基于对抗生成网络与关键点视觉追踪模型的导线异物隐患可视化检出方法  

Visual Detection Method of Hidden Danger of Wire Foreign Object Based on Countermeasure Generation Network and Key Point Visual Tracking Model

作　　者：李丽格 陈燕梅 LI Lige;CHEN Yanmei(State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 321400,China)

机构地区：[1]国网浙江省电力有限公司,浙江杭州321400

出　　处：《微型电脑应用》2024年第6期176-179,共4页Microcomputer Applications

摘　　要：导线关键点附着异物会造成短路或漏电,为了改善恶劣气象条件对图像特征维度对异物隐患可视化检出方法的影响,减少误检情况,提出基于对抗生成网络与关键点视觉追踪模型的导线异物隐患可视化检出方法。使用二维Otsu方法分割去雾导线图像,提取导线异物目标区域,依据所得分割图像,采用对抗生成网络实现导线异物隐患可视化检出。实验结果表明:该方法对导线各关键点的追踪位置与实际位置十分接近,最大偏差仅为0.03 m;经过去雾处理可以明显改善导线关键点图像的清晰度和颜色信息;能够准确、完整地提取导线异物目标区域,且边界信息处理较好。The attachment of foreign objects at key points of the wire can cause short circuits or leakage.To improve the impact of adverse weather conditions and image feature dimensions on visual detection methods for foreign object hidden dangers and reduce false detections,a visual detection method for foreign object hazards in the wire based on adversarial generation networks and key point visual tracking model is proposed.This paper uses the two-dimensional Otsu method to segment and remove fog wire images,extract the target area of wire foreign objects.Based on the segmented images,we use adversarial generation networks to achieve visual detection of wire foreign object hidden dangers.The experimental results show that the tracking positions of each key point on the wire by using this method are very close to the actual position,with a maximum deviation of only 0.03 m.After defogging,the clarity and color information of key point images on the wire can be significantly improved.It can accurately and completely extract the target area of foreign objects in the wire,and the boundary information processing is better.

关 键 词：对抗生成网络 关键点 视觉追踪 电力线 异物隐患 可视化检出 

分 类 号：TP368[自动化与计算机技术—计算机系统结构]