论文部分内容阅读
动车组运行故障动态图像检测系统(TEDS),通过在轨边安装布置高速线阵采集相机,实现对运行中列车的全方位监控。利用获得的高质量图像,通过机器学习和模式识别,实现列车故障的自动化诊断和检测。但是线阵相机拍摄的图像易受动车速度的影响,在图像水平方向上存在几何变形,给后续目标的自动识别和检测带来了困难。为了解决这个问题,设定一组基准图像,对其他时间段所获得的目标图像分别按照对应的基准图像进行配准和重分割,尽量减小列车速度对成像变形的影响。结合TEDS,利用多分辨率下的图像快速配准方法,实现了后续目标图像的快速分割与对齐。提出了一种改进的图像差影技术,通过将对齐之后的目标图像与历史标准图像进行比对分析,快速实现动车故障区域的自动定位和检测。
EMU running fault dynamic image detection system (TEDS), through the rail installation of high-speed line array camera installed to achieve full control of the train running. Using the high-quality images obtained, automatic diagnosis and detection of train faults can be realized through machine learning and pattern recognition. However, the image taken by a line-array camera is susceptible to the speed of a moving vehicle, and there is a geometric distortion in the horizontal direction of the image, which makes it difficult to automatically identify and detect subsequent targets. In order to solve this problem, a set of reference images are set, the target images obtained in other time periods are respectively registered and re-divided according to the corresponding reference images, and the influence of the train speed on the image deformation is minimized. Combined with TEDS, the fast image segmentation and alignment of subsequent target images are realized by using the fast image registration method under multi-resolution. An improved image aberration technique is proposed. By comparing the target image after alignment with the historical standard image, the automatic locating and detecting of the fault area of the vehicle can be quickly realized.