Zero-Shot Image Classification Method Based on Attention Mechanism and Semantic Information Fusion.

The zero-shot image classification (ZSIC) is designed to solve the classification problem when the sample is very small, or the category is missing. A common method is to use attribute or word vectors as a priori category features (auxiliary information) and complete the domain transfer from training of seen classes to recognition of unseen classes by building a mapping between image features and a priori category features. However, feature extraction of the whole image lacks discrimination, and the amount of information of single attribute features or word vector features of categories is insufficient, which makes the matching degree between image features and prior class features not high and affects the accuracy of the ZSIC model. To this end, a spatial attention mechanism is designed, and an image feature extraction module based on this attention mechanism is constructed to screen critical features with discrimination. A semantic information fusion method based on matrix decomposition is proposed, which first decomposes the attribute features and then fuses them with the extracted word vector features of a dataset to achieve information expansion. Through the above two improvement measures, the classification accuracy of the ZSIC model for unseen images is improved. The experimental results on public datasets verify the effect and superiority of the proposed methods.

Insulator Umbrella Disc Shedding Detection in Foggy Weather.

The detection of insulator umbrella disc shedding is very important to the stable operation of a transmission line. In order to accomplish the accurate detection of the insulator umbrella disc shedding in foggy weather, a two-stage detection model combined with a defogging algorithm is proposed. In the dehazing stage of insulator images, solving the problem of real hazy image data is difficult; the foggy images are dehazed by the method of synthetic foggy images training and real foggy images fine-tuning. In the detection stage of umbrella disc shedding, a small object detection algorithm named FA-SSD is proposed to solve the problem of the umbrella disc shedding occupying only a small proportion of an aerial image. On the one hand, the shallow feature information and deep feature information are fused to improve the feature extraction ability of small targets; on the other hand, the attention mechanism is introduced to strengthen the feature extraction network's attention to the details of small targets and improve the model's ability to detect the umbrella disc shedding. The experimental results show that our model can accurately detect the insulator umbrella disc shedding defect in the foggy image; the accuracy of the defect detection is 0.925, and the recall is 0.841. Compared with the original model, it improved by 5.9% and 8.6%, respectively.

Multi-Geometric Reasoning Network for Insulator Defect Detection of Electric Transmission Lines.

To address the challenges in the unmanned system-based intelligent inspection of electric transmission line insulators, this paper proposed a multi-geometric reasoning network (MGRN) to accurately detect insulator geometric defects based on aerial images with complex backgrounds and different scales. The spatial geometric reasoning sub-module (SGR) was developed to represent the spatial location relationship of defects. The appearance geometric reasoning sub-module (AGR) and the parallel feature transformation (PFT) sub-module were adopted to obtain the appearance geometric features from the real samples. These multi-geometric features can be fused with the original visual features to identify and locate the insulator defects. The proposed solution is assessed through experiments against the existing solutions and the numerical results indicate that it can significantly improve the detection accuracy of multiple insulator defects using the aerial images.

Two-Level Model for Detecting Substation Defects from Infrared Images.

Training a deep convolutional neural network (DCNN) to detect defects in substation equipment often requires many defect datasets. However, this dataset is not easily acquired, and the complex background of the infrared images makes defect detection even more difficult. To alleviate this issue, this article presents a two-level defect detection model (TDDM). First, to extract the target equipment in the image, an instance segmentation module is constructed by training from the instance segmentation dataset. Then, the target equipment is segmented by the superpixel segmentation algorithm into superpixels according to obtain more details information. Next, a temperature probability density distribution is constructed with the superpixels, and the defect determination strategy is used to recognize the defect. Finally, experiments verify the effectiveness of the TDDM according to the defect detection dataset.

Multiscale Entropy Feature Extraction Method of Running Power Equipment Sound.

The equipment condition monitoring based on computer hearing is a new pattern recognition approach, and the system formed by it has the advantages of noncontact and strong early warning abilities. Extracting effective features from the sound data of the running power equipment help to improve the equipment monitoring accuracy. However, the sound of running equipment often has the characteristics of serious noise, non-linearity and instationary, which makes it difficult to extract features. To solve this problem, a feature extraction method based on the improved complementary ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and multiscale improved permutation entropy (MIPE) is proposed. Firstly, the ICEEMDAN is utilized to obtain a group of intrinsic mode functions (IMFs) from the sound of running power equipment. The noise IMFs are then identified and eliminated through mutual information (MI) and mean mutual information (meanMI) of IMFs. Next, the normalized mutual information (norMI) and MIPE are calculated respectively, and norMI is utilized to weigh the corresponding MIPE result. Finally, based on the separability criterion, the weighted MIPE results are feature-dimensionally reduced to obtain the multiscale entropy feature of the sound. The experimental results show that the classification accuracies of the method under the conditions of no noise and 5 dB reach 96.7% and 89.9%, respectively. In practice, the proposed method has higher reliability and stability for the sound feature extraction of the running power equipment.

Image Representation Method Based on Relative Layer Entropy for Insulator Recognition.

Deep convolutional neural networks (DCNNs) with alternating convolutional, pooling and decimation layers are widely used in computer vision, yet current works tend to focus on deeper networks with many layers and neurons, resulting in a high computational complexity. However, the recognition task is still challenging for insufficient and uncomprehensive object appearance and training sample types such as infrared insulators. In view of this, more attention is focused on the application of a pretrained network for image feature representation, but the rules on how to select the feature representation layer are scarce. In this paper, we proposed a new concept, the layer entropy and relative layer entropy, which can be referred to as an image representation method based on relative layer entropy (IRM_RLE). It was designed to excavate the most suitable convolution layer for image recognition. First, the image was fed into an ImageNet pretrained DCNN model, and deep convolutional activations were extracted. Then, the appropriate feature layer was selected by calculating the layer entropy and relative layer entropy of each convolution layer. Finally, the number of the feature map was selected according to the importance degree and the feature maps of the convolution layer, which were vectorized and pooled by VLAD (vector of locally aggregated descriptors) coding and quantifying for final image representation. The experimental results show that the proposed approach performs competitively against previous methods across all datasets. Furthermore, for the indoor scenes and actions datasets, the proposed approach outperforms the state-of-the-art methods.