Medical image fusion (MIF) has received painstaking attention due to its diverse medical applications in response to accurately diagnosing clinical images. Numerous MIF methods have been proposed to date, but the fused image suffers from poor contrast, non-uniform illumination, noise presence, and improper fusion strategies, resulting in an inadequate sparse representation of significant features. This paper proposes the morphological preprocessing method to address the non-uniform illumination and noise by the bottom-hat–top-hat strategy. Then, grey-principal component analysis (grey-PCA) is used to transform RGB images into gray images that can preserve detailed features. After that, the local shift-invariant shearlet transform (LSIST) method decomposes the images into the low-pass (LP) and high-pass (HP) sub-bands, efficiently restoring all significant characteristics in various scales and directions. The HP sub-bands are fed to two branches of the Siamese convolutional neural network (CNN) by process of feature detection, initial segmentation, and consistency verification to effectively capture smooth edges, and textures. While the LP sub-bands are fused by employing local energy fusion using the averaging and selection mode to restore the energy information. The proposed method is validated by subjective and objective quality assessments. The subjective evaluation is conducted by a user case study in which twelve field specialists verified the superiority of the proposed method based on precise details, image contrast, noise in the fused image, and no loss of information. The supremacy of the proposed method is further justified by obtaining 0.6836 to 0.8794, 0.5234 to 0.6710, and 3.8501 to 8.7937 gain for ${\mathrm{Q}}_{\mathrm{F}}^{\mathrm{AB}}$, CRR, and AG and noise reduction from 0.3397 to 0.1209 over other methods for objective parameters.

Deep learning (DL) has achieved significant attention in the field of infrared (IR) and visible (VI) image fusion, and several attempts have been made to enhance the quality of the final fused image. It produces better results than conventional methods; however, the captured image cannot acquire useful information due to environments with poor lighting, fog, dense smoke, haze, and the noise generated by sensors. This paper proposes an adaptive fuzzy-based preprocessing enhancement method that automatically enhances the contrast of images with adaptive parameter calculation. The enhanced images are then decomposed into base and detail layers by anisotropic diffusion-based edge-preserving filters that remove noise while smoothing the edges. The detailed parts are fed into four convolutional layers of the VGG-19 network through transfer learning to extract features maps. These features maps are fused by multiple fusion strategies to obtain the final fused detailed layer. The base parts are fused by the PCA method to preserve the energy information. Experimental results reveal that our proposed method achieves state-of-the-art performance compared with existing fusion methods in a subjective evaluation through the visual experience of experts and statistical tests. Moreover, the objective assessment parameters are conducted by various parameters ($FMI$, $SSI{M}_a$, $API$, $\mathrm{EN}$, ${\mathrm{Q}}_{\mathrm{F}}^{\mathrm{AB}}$, and $N_F^{AB}$) which were used in the comparison method. The proposed method achieves 0.2651 to 0.3951, 0.5827 to 0.8469, 56.3710 to 71.9081, 4.0117 to 7.9907, and 0.6538 to 0.8727 gain for $FMI$, $SSI{M}_a$, $API$, $\mathrm{EN}$, and ${\mathrm{Q}}_{\mathrm{F}}^{\mathrm{AB}}$, respectively. At the same time, the proposed method has more noise reduction (0.3049 to 0.0021) that further justifies the efficacy of the proposed method than conventional methods.

Measuring the temperature of insulator in infrared image and diagnosing whether there is abnormal temperature rise is important for electric power inspection. Traditional object detection uses horizontal detection boxes. When they are applied to insulator temperature measurement, their rough positioning results in measurement deviation. Although some detectors with rotated box have been used to tackle this problem, their rotation angle prediction is still not precise enough, resulting in the positioning deviation of insulator core rod, which also leads to temperature measurement deviation. In this paper, we propose a complete solution to address these problems. First, we design an adaptive balanced feature pyramid network (Adaptive BFPN) to fuse localization and semantic information more efficiently, which can improve the detection integrity of large-scale insulators. Second, we design a novel θ-Intersection over Union (θ-IoU) loss to enhance the accuracy of the detector in predicting rotation angle and insulator positioning. Third, we propose a method to locate and automatically correct the position of insulator core rod, measure the temperature, and diagnose defects. It enables faster temperature measurement and more automatic defect diagnosis. Finally, comparative experiments show that our method has a higher accuracy in diagnosing overheating defects than other advanced methods, reaching 97.07%. Our method provides a more intelligent and automated solution for inspecting insulator overheating defects.

