FIELD: railway engineering.
SUBSTANCE: information-measuring systems used in computer vision systems designed to solve the problem of measuring the distance to an object using its only digital video image. The object to which the range is measured is the nearest railway car along the route of the diesel shunter with an automatic control system. The method for measuring the distance to a car using a video camera is based on recognizing in the image, using a machine learning algorithm, the inter-rail space of the railway track free of cars; applying a morphological closure operation to the resulting binary image; automatically selecting a line of a binary image corresponding to the end of a section of the track free from cars, and determining in it the pixel coordinates of the extreme points of the binary image. Further calculation of the range to the car consists of solving the equations of projective geometry for the a priori known width of the railway track L.
EFFECT: increasing the accuracy of measuring the distance to the car in conditions of insufficient visibility or uneven illumination.
1 cl, 8 dwg
