强环境噪声下的双目视觉受电弓轨旁异常检测  

Binocular vision-based trackside pantograph anomaly detection under strong environmental noise

作　　者：赵进[1,2] 郭寅 尹仕斌 郭磊 邾继贵 ZHAO Jin;GUO Yin;YIN Shibin;GUO Lei;ZHU Jigui(State Key Laboratory of Precision Measuring Technology and Instruments,Tianjin University,Tianjin 300072,China;ISVision(Hangzhou)Technology Co.,Ltd.,Hangzhou 310052,China)

机构地区：[1]天津大学精密测试技术及仪器全国重点实验室,天津300072 [2]易思维(杭州)科技股份有限公司,浙江杭州310052

出　　处：《光学精密工程》2025年第3期438-451,共14页Optics and Precision Engineering

基　　金：面向智能制造与智能运维的工业机器视觉创业团队项目(No.TD2020009)。

摘　　要：为了应对列车受电弓轨旁异常检测场景下,强环境噪声对双目视觉系统结构参数造成较大的扰动,导致视差图计算结果不准确进而影响异常检测精度的问题,对原有立体匹配方法进行改进后并结合异常特征检测方法,提出一种应用于该场景下的受电弓轨旁异常检测方法。采用扩展邻域的代价计算和加权代价聚合方法,有效解决在强环境噪声时由于环境振动或自身结构蠕变导致双目极线不准确的情况;采用局部二值模式方法计算代价分布函数,使算法更适用于已知工件的固定场景检测;结合实际应用场景,限定视差计算搜索空间,优化计算效率,提升轨旁检测的实时性;最后对三维重建后的点云信息进行异常特征检测,在受电弓轨旁异常检测系统中验证了算法的有效性。实验结果表明,本文提出的算法较传统算法测量精度提升60%以上,时间效率提升30%以上,有效解决了该场景下轨道交通现场检测设备效率低和精度不足的问题。To address the challenge posed by significant environmental noise that disrupts the parameters of binocular vision systems in pantograph anomaly detection-thereby compromising the accuracy of dispari⁃ty maps and detection precision-an improved stereo matching method was developed and integrated with anomaly feature detection for this application.This study employs an expanded neighborhood cost calcula⁃tion and weighted cost aggregation to mitigate the inaccuracies associated with binocular epipolar geometry induced by environmental noise or structural alterations.The local binary pattern method was utilized to compute the cost distribution function,rendering the algorithm applicable for fixed scene detection.Addi⁃tionally,the disparity search space was constrained to enhance efficiency for real-time trackside detection.Subsequently,abnormal feature detection was conducted on the reconstructed 3D point cloud to derive measurement outcomes.The efficacy of this approach was validated within a pantograph anomaly detec⁃tion system at railway stations.Experimental results indicate that the proposed algorithm enhances time ef⁃ficiency by over 30%and measurement accuracy by more than 60%when compared to conventional algo⁃rithms,thus effectively addressing the issues of low efficiency and insufficient accuracy in rail transit onsite detection equipment.

关 键 词：受电弓检测 立体匹配 异常检测 视差优化 三维重建 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术]