电机与控制应用2024，Vol.51Issue(5)：50-60,11.DOI:10.12177/emca.2024.037
基于改进ResNet34网络的变电站设备巡检图像分类识别的方法
Method for Substation Equipment Inspection Image Classification and Recognition Based on Improved ResNet34 Network
摘要
Abstract
Aiming at the problems of limited image scale and low recognition accuracy in the field of substation equipment inspection image recognition,an image classification and recognition method based on improved ResNet34 network is proposed.The Seam Carving algorithm is employed to compress the low-energy areas in the image for the preservation of key features.Additionally,six types of image enhancement techniques such as elastic transformation and Gaussian noise are utilized to increase the diversity of the images.The basic ResNet34 network is integrated with the convolutional block attention module to enhance the model's ability to extract key features from equipment inspection images.A model pre-trained on the ImageNet dataset is utilized as a feature extractor for transfer learning to address the issue of insufficient sample quantity.A cosine annealing strategy is introduced in the Adam optimizer to dynamically adjust the learning rate,to make the improved ResNet34 network converge to the optimal solution faster.Experimental results show that the proposed method improves accuracy by 0.073 3 and reduces the loss rate by 0.201 9 compared to the basic ResNet34 network,which provides a reliable solution for the field of substation equipment inspection image recognition.关键词
ResNet34/卷积注意力模块/迁移学习/余弦退火策略Key words
ResNet34/convolutional block attention module/transfer learning/cosine annealing strategy分类
信息技术与安全科学引用本文复制引用
刘志坚,孟欣雨,刘航,罗灵琳,张德春..基于改进ResNet34网络的变电站设备巡检图像分类识别的方法[J].电机与控制应用,2024,51(5):50-60,11.基金项目
云南省重点研发计划(202303AA080002) （202303AA080002）
云南省基础研究重点项目(202301AS070055) （202301AS070055）
云南省基础研究青年项目(202201AU070086)Major Project of Basic Research Foundation of Yunnan Province(202303AA080002) （202201AU070086）
Key Project of Yunnan Fundamental Research Projects(202301AS070055) （202301AS070055）
Youth Project of Yunnan Fundamental Research Projects(202201AU070086) （202201AU070086）
