Defect Recognition Method Based on HOG and SVM for Drone Inspection Images of Power Transmission Line

Abstract

This paper introduces the method for defect recognition of power transmission lines based on Histogram of Oriented Gradients (HOG) algorithm and Support Vector Machine (SVM) algorithm. Firstly, this paper investigates the key technologies in the system including image preprocessing, feature extraction methods, feature dimension reduction and classifiers. Secondly, according to the characteristics of power transmission line images, HOG is used to extract image features. HOG is a dense descriptor for the local overlapping area of the image. It constructs the feature by calculating the gradient direction histogram of the local region. Principal Component Analysis (PCA) method is applied to solve the feature dimension explosion. It can be used to extract the main feature components of the data and often used for dimensionality reduction of high-dimensional data. Thirdly, the SVM algorithm is used for classification. In the field of machine learning, it is a supervised learning model, which is usually used for pattern recognition, classification and regression analysis. The Directed Acyclic Graph (DAG) multi-classifiers is designed for the defect recognition of power transmission lines, such as normal lines, strand breakage lines and foreign-matter lines. In addition, the experimental results show that when the size of the pixel cell is 32*32 and the PCA contribution rate is 99%, the image processing has the best defect recognition performance, the processing speed of each image is 0.539 seconds and the average recognition accuracy is 84.3%.