Search

The outbreaks of green tide have caused severe harm to the marine environment and human society. Synthetic Aperture Radar (SAR) plays an important role in green tide monitoring by virtue of its high resolution and cloud-free nature. The existing green tide extraction methods still face challenges in identifying multi-scale green tide patches due to noise interference, uneven greyscale and blurred boundaries in SAR images. Meanwhile, the practical application of deep learning methods with high precision is limited due to the complexity of the model and the large amount of computation. Therefore, we propose a multi-scale context-aware and batch-independent lightweight green tide extraction network called MBL-Net. A novel lightweight heterogeneous backbone is designed to extract multi-scale discriminative features and improve segmentation efficiency by using multi-scale selection kernel (MSK) modules and lightweight stages. Meanwhile, Triplet attention module is introduced to improve the internal consistency of the green tide region and suppress the effect of speckle noise. Then, the mixed pooling-based channel prior module (MCPM) is used to expand the receptive field of the network and extract the fine green tide structure by fusing multi-scale features. In addition, Filter Response Normalisation (FRN) is innovatively applied for feature normalization in the decoding stage, eliminating batch dependency. In order to verify the effectiveness of the proposed method, a dataset is built using the Sentinel-1 images of the Yellow Sea, China, from 2019 to 2021. The experimental results show that the proposed method achieves an overall accuracy of 98.59% with 0.970 G FLOPs and 3.525 M parameters, which ensures high precision and improves green tide detection efficiency. Compared with several representative networks, this method can capture more details of green tide with fewer parameters and faster calculation speed. [ABSTRACT FROM AUTHOR]

Collaborative representation-based (CR) methods have received widespread attention in hyperspectral anomaly detection, but the results are greatly affected by the quality of the background dictionary. Abnormal pixels and abnormal-mixed pixels in the background dictionary may affect the accuracy of linear representation and make its performance poor. To address the above problem, an adaptive background dictionary construction-based anomaly detection method is proposed. To ensure the purity of the background dictionary, abnormal pixels and abnormal-mixed pixels around each test pixel are removed adaptively through clustering and pure pixel extraction. Furthermore, the saliency weight of the test pixel is calculated through the pixels in the inner window and weighted into the linear representation process to improve the robustness of the method. Experimental results on four hyperspectral datasets show that the proposed method performs better than other CR methods and traditional detectors, and it can reduce the dependence of anomaly detection performance on dual window size. [ABSTRACT FROM AUTHOR]

Seagrass beds play a vital ecological role by regulating climate, maintaining biodiversity, and sequestering carbon. Achieving accurate classification of seagrass beds across both time and space is of significant importance for efficient monitoring. This paper addresses the challenges of seagrass bed classification in remote sensing imagery and the difficulty of achieving temporal and spatial transferability of classification model. Leveraging a long-term Landsat satellite image time series spanning from 1976 to 2022 in the Yellow River Delta, we enhance the DeepLab V3+ network and propose a cross-temporal-spatial domain seagrass bed transfer learning classification approach. We utilize selectively chosen images from a few years in partial regions for training, introduce freeze-training and-unfreeze-training during the model training phase, and then transfer the model to achieve cross-temporal and cross-temporal-spatial domain classification on images from other years and regions. Additionally, we discuss the factors influencing the classification results. The research results indicate that: (1)The method we proposed has shown good results, achieving classification accuracy of 83.17% and 80.99% for seagrass beds in both cross-temporal and cross-temporal-spatial domains. (2) The classification results indicate that this method achieves an average classification accuracy higher by 16.18% compared to networks such as UNet, PSPNet, HRNet, UNet++, SegFormer, etc. under cross-temporal conditions and higher by 17.56% under cross-spatiotemporal conditions for seagrass bed classification. (3) Based on the classification results, it is observed that from 1973 to 1986, the overall area of seagrass beds in the Yellow River Delta had an initial growth trend, with the largest seagrass bed area recorded in 1986, reaching 4281.289 hectares. Subsequently, the seagrass beds showed an overall decreasing trend, and by 2019 they had almost completely disappeared. The cross-temporal-spatial domain seagrass bed transfer learning classification method proposed in this paper can provide valuable support for the monitoring, restoration, management, and utilization of seagrass ecosystems. [ABSTRACT FROM AUTHOR]

