High-voltage line defect detection method and device, storage medium and electronic equipment

• Main Authors: LI MINGLEI, QIN YIXIU, LUO ZHIYONG, XIONG YONGLIANG, GUO BAOMING, JIANG JIONG, CHEN DAIGENG, WANG QUN
• Format: Patent
• Language: Chinese; English
• Published: 19.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The embodiment of the invention discloses a high-voltage line defect detection method and device, a storage medium and electronic equipment. The method comprises the steps: acquiring an input image corresponding to a to-be-detected area; compressing the input image to obtain an image with a preset size; performing feature extraction on the image of the preset size through a feature extraction network to obtain a plurality of feature images of different sizes; and based on an SPP layer and a YOLO layer in the Yolov3 neural network algorithm model, detecting the plurality of feature images of different sizes to obtain a defect detection result. The SPP layer is optimally added to the Yolov3 algorithm, so that the accuracy and efficiency of defect detection can be improved. 本申请实施例公开了一种高压线路缺陷检测方法、装置、存储介质及电子设备，所述方法包括：获取待检测区域对应的输入图像；将所述输入图像进行压缩处理得到预设尺寸的图像；通过特征提取网络对所述预设尺寸的图像进行特征提取得到的多个不同尺寸的特征图像；基于Yolov3神经网络算法模型中的SPP层和YOLO层对所述多个不同尺寸的特征图像进行检测得到缺陷检测结果，本申请在Yolov3算法上优化添加了SPP层，可以提高缺陷检测的准确率和效率。