铁路路况识别系统的设计和开发

为了实现对多种复杂铁路路况的识别,需要采集路况图像并加以处理,以得到识别所需的图像特征,最后通过模式识别辨别路况.由摄像机、采集卡、计算机及相关软件建立一套路况图像采集与识别系统.探讨数字图像的采集、图像处理中同态滤波、对比度增强、优化二值化算法、膨胀操作、粒子滤波等处理方法以及模式识别方法在铁路路况识别系统中的应用.经过现场验证,所设计系统识别准确率达94.4%,识别效果理想,可以满足路况采集及识别的需要,是一种可以运用在铁路机车智能减振系统中的新方法.

Design and development of Automatic Railway Condition Recognition System

In order to get the feathers and recognize some complex status of railway, digital image should be gathered and processed. The railway image was taken by a CCD camera, and stored in the computer. Those images were processed so it could be get the feathers. The processing included homomorphism enhancement, contrast ratio enlargement, threshold, dilate, particle filter. The feathers of the image were used to recognize the status of railway. It was processed a series railway image, and the accuracy of recognizing was 94.4%. The System was credible. It was a new method which could be used in Shocking Absorption System on engine.