (i.e., the kappa coefficient of 0.81 and the overall accuracy up to 0.92).

The deep learning-based change detection (CD) methods have achieved remarkable progress with remote sensing imagery. These methods mainly rely on complex feature extraction structures and numerous attention mechanisms to realize effective feature extraction and recognition. However, this results in a significant increase in the number of parameters and the training cost of the whole network. The increase in parameterization can also lead to the degradation of network performance when the amount of training data is insufficient. Thus, it is still promising and challenging to perform reliable change detection results through light network design. In this paper, we propose a lightweight full-scale hybrid network (LFHNet). The network is comprised of convolutional neural network (CNN), multilayer perceptron (MLP), and transformer, and it is capable of achieving high performance in CD tasks with a lightweight structure. Firstly, the MLP structures are integrated into the basic network to extract global feature information, compensating for the information loss caused by the convolutional operations of CNN. Secondly, a full-scale difference module is designed to sufficiently extract the feature information and ensure enough feedforward information. Thirdly, a lightweight transformer is appended at the end of the network to accomplish the spatial-temporal correlation of features, which effectively enhances the quality of the final extracted features. Experimental results on three classical CD datasets show that the proposed method outperforms the state-of-the-art (SOTA) methods.