Dune images typically display intricate details and relatively uniform spectral characteristics, making them a unique challenge for image segmentation tasks. Due to the limitations of traditional convolution operations, the CNN-based methods struggle to capture long-range dependencies. The Transformer-based methods have good performance in long-term dependency relationships, but it lacks modeling of local context. Based on the strengths of both approaches and the concept of a dual-branch architecture, in order to better achieve segmentation of sand dune images in desert areas, a dual-branch network combining Convolutional Neural Network(CNN) and Transformer (CTCNet) is proposed, and comparative experiments are conducted on a self-made Chinese desert sand dune morphology dataset and the Registan-Kharan desert sand dune morphology dataset. The CNN branch aims to capture local information and enhance feature extraction capabilities using Convolutional Attention Block. The Transformer branch captures global information and employs an enhanced transformer block to improve the capture of remote dependencies and create more discriminative features. Afterwards, the dual branch features are merged through a Feature Fusion Module to enhance the capture of finer details. Driven by its dual-branch structure and other design features, CTCNet has demonstrated exceptional capability in capturing dependencies and contextual information for sand dune image segmentation tasks. The experimental results demonstrate that CTCNet achieves an accuracy of 89.66% and a mean Intersection over Union(MIoU) of 82.29% on the Chinese desert sand dune morphology dataset. On the Registan-Kharan desert dune morphology dataset, it achieves an accuracy of 91.24% and a MIoU of 81.21%. Outperforming other models of similar complexity and size, achieving state-of-the-art results, and demonstrating the effectiveness and robustness of CTCNet.

With the continuous development of technologies such as the Internet of Things (IoT), scheduling issues in edge-cloud systems are becoming a research focus. Deep reinforcement learning (DRL) has become an effective way to address scheduling issues in edge-cloud systems due to its ability to interact with the environment and engage in adaptive learning to solve complex decision-making problems. However, due to the increasing scale of edge-cloud systems, traditional DRL still faces challenges in scheduling, such as slow convergence and high computational requirements. To address these challenges, we propose a diffusion model-based deep reinforcement learning algorithm called DMaiS, which utilizes the diffusion model as the policy network in the advantage actor-critic (A2C) to expedite policy learning. Additionally, we develop a distributed service orchestration approach utilizing multi-agent advantage actor-critic (MAA2C) to effectively and flexibly manage extensive and intricate cloud service resources. The experimental results using real-world data demonstrate that compared to the baseline algorithms, DMaiS achieves a higher system throughput rate and a lower scheduling latency when managing scheduling for the edge-cloud system. It also exhibits a faster convergence speed compared to traditional DRL algorithms.

Hyperspectral images (HSIs) contain a wealth of information and have important applications in the fields of military, agriculture, medicine and et al. The excellent local feature representation ability of convolutional neural network (CNN) makes it achieve good classification results in hyperspectral image classification tasks, but its ability to capture global features is limited and the computational cost is high. The Transformer’s ability to represent global features can largely make up for the above shortcomings of CNNs. Therefore, in this paper, we propose a hybrid network based on CNN and transformer (CTHN) for HSI classification. Firstly, the multi-scale spectral and spatial features were preliminarily extracted through the multi-scale spectral-spatial feature extraction module. Then, the deformable convolutional residual module is introduced to enhance the adaptability of the network to various complex shapes of ground objects, and further learn complex spatial information. Finally, the transformer module is used to deeply represent and learn global features. A series of experimental results on three publicly available datasets show that the classification performance of CTHN outperforms several state-of-the-art comparison algorithms.

Desertification is a serious land degradation process that poses various hazards to economic development and environmental security. Satellite remote sensing images have the characteristics of wide coverage and high resolution. Therefore, using deep neural networks and remote sensing image technology to extract desert boundaries is of great significance for scientific research and sustainable development. Inspired by this, a hybrid network is proposed based on adaptive semantic connections, which enables the model to better capture global context information and texture information while reducing the semantic gap between the encoder and the decoder. Secondly, to address computational complexity and improve model generalization capabilities, a dynamic feature scaling multi-Head self-Attention is introduced. Additionally, convolutional block attention modules with residuals are incorporated into the decoder to facilitate the model in learning relevant features. Finally, a differentiable boundary metric is used as the loss function leads to better performance and more accurate boundary segmentation. We conduct experiments on the Landsat 8 dataset. Through visual interpretation of the experimental results and calculation of evaluation indicators, it can be seen that our model has good results for desert boundary extraction.