Timely and accurate acquisition of winter wheat planting areas is crucial for food security. In this study, Sentinel-1 and Sentinel-2 time-series data are integrated at the feature level to enhance the accuracy of winter wheat extraction. However, existing feature-level fusion models suffer from insufficient feature extraction and lack of feature completeness, thereby overlooking the complementarity and correlation between these two modalities. A Multimodal Fusion Convolutional Neural Network (MMF-CNN) model is proposed to address the issues above. Firstly, the images of Sentinel-1 and Sentinel-2 are processed to obtain the NDVI and backscatter characteristics of the winter wheat time series life cycle. A single feature and a combination of two features are then imported into each end of the model. The model adds a feature fusion module, which can fully extract the feature information. At the same time, the original features are retained in the process of multiscale feature fusion, which avoids the loss of the original information. Finally, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Visual Geometry Group (VGG) are selected as the comparison models for comparative experiments, and the classification results of remote sensing images are obtained. These results demonstrate that the joint utilization of SAR and optical data yields the highest classification accuracy, with an F1 score of 97.42% for winter wheat. The overall accuracy (OA) of the proposed MMF-CNN method in this study is 96.87%, representing a 1.86% improvement compared to the Conv1D-CNN model. This improvement signifies adaptive feature learning at different hierarchical levels. Comparing the accuracy with other mainstream methods, the OA improves by 1.75%–4.37%, reveals finer ground details, and demonstrates faster performance. This study can provide methodological references for crop extraction studies based on multi-source data and time series analysis. [ABSTRACT FROM AUTHOR]

In the hyperspectral image (HSI) classification tasks, various deep learning models have achieved remarkable success. However, most deep learning models are compute-intensive, requiring significant computing power, time, and other resources. It becomes a challenge to pursue better results while saving computational resources. Therefore, a novel dual-input ultralight multi-head self-attention learning network (DUMS-LN) is proposed for HSI classification. The proposed DUMS-LN consists of three main core modules, namely the high-dimensional reduced module (HDRM), lightweight multi-head self-attention (LMHSA) module, and linearized hierarchical conversion module (LHCM). HDRM is used as a pre-processing module with efficient data compression and combines spatial and spectral information extraction from the raw data to provide cleaner and more comprehensive feature data for subsequent processing. In addition, the core computational module of DUMS-LN is the LMHSA module, which is lightweight but possesses better data processing capability than the traditional multi-head self-attention module. Finally, the LHCM divides the model into two phases, reducing the dimensionality of the feature data phase by phase so that the LMHSA module can perform feature extraction at different levels. Experiments on four benchmark HSI datasets show that the proposed DUMS-LN outperforms the comparison HSI classification algorithms regarding speed and classification accuracy. [ABSTRACT FROM AUTHOR]

Monitoring marine oil pollution holds both practical and scientific significance. Synthetic Aperture Radar (SAR) is an active microwave remote sensing technique capable of all-weather and all-day with fine spatial resolution. However, under low wind conditions, rain cells and young ice are examples of look-alikes affect the accuracy of oil spill detection. Polarimetric SAR assumes a crucial role in this context, as it can extract abundant polarimetric features by polarimetric target decomposition. Drawing inspiration from this advancement, an improved polarimetric feature named relative feature based on Cloude-Pottier target decomposition was proposed. The Jeffries-Matusita distance indicates the substantial potential of the relative feature in detecting oil spills. The improved polarimetric feature within U-Net, FCN-8s, and DeepLabv3+ResNet-18 for oil spill detection using polarization SAR images. Experiment results demonstrated that the relative feature has superior performance compared to other polarimetric features and obtained the highest accuracy and dice within U-Net compared to the other two models. These findings introduce promising concepts for achieving rapid and precise detection of oil spills in future applications. [ABSTRACT FROM AUTHOR]

Arctic sea ice change is one of the critical factors affecting the global climate environment; hence, it is crucial to obtain sea ice thickness with high accuracy while studying polar and global climate change. In the process of using altimetry data to estimate sea ice thickness, the mean sea surface height will bring greater uncertainty to the extraction of sea ice freeboard, which will affect the accuracy of sea ice thickness. Also, the influence of snow cover on radar signal penetration will bring greater uncertainty to sea ice thickness. In this paper, we present a processing chain for sea ice thickness estimation. First, we compare the effect of four different MSS models on the freeboard estimation. Then, considering the incomplete penetration of radar signals and the different speeds of radar signals penetrating the snow layer and the vacuum, the traditional sea ice thickness model is optimized to obtain the sea ice thickness. Compared with the Operation IceBridge (OIB) sea ice thickness, the accuracy of sea ice thickness obtained by the optimized model is better than 0.350 m, with a root mean square error of 0.260 m and a mean bias of 0.048 m. The comparison results show that the combination of the latest DTU18 MSS model and sea ice thickness optimization model effectively improve the accuracy of sea ice thickness. [ABSTRACT FROM AUTHOR]

