Search

To ensure the timely detection of safety hazards in transmission lines and to enhance accurately the detection of insulator defects in complicated environments, this study proposes a 3D attention-focused pure convolutional target detection algorithm (CMYOLOv7) based on you only look once v7 (YOLOv7) for defect detection on insulators in complicated environments. Firstly, to address the incapacity of focusing on the target in the backbone feature extraction networks, this study proposes a focused pure convolutional feature extraction module (ConvSimCB) to enhance the extraction and focus capability on insulator defect features. Secondly, to solve the problem of loss of key detail feature information caused by maximum pooling in spatial pyramid pooling module (SPPCSPC), this study proposes a mixed spatial pyramid pooling module (MIXPCSPC) to retain abundant image texture detail information and increase accuracy in detection of tiny insulator defects. Finally, a lightweight generic upsampling operator (CARAFE) is introduced to enhance the feature map resolution to address image distortion caused by the Nearest Neighbor Method of upsampling. This study proposed CMYOLOv7 achieves 98.37% precision, 90.59% recall, 95.68% mean average precision (MAP), and 94% F1 score, higher than YOLOv7 by 0.61%, 8.64%, 5.41%, and 5%. [ABSTRACT FROM AUTHOR]

The fusion of infrared and visible images aims to extract and fuse thermal target information and texture details to the fullest extent possible, enhancing the visual understanding capabilities of images for both humans and computers in complex scenes. However, existing methods have difficulties in preserving the comprehensiveness of source image feature information and enhancing the saliency of image texture information. Therefore, we put forward a novel infrared and visible image fusion algorithm based on global information-enhanced attention network (GIEA). Specifically, we develop an attention-guided Transformer module (AGTM) to make sure the fused images have enough global information. This module combines the convolutional neural network and Transformer to perform adequate feature extraction from shallow to deep layers, and utilize the attention network for multi-level feature-guided learning. Then, we build the contrast enhancement module (CENM), which enhances the feature representation and contrast of the image so that the fused image contains significant texture information. Furthermore, our network is driven to fully preserve the texture and structure details of the source images with a loss function that consists of content loss and total variance loss. Numerous experiments demonstrate that our fusion approach outperforms other fusion approaches in both subjective and objective assessments. • Combining CNN and Transformer to fully extract complementary features. • Designed an attention network for multi-level feature learning. • Designed a contrast enhancement module to enhance feature saliency. [ABSTRACT FROM AUTHOR]

• We first noticed the importance of similar and heterogeneous pixel gradients in feature extraction. • Introducing clustering algorithms into the field of image fusion to improve feature extraction capabilities. • Using source image gradients instead of the clustering base layer of traditional algorithms. Image fusion is performed to merge the information of different source images into one image. In this study, a fusion algorithm based on the pixel mean shift and source image gradient was proposed to make the background of the fused image clear and the target prominent. First, a pixel spatial average kernel function was designed to separate the image texture and the significant target during pixel density migration. In this study, a novel approach is presented that distinguishes itself from other methods in two distinct ways. Firstly, it segregates the texture details of dissimilar pixel regions and captures the texture characteristics of analogous pixel regions. Secondly, by utilizing the discrepancy between the minimum and maximum values of infrared and visible images, the proposed technique incorporates the source graph into the fusion process, thereby improving the precision of the information. Additionally, the feature reconstruction function was designed based on the layer features, which could adaptively concentrate the source image information on one image and further improve the clarity and information retention of the fused image. Finally, the results of the qualitative and quantitative comparison of our proposed method with other state-of-the-art methods available, obtained by applying them to public datasets, demonstrated the advantages of our algorithm. Our results retained more appearance details and significantly more target information. [ABSTRACT FROM AUTHOR]