Recent change detection (CD) methods focus on the extraction of deep change semantic features. However, existing methods overlook the fine-grained features and have the poor ability to capture long-range space–time information, which leads to the micro changes missing and the edges of change types smoothing. In this paper, a potential transformer-based semantic change detection (SCD) model, Pyramid-SCDFormer is proposed, which precisely recognizes the small changes and fine edges details of the changes. The SCD model selectively merges different semantic tokens in multi-head self-attention block to obtain multiscale features, which is crucial for extraction information of remote sensing images (RSIs) with multiple changes from different scales. Moreover, we create a well-annotated SCD dataset, Landsat-SCD with unprecedented time series and change types in complex scenarios. Comparing with three Convolutional Neural Network-based, one attention-based, and two transformer-based networks, experimental results demonstrate that the Pyramid-SCDFormer stably outperforms the existing state-of-the-art CD models and obtains an improvement in MIoU/F1 of 1.11/0.76%, 0.57/0.50%, and 8.75/8.59% on the LEVIR-CD, WHU_CD, and Landsat-SCD dataset respectively. For change classes proportion less than 1%, the proposed model improves the MIoU by 7.17–19.53% on Landsat-SCD dataset. The recognition performance for small-scale and fine edges of change types has greatly improved.

Using the powerful communication capability of 6G, various in-vehicle services in the Internet of Vehicles (IoV) can be offered with low delay, which provide users with a high-quality driving experience. Edge computing in 6G-enabled IoV utilizes edge servers distributed at the edge of the road, enabling rapid responses to delay-sensitive tasks. However, how to execute computation offloading effectively in 6G-enabled IoV remains a challenge. In this paper, a Computation Offloading method with Demand prediction and Reinforcement learning, named CODR, is proposed. First, a prediction method based on Spatial-Temporal Graph Neural Network (STGNN) is proposed. According to the predicted demand, a caching decision method based on the simplex algorithm is designed. Then, a computation offloading method based on twin delayed deterministic policy gradient (TD3) is proposed to obtain the optimal offloading scheme. Finally, the effectiveness and superiority of CODR in reducing delay are demonstrated through a large number of simulation experiments.

Tree species classification within shelterbelts is crucial for shelterbelt management. The large-scale satellite-based and low-altitude drone-based approaches serve as powerful tools for forest monitoring, especially in tree species classification. However, these methods face challenges in distinguishing individual tree species within complex backgrounds. Additionally, the mixed growth of trees within protective forest suffers from similar crown size among different tree species. The complex background of the shelterbelts negatively impacts the accuracy of tree species classification. The You Only Look Once (YOLO) algorithm is widely used in the field of agriculture and forestry, ie., plant and fruit identification, pest and disease detection, and tree species classification in forestry. We proposed a YOLOv7-Kmeans++_CoordConv_CBAM (YOLOv7-KCC) model for tree species classification based on drone RGB remote sensing images. Firstly, we constructed a dataset for tree species in shelterbelts and adopted data augmentation methods to mitigate overfitting due to limited training data. Secondly, the K-means++ algorithm was employed to cluster anchor boxes in the dataset. Furthermore, to enhance the YOLOv7 backbone network’s Efficient Layer Aggregation Network (ELAN) module, we used Coordinate Convolution (CoordConv) replaced the ordinary 1×1 convolution. The Convolutional Block Attention Module (CBAM) was integrated into the Path Aggregation Network (PANet) structure to facilitate multiscale feature extraction and fusion, allowing the network to better capture and utilize crucial feature information. Experimental results showed that the YOLOv7-KCC model achieves a mean average precision@0.5 of 98.91%, outperforming the Faster RCNN-VGG16, Faster RCNN-Resnet50, SSD, YOLOv4, and YOLOv7 models by 5.71%, 11.75%, 5.97%, 7.86%, and 3.69%, respectively. The GFlops and Parameter values of the YOLOv7-KCC model stand at 105.07G and 143.7MB, representing an almost 5.6% increase in F1 metrics compared to YOLOv7. Therefore, the proposed YOLOv7-KCC model can effectively classify shelterbelt tree species, providing a scientific theoretical basis for shelterbelt management in Northwest China focusing on Xinjiang.

Based on cloud-edge computing, the Internet of Vehicles (IoV) is rapidly developing as a key part of greatly facilitating our lives in the era of Web 3.0. Plenty of delay-sensitive tasks are executed in adjacent edge servers (ESs) in IoV, incurring the increasing significance of the distribution of ESs. As a decentralized network, Web 3.0 allows for data and applications to be distributed across multiple nodes, making it more transparent and user-controlled and placing higher demands on security. Specifically, some attackers outside IoV transmit insecure tasks, which may damage the ESs or waste computing resources after being executed in ESs. To achieve the security of Web 3.0, zero-trust security, an enhanced security model, is used, which assumes that all the service requests are not trusted to access the system networks by default unless passing the anomaly detection. Therefore, in this paper, a secure ESP method with the non-cooperative game for IoV in cloud-edge computing, named ESPS, is proposed. By incorporating an anomaly detection mechanism of tasks, ESPS enhances the security of ESP. Eventually, the experiments on the distribution of Telecom base stations in Shanghai, China show the effectiveness of ESPS.

Accurately extracting buildings is essential for urbanization rate statistics, urban planning, resource allocation, etc. The high-resolution remote sensing images contain rich building information, which provides an important data source for building extraction. However, the extreme abundance of building types with large differences in size, as well as the extreme complexity of the background environment, result in the accurate extraction of spatial details of multi-scale buildings, which remains a difficult problem worth studying. To this end, this study selects the representative Xinjiang Tumxuk urban area as the study area. A building extraction network (SCA-Net) with feature highlighting, multi-scale sensing, and multi-level feature fusion is proposed, which includes Selective kernel spatial Feature Extraction (SFE), Contextual Information Aggregation (CIA), and Attentional Feature Fusion (AFF) modules. First, Selective kernel spatial Feature Extraction modules are used for cascading composition, highlighting information representation of features, and improving the feature extraction capability. Adding a Contextual Information Aggregation module enables the acquisition of multi-scale contextual information. The Attentional Feature Fusion module bridges the semantic gap between high-level and low-level features to achieve effective fusion between cross-level features. The classical U-Net, Segnet, Deeplab v3+, and HRNet v2 semantic segmentation models are compared on the self-built Tmsk and WHU building datasets. The experimental results show that the algorithm proposed in this paper can effectively extract multi-scale buildings in complex backgrounds with IoUs of 85.98% and 89.90% on the two datasets, respectively. SCA-Net is a suitable method for building extraction from high-resolution remote sensing images with good usability and generalization.