As ship target detection technology has high application value in military and civil fields, it is significant to research ship detection in SAR images. Aiming at the complex and diverse backgrounds, significant differences in ship sizes, and real-time detection problems in the ship target detection task of SAR remote sensing images, a lightweight ship detection network based on the YOLOx-Tiny model is proposed. Firstly, a multi-scale ship feature extraction module is proposed, composed of a parallel multi-branch structure connected by a standard convolution layer, asymmetric convolution layer, and dilatation convolution layer with different expansion rates in turn. It makes better use of local features and global features and effectively improves the detection accuracy of multi-scale ship targets; Secondly, to ensure detection performance and eliminate background interference, we propose a whole SAR remote sensing image detection strategy based on an adaptive threshold, which effectively suppresses false alarms caused by background and improves detection speed. The experimental results on two different SAR ship datasets, SSDD and HRSID, show that, compared with several advanced methods, the effectiveness and superiority of the method in this paper are verified, and excellent results are shown in the detection of the whole SAR remote-sensing image. It can provide effective theoretical and technical support for ship detection on platforms with limited computing resources and has good application prospects. [ABSTRACT FROM AUTHOR]

The combination of multi-source Geostationary Earth Orbit (GEO) satellites can realize simultaneous global observation with high frequency, which is significant to fine weather forecast and global climate change research. Here the radiance consistency and deviation characterization in the overlapping regions are analysed for three new generation GEO satellites, including the Advanced Himawari Imager (AHI) onboard the Himawari-8 satellite, the Advanced Baseline Imager (ABI) onboard the Geostationary Operational Environmental Satellite-17 (GOES-17) and the Advanced Geostationary Radiation Imager (AGRI) onboard FengYun satellite-4A (FY-4A). The result shows that the radiance has higher consistency for visible and near-infrared (VNIR) channels with correlation coefficient r > 0.98 than infrared (IR) channels with r > 0.90 in the overlapping regions of different GEO satellites. For FY-4A & Himawari-8, the average percentage deviation (APD) of VNIR channels is 5.54%–9.03%. The brightness temperature (BT) bias of IR channels is 1.16 K-2.50 K. For GOES-17 & Himawari-8, the APD of VNIR channels is 4.48%–6.71%, and the BT bias of IR channels is 0.96 K −2.76 K. Solar-viewing geometries significantly influence the radiance deviation in the over regions. The future work is to design a radiance fusion method and achieve cloud detection in ample space with high frequency by combining multi-source GEO satellites. [ABSTRACT FROM AUTHOR]

The geostationary satellite Himawari-8 has become the primary source for fire remote-sensing detection because of its advantages of high frequency, large width and easy access. To solve the problem of difficulty in small fire detection and with a high omission on Himawari-8 image, a spatio-temporal fire detection (STFD) method based on Himawari-8 image brightness temperature change is proposed. Calculate the mean value difference of brightness temperature between multi-time series images before the target time, and use the least square model to fit the ideal mean value difference of brightness temperature between the target time and the image at the previous time. Then, the difference value of the actual brightness temperature between the target time and the last image time is calculated. The initial brightness temperature change pixels are obtained by the comparative analysis method. Based on the spatial statistical characteristics, the potential fire point is determined by the brightness temperature value ratio of the image, temperature mean and standard temperature deviation. Then, combined with the spatio-temporal context information, the persistent fire points are detected according to the threshold conditions to supplement undetected persistent fires. The results of experiments on the Himawari-8 images in Guizhou, China and southwestern Australia indicate that STFD exhibits superior performance on small fire detection points, and the accuracy is better than the several traditional methods. [ABSTRACT FROM AUTHOR]

Mixed pixels are the main reason for the low accuracy of traditional remote sensing applications. Hyperspectral image unmixing can explore the sub-pixel information of mixed pixels, which is an effective measure to solve the problems of low precision. Current unmixing methods only consider the correlation of local or global pixels and do not fully utilize images information. Based on the above problems, we proposed a novel sparse unmixing model named combining low-rank constrain for similar superpixels and total variation sparse unmixing (CLRSS-TV) in this current research paper. The adjacent similar pixels are clustered first into superpixels, then the superpixels with the same semantic information are merged into a collection. The spatial information of the image is fully considered by twice clustering. Weighted low-rank constraint is imposed on each collection to consider the spectral correlation of pixels. Moreover, the TV regularization and l2,1 norm are utilized to improve the smoothness and row sparsity, respectively. Experimental results reveal that the proposed method is not only competitive with the four state-of-the-art algorithms in simulated and actual datasets, but also has good anti-noise ability and universality. However, this paper still fails to overcome the problem of parameters selection in sparse unmixing, so the future work study intends to adopt the intelligent optimization algorithm to obtain the optimal parameters. [ABSTRACT FROM AUTHOR]