With the development of smart grids, vision-based meter reading recognition methods are gradually replacing traditional manual inspections. In substations, meter reading faces image corruption challenges caused by various factors such as strong electromagnetic interference, lighting variations and weather conditions. The existing methods show significant performance degradation in noisy environments. To address this, we propose a robust pointer meter reading recognition method under image corruption. We first design image corruption augmentation (ICA), which significantly enhances the resilience of the model to disturbances. We introduce mask scoring convolution region-based convolutional neural network (MSC R-CNN) to segment pointer and scale masks on dial. MSC head improves localization and segmentation accuracy, while the balanced aggregation feature pyramid (BAFP) fuses features and enables multi-scale predictions. The inclusion of the global context (GC) block mitigates the impact of interference. For meter readings, we develop scale area proportion (SAP) reading method to process pointer and scale masks. The experimental results demonstrate that MSC R-CNN achieves 64.2 Mask mAP and 58.4 Mask mPC, surpassing the 58.4 Mask mAP and 26.0 Mask mPC of Mask R-CNN. SAP reading method achieves a successful meter reading rate (SMR rate) of 94.6% and maintains an average SMR rate of 92.4% under image corruption. The proposed method manifests robust meter reading recognition under image corruption. It can contribute to the further upgrading of smart grids. The code is available at https://github.com/ZhaolinWang0110/MeterRecognition.

Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in skeleton‐based action recognition. However, existing GCN‐based models have several issues, such as the topology of the graph is defined based on the natural skeleton of the human body, which is fixed during training, and it may not be applied to different layers of the GCN model and diverse datasets. Besides, the higher‐order information of the joint data, for example, skeleton and dynamic information is not fully utilised. This work proposes a novel multi‐stream adaptive spatial‐temporal attention GCN model that overcomes the aforementioned issues. The method designs a learnable topology graph to adaptively adjust the connection relationship and strength, which is updated with training along with other network parameters. Simultaneously, the adaptive connection parameters are utilised to optimise the connection of the natural skeleton graph and the adaptive topology graph. The spatial‐temporal attention module is embedded in each graph convolution layer to ensure that the network focuses on the more critical joints and frames. A multi‐stream framework is built to integrate multiple inputs, which further improves the performance of the network. The final network achieves state‐of‐the‐art performance on both the NTU‐RGBD and Kinetics‐Skeleton action recognition datasets. The simulation results prove that the proposed method reveals better results than existing methods in all perspectives and that shows the superiority of the proposed method.

Due to long-term exposure to the wild, insulators are prone to various defects that affect the safe operation of the power system. In recent years, the combination of drones and deep learning has provided a more intelligent solution for insulator automatic defect inspection. Positioning insulators is an important prerequisite step for defect detection, and the accuracy of insulator positioning greatly affects defect detection. However, traditional horizontal detectors lose directional information and it is difficult to accurately locate tilted insulators. Although oriented detectors can predict detection boxes with rotation angles to solve this problem, these models are complex and difficult to apply to edge devices with limited computing power. This greatly limits the practical application of deep learning methods in insulator detection. To address these issues, we proposed a lightweight insulator oriented detector. First, we designed a lightweight insulator feature pyramid network (LIFPN). It can fuse features more efficiently while reducing the number of parameters. Second, we designed a more lightweight insulator oriented detection head (LIHead). It has less computational complexity and can predict rotated detection boxes. Third, we deployed the detector on edge devices and further improved its inference speed through TensorRT. Finally, a series of experiments demonstrated that our method could reduce the computational complexity of the detector by approximately 49 G and the number of parameters by approximately 30 M while ensuring almost no decrease in the detection accuracy. It can be easily deployed to edge devices and achieve a detection speed of 41.89 frames per second (FPS).