Aerosol optical depth is a crucial parameter that characterizes the impact of aerosols on light attenuation. This parameter serves as the fundamental prerequisite for quantitative remote sensing studies and holds significant importance in climate change research, atmospheric pollution monitoring, and environmental governance. In this article, four machine learning models, namely, LSTM, RF, XGBoost, and LightGBM, were used to achieve aerosol optical depth retrieval using MODIS data as input features. Spatiotemporal cross-validation was used for model training and evaluation, and the results showed that the LSTM model had the best performance among the four models. In independent sites validation, both the LSTM and LightGBM models exhibited superior performance compared to the MODIS Deep Blue algorithm, indicating that the machine learning methods will contribute to enhancing the capability of satellite remote sensing for aerosol optical depth retrieval.

Synthetic aperture radar (SAR) has the advantage of all-weather observation, but its imaging principle based on the backscattering of electromagnetic waves makes its information less interpretable. One feasible approach is to convert SAR images into optical images, which not only improves the interpretability of SAR images but also fills the gaps in information captured by optical sensors due to weather and light limitations. Since conditional generative adversarial network (cGAN) has the powerful ability to generate images, many studies have started to apply it to image translation tasks. For SAR-to-optical translation, some specialized cGAN models have been proposed, but most of them struggle to process SAR images with widely varying styles, often generating images with poor quality. To this end, we propose a hybrid cGAN that combines the advantages of convolutional neural network (CNN) and vision transformer (ViT). With the advantage of ViT to capture long-distance feature dependencies, the global features can be extracted and then fused with the local features extracted by CNN to improve the representation capabilities of our generator. Moreover, we expand the receptive field of the residual blocks in CNN by hierarchical convolution. Perceptual loss and classification loss are added for training to further improve the fidelity of the generated images. Finally, we introduce the multiscale strategy into the discriminator to balance its learning ability with that of the generator. Both visual and quantitative experiments are conducted with other state-of-the-art methods. The results show that our method not only achieves the optimal results in all the evaluation metrics but also generates images that are more consistent with the human visual system. In addition, the potential of our method to process multitype SAR images with significant style differences is also experimentally demonstrated.

Plant recognition recently becomes more and more attractive in computer vision and pattern recognition. Although some researchers have proposed several methods, their accuracy is not satisfactory. Therefore, a novel method of plant recognition based on leaf image is proposed in the paper. Both shape and texture features are employed in the proposed method Texture feature is extracted by intersecting cortical model, and shape feature is obtained by the representation of center distance sequence. Support vector machine is employed for the classifier. The leaf image is preprocessed to get better quality for extracting features, and then entropy sequence and center distance sequence are obtained by intersecting cortical model and center distance transform, respectively. Redundant data of entropy sequence vector and center distance are reduced by principal component analysis. Finally, feature vector is imported into the classifier for classification. In order to evaluate the performance, several existing methods are used to compare with the proposed method and three leaf image datasets are taken as test samples. The experimental result shows the proposed method gets the better accuracy of recognition than other methods.

This letter proposes a novel dual-output pulse coupled neural network model (DPCNN). The new model is applied to obtain a more stable texture description in the face of the geometric transformation. Time series, which are computed from output binary images of DPCNN, are employed as translation-, rotation-, scale-, and distortion-invariant texture features. In the experiments, DPCNN has been well tested by using Brodatz's album and the VisTex database. Several existing models are compared with the proposed DPCNN model. The experimental results, based on different testing data sets for images with different translations, orientations, scales, and affine transformations, show that our proposed model outperforms existing models in geometry-invariant texture retrieval. Furthermore, the robustness of DPCNN to noisy data is examined in the experiments.