Improvement of Machine Vision Video Signal Processing Algorithm for Higher Accuracy in Extended Object Speed Measurements

Abstract

Machine vision systems are widely used for monitoring of the railway infrastructure condition. High reliability of machine vision systems allows using them not only for video recording but also for automation of technological processes. One of the important tasks in the process automation is measurement of an extended object speed (rail-road cars, electric locomotives and rolling stock). Some systems have a requirement to estimate speed in real time (braking of cars at a shunting yard). In this case the speed is calculated by two adjacent frames to ensure the minimum delay for measurement. However, the image of an extended object can be uninformative (image fragments are uniform in brightness), the weather can cause interference. It leads to high speed estimation error. This article describes the improvement for the existing real-time algorithm which allows for higher accuracy in speed measurements. The improvement implies selection of an informative image area corresponding to an extended object. A comparative analysis of the existing and improved algorithm showed a significant reduction in the estimation error in speed measurements.