РАЗРАБОТКА ВЫСОКОПРОИЗВОДИТЕЛЬНОГО МЕТОДА ОПРЕДЕЛЕНИЯ ГЕОМЕТРИЧЕСКИХ ПАРАМЕТРОВ ОБЪЕКТОВ НА ИЗОБРАЖЕНИИ

Abstract

Currently, the development of various process automation systems is becoming more widelyused every day in various fields and industries, the task of developing software methods for thecorresponding automated systems remains urgent. One of the industries where the use and applicationof process automation systems is in demand is the field of non-contact measurement of objectsand their parameters. As an example, the task of determining the geometric parameters ofround timber stacked was chosen. In this regard, in this paper, methods were proposed for determiningthe geometric parameters of objects based on mathematical morphology operations, organizedusing the Canny detector and the Hough algorithm, and a method using a neural networkapproach based on the architecture of the YOLOv5 convolutional neural network. As a result ofthe conducted experimental studies, for the organization of which specially 3d-printed models oflogs were used, it was found that the method based on the use of neural networks is more accuratethan the method based on mathematical morphology. When solving the problem of counting thenumber of objects in the image, using the method based on the neural network approach, all objectslocated in the image were determined, whereas the method using mathematical morphology operations was able to determine only 13 of the 16 logs located, and I identified one false object,as a result of which the result error was about 19% for an image obtained from the Internet. Whenconducting an experiment on manufactured cylinder models, the method based on mathematicalmorphology operations showed unsatisfactory results. Another advantage of the method based onthe neural network approach is the possibility of calculating the area of the ends of logs in theimage and determining the volume of each of the logs located in the stack, as well as the total totalvolume of the entire pack of measured round timber.