Accurate multi-scale object detection in remote sensing images poses a challenge due to the complexity of transferring deep features to shallow features among multi-scale objects. Therefore, this study developed a multi-feature fusion and attention network (MFANet) based on YOLOX. By reparameterizing the backbone, fusing multi-branch convolution and attention mechanisms, and optimizing the loss function, the MFANet strengthened the feature extraction of objects at different sizes and increased the detection accuracy. The ablation experiment was carried out on the NWPU VHR-10 dataset. Our results showed that the overall performance of the improved network was around 2.94% higher than the average performance of every single module. Based on the comparison experiments, the improved MFANet demonstrated a high mean average precision of 98.78% for 9 classes of objects in the NWPU VHR-10 10-class detection dataset and 94.91% for 11 classes in the DIOR 20-class detection dataset. Overall, MFANet achieved an mAP of 96.63% and 87.88% acting on the NWPU VHR-10 and DIOR datasets, respectively. This method can promote the development of multi-scale object detection in remote sensing images and has the potential to serve and expand intelligent system research in related fields such as object tracking, semantic segmentation, and scene understanding.

Correct detection of floating objects in complex water environments is a challenge because of the problems of obscuration and dense floating objects. In view of the above issues, this paper proposed a network called EC-YOLOX by introducing the CA (Coordinate Attention) and ECA (Efficient Channel Attention) mechanism and improving the loss function to further the multi-feature extraction and detection accuracy of floating objects. In this paper, ablation experiments and comparison experiments were conducted on the river floating objects dataset. The ablation experiments showed that the ECA and CA mechanism played a great role in EC-YOLOX, which can reduce the miss detection rate by 5.86% and increase the mAP by 5.53% compared with YOLOX. The EC-YOLOX was also applicable to different types of floating objects; the mAP of the ball, plastic-garbage, plastic-bag, leaf, milk-box, grass, and branches were respectively improved by 4%, 4%, 4%, 6%, 4%, 18%, and 5%. The mAP of the comparison experiments was improved by 15.13%, 9.30%, and 8.03% compared to Faster R-CNN, YOLOv5, and YOLOv3, respectively. This method facilitates the precise extraction of floating objects from images, which holds paramount importance for monitoring and safeguarding water environments. It offers significant contributions to water environment monitoring and protection.

With the rapid development of information technology construction, increasing specialized data in the field of informatization have become a hot spot for research. Among them, meteorological data, as one of the foundations and core contents of meteorological informatization, is the key production factor of meteorology in the era of digital economy as well as the basis of meteorological services for people and decision-making services. However, the existing centralized cloud computing service model is unable to satisfy the performance demand of low latency, high reliability and high bandwidth for weather data quality control. In addition, strong convective weather is characterized by rapid development, small convective scale and short life cycle, making the complexity of real-time weather data quality control increased to provide timely strong convective weather monitoring services. In order to solve the above problems, this paper proposed the cloud–edge cooperation approach, whose core idea is to effectively combine the advantages of edge computing and cloud computing by taking full advantage of the computing resources distributed at the edge to provide service environment for users to satisfy the real-time demand. The powerful computing and storage resources of the cloud data center are utilized to provide users with massive computing services to fulfill the intensive computing demands.

The comprehensive use of high-resolution remote sensing (HRS) images and deep learning (DL) methods can be used to further accurate urban green space (UGS) mapping. However, in the process of UGS segmentation, most of the current DL methods focus on the improvement of the model structure and ignore the spectral information of HRS images. In this paper, a multiscale attention feature aggregation network (MAFANet) incorporating feature engineering was proposed to achieve segmentation of UGS from HRS images (GaoFen-2, GF-2). By constructing a new decoder block, a bilateral feature extraction module, and a multiscale pooling attention module, MAFANet enhanced the edge feature extraction of UGS and improved segmentation accuracy. By incorporating feature engineering, including false color image and the Normalized Difference Vegetation Index (NDVI), MAFANet further distinguished UGS boundaries. The UGS labeled datasets, i.e., UGS-1 and UGS-2, were built using GF-2. Meanwhile, comparison experiments with other DL methods are conducted on UGS-1 and UGS-2 to test the robustness of the MAFANet network. We found the mean Intersection over Union (MIOU) of the MAFANet network on the UGS-1 and UGS-2 datasets was 72.15% and 74.64%, respectively; outperforming other existing DL methods. In addition, by incorporating false color image in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.64%; by incorporating vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.09%; and by incorporating false color image and the vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.73%. Our experimental results demonstrated that the proposed MAFANet incorporating feature engineering (false color image and NDVI) outperforms the state-of-the-art (SOTA) methods in UGS segmentation, and the false color image feature is better than the vegetation index (NDVI) for enhancing green space information representation. This study provided a practical solution for UGS segmentation and promoted UGS mapping.