摘要
针对列车车顶受电弓监控中由于光照异变产生的对受电弓健康状态监控的干扰问题,采用了一种根据图像灰度级分布特征进行欠曝光、正常、过曝光类型的分类方法,根据不同图像增强算法比较后,进行欠曝光的Gamma变换与过曝光的CLAHE算法进行图像增强。对CLAHE算法后串联基于形态学与掩模的方法去除残余阴影,再对处理后的所有图像经过多种滤波方式处理,并以峰值信噪比作为滤波效果指标。结果显示该图像处理方法能有效解决受电弓监控中光照异变问题,采用双边滤波的效果最佳。
Aiming at the interference problem of pantograph health status monitoring caused by light variation in train roof pantograph monitoring,a classification method of under-exposure,normal and over-exposure types is adopted according to the distribution characteristics of image gray level.After the image enhancement algorithms are compared,the Gamma transform of the underexposed image and the CLAHE algorithm of the overexposed image are used for image enhancement.After the CLAHE algorithm,a method based on morphology and mask is connected in series to remove residual shadows,and then all the processed images are processed by multiple filtering methods and the peak signal-to-noise ratio is used as the filtering effect indicator.The results show that this image processing method can effectively solve the problem of illumination anomalies in pantograph monitoring,and the bilateral filter has the best effect.
作者
寇皓为
苏燕辰
李恒奎
邓越
陈国俊
KOU Haowei;SU Yanchen;LI Hengkui;DENG Yue;CHEN Guojun(School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China;CRRC Qingdao Sifang Locomotive and Rolling Stock Co.,Ltd,Shandong 266111,China)
出处
《激光杂志》
CAS
北大核心
2022年第9期83-87,共5页
Laser Journal
基金
国家重点研发计划(2020YFB1200300ZL)资助
成都市重点研发支撑计划(2019-YF05-02685-SN)。
