Cloud segmentation is one of the hot tasks in the field of weather forecast, environmental monitoring, site selection for observatory, and other areas. In this letter, we proposed a new deep convolutional neural network architecture called CloudU-Net for daytime and nighttime cloud images' segmentation. The net consists of dilated convolution, activation, batch normalization (BN), max pooling, upsampling, skip connection, and fully connected conditional random field (CRF) layers. The benefits of the net architecture are four aspects: First, the dilated convolution increases the receptive field of the filters to obtain more information of the context without increasing the extra amount of computation and the extra number of parameters. Second, the BN layer increases the speed of network training and prevents over-fitting. Third, the fully connected CRF optimizes the output of the front end of the architecture, and finally gets better segmentation results. Finally, the enhanced optimizer Lookahead improves the learning stability and speeds up model convergence. Compared with the current deep-learning-based state-of-the-art cloud images' segmentation algorithms, the CloudU-Net demonstrates better segmentation performance for daytime and nighttime cloud images.

With the rapid development of high-resolution satellite remote sensing observation technology, power tower detection based on satellite remote sensing images has become a key research focus for power intelligent inspection. However, the performance of power tower detection in satellite remote sensing images needs improvement due to complex backgrounds, and small and nonuniform target sizes. To address this, this article first constructs a multiscene high-resolution satellite remote sensing power tower dataset and then proposes the large selective kernel feature fusion (LSKF)-you only look once (YOLO) network for high-resolution satellite remote sensing images. This network primarily consists of a large spatial kernel selective attention fusion module and a multiscale feature alignment fusion (MFAF) structure. The large spatial selective kernel mechanism (LSKM) is improved by using the attentional feature fusion module, which provides richer feature information for accurately locating the position of the power tower. The MFAF structure effectively utilizes low-level semantic information, mitigates feature ambiguity in deeper network layers, and enables multiscale feature fusion of power towers within complex backgrounds. In addition, the introduction of minimum point distance-IoU (MPDIoU) enhances complete-IoU (CIoU), further improving the model’s performance. The results demonstrate that the $F1$ score and mAP0.5 of the LSKF-YOLO network reach 0.764% and 77.47%, respectively. Compared with other deep learning-based satellite remote sensing power tower inspection methods, the LSKF-YOLO network significantly enhances detection accuracy and provides crucial technical support for intelligent inspection of power lines via satellite remote sensing.

The unmanned aerial vehicle (UAV) patrol inspection has become an efficient method to ensure the operation condition of transmission lines. The detection of key components with defects in transmission lines is a critical task in maintaining a power system’s stability. However, the complex inspection environment and the imbalance between the number of normal component samples and that of defect samples significantly affect the detection accuracy. In this article, we present a novel method for defect detection in UAV patrol images, based on a hierarchical convolutional vision transformer (HC-ViT) and a simple contrastive masked autoencoder (SC-MAE). The HC-ViT backbone integrates the advantages of vision transformer and convolution, while the SC-MAE is a self-supervised learning method that extracts useful features from normal samples. By introducing the normal features into the backbone, we enhance the performance of the defect detection task. We demonstrate the effectiveness of our method through experiments, and show that it can leverage a large amount of unlabeled normal images, reducing the need for manual annotation. Our method offers a new way to exploit the potential features of patrol inspection images.

A transmission line is the lifeline of a power system, while bolts play the role of connecting fittings and tightening conductors. However, bolts at different positions have different definitions of defects, which belongs to the problem of visually indistinguishable. Aiming at visually indistinguishable bolt defects in transmission lines, this paper propose an end-to-end visually indistinguishable bolt defects detection method that is based on transmission line knowledge reasoning. Firstly, we use the End-to-end Object Detection with Transformers (DETR) as the basic model and augment it with the dilated encoder module to obtain the multi-scale features of the target. Then we design a transmission line image relative position encoding (TL-iRPE) to infer the bolt position knowledge. Finally, this paper designs a bolt attributes classifier and a bolt defects classifier. By combining the position knowledge and the attributes knowledge to assist bolt defect classifier in reasoning bolt defects, the accuracy of bolt defects detection is further improved. We have constructed the Visually Indistinguishable Bolt Defects Dataset (VIBD Dataset) and carried out experiments on the dataset. We call the bolt defects detection method combining position knowledge and attributes knowledge PA-DETR. Compared with other transmission line bolt defect detection methods, PA-DETR has more advantages in transmission line bolt defect detection.

Obtaining accurate cloudage information through ground-based cloud observation is of great significance to astronomical telescope observatory site selection. This paper proposes a residual attention-based encoder–decoder network (CloudRAEDNet) for ground-based cloud image segmentation in nychthemeron. CloudRAEDNet uses ImageNet pre-trained ResNet50 as the encoder backbone network, which reduces the number of network training. The network decoder introduces residual modules to solve the problem of network degradation caused by the increase in the number of network layers. CloudRAEDNet connects encoder and decoder through attention gates to suppress the features of irrelevant areas and automatically focus on areas with prominent features. In addition, the segmentation performance of the network is further improved by the ranger optimizer. The comparative experimental results show that CloudRAEDNet can segment the local details of the ground-based cloud images more finely without increasing the time complexity. Compared with CloudSegNet, EFCN, CloudU-Net and CloudU-Netv2, CloudRAEDNet has the best segmentation performance. The results of ablation experiments show that the attention module contributes the most to CloudRAEDNet and the residual module contributes the least to CloudRAEDNet. In addition, the pre-training and Ranger optimizer also contribute to improving the segmentation performance of CloudRAEDNet.