Multi-patch deep features for power line insulator status classification from aerial images

Zhao, Zhenbing; Xu, Guangquan; Qi, Yincheng; Liu, Ning; Zhang, Tiefeng

doi:10.1109/ijcnn.2016.7727606

Cited by 97 publications

(53 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep learning techniques in computer vision applications such as autonomous inspection and monitoring have had a tremendous impact in recent years [16]. Using convolutional neural networks (CNNs) have led computer vision to more advanced approaches.…”

Section: Introductionmentioning

confidence: 99%

Wind turbine tower detection using feature descriptors and deep learning

Abedini

Bahaghighat²,

Shoyan

2020

Facta Univ Electron Energ

View full text Add to dashboard Cite

Wind Turbine Towers (WTTs) are the main structures of wind farms. They are costly devices that must be thoroughly inspected according to maintenance plans. Today, existence of machine vision techniques along with unmanned aerial vehicles (UAVs) enable fast, easy, and intelligent visual inspection of the structures. Our work is aimed towards developing a visionbased system to perform Nondestructive tests (NDTs) for wind turbines using UAVs. In order to navigate the flying machine toward the wind turbine tower and reliably land on it, the exact position of the wind turbine and its tower must be detected. We employ several strong computer vision approaches such as Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Features from Accelerated Segment Test (FAST), Brute-Force, Fast Library for Approximate Nearest Neighbors (FLANN) to detect the WTT. Then, in order to increase the reliability of the system, we apply the ResNet, MobileNet, ShuffleNet, EffNet, and SqueezeNet pre-trained classifiers in order to verify whether a detected object is indeed a turbine tower or not.

show abstract

Section: Introductionmentioning

confidence: 99%

Wind turbine tower detection using feature descriptors and deep learning

Abedini

Bahaghighat²,

Shoyan

2020

Facta Univ Electron Energ

View full text Add to dashboard Cite

show abstract

“…An insulator recognition method based on target recommendation and AdaBoost algorithm was proposed in [10], which can quickly locate insulators and improve the processing speed by changing the search window mechanism. In [11], a novel approach was proposed to inspect insulators with CNN. A CNN model with a multi-patch feature extraction method was applied to represent the status of insulators, and an SVM was trained based on these features.…”

Section: Introductionmentioning

confidence: 99%

“…A CNN model with a multi-patch feature extraction method was applied to represent the status of insulators, and an SVM was trained based on these features. A thorough evaluation was given in [11] on this insulator status dataset of six classes by using on-site inspection videos.…”

Section: Introductionmentioning

confidence: 99%

Image Representation Method Based on Relative Layer Entropy for Insulator Recognition

Zhao

Fan

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

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.Entropy 2020, 22, 419 2 of 17 efficiency for real-time intelligent insulator recognition methods [6,7]. Figure 1 shows insulators on a transmission line.

show abstract

“…During UAV inspections, a number of images are collected to detect the defects in transmission lines. The use of image detection technology greatly improves the efficiency and has become a research hotspot in current smart grids [4][5][6][7]. Insulators, of which the main roles are electrical insulation and line support, are very important components of transmission lines.…”

Section: Introductionmentioning

confidence: 99%

Self-Shattering Defect Detection of Glass Insulators Based on Spatial Features

et al. 2019

View full text Add to dashboard Cite

During an automatic power transmission line inspection, a large number of images are collected by unmanned aerial vehicles (UAVs) to detect existing defects in transmission line components, especially insulators. However, with twin insulator strings in the inspection images, when the umbrella skirts of the rear string are obstructed by the front string, defect detection becomes difficult. To solve this problem, we propose a method to detect self-shattering defects of insulators based on spatial features contained in images. Firstly, the images are segmented according to the particular color features of glass insulators, and the main axes of insulator strings in the images are adjusted to the horizontal direction. Then, the connected regions of insulators in the images are marked. After that, the vertical lengths of the regions, the number of insulator pixels in the regions, as well as the horizontal distances between two adjacent connected regions are selected as spatial features, based on which defect discriminants are formulated. Finally, experiments are performed using the proposed formula to detect self-shattering defects in the insulators, using the spatial distribution of the connected regions to locate the defects. The experiment results indicate that the proposed method has good detection accuracy and localization precision.

show abstract

Multi-patch deep features for power line insulator status classification from aerial images

Cited by 97 publications

References 24 publications

Wind turbine tower detection using feature descriptors and deep learning

Wind turbine tower detection using feature descriptors and deep learning

Image Representation Method Based on Relative Layer Entropy for Insulator Recognition

Self-Shattering Defect Detection of Glass Insulators Based on Spatial Features

Contact Info

Product

Resources

About