ВЫБОР МОДЕЛИ И АРХИТЕКТУРЫ НЕЙРОННОЙ СЕТИ ДЛЯ СИСТЕМЫ ТЕХНИЧЕСКОГО ЗРЕНИЯ ДЕТЕКЦИИ КОРНЕПЛОДОВ САХАРНОЙ СВЁКЛЫ

Abstract

The use of a technical vision system, aimed at ensuring greater safety of sugar beet roots during harvesting and storage by analyzing raw materials arriving at factories, is considered among the methods of long-term storage. The process of distribution of trucks at the receiving point of sugar factories is considered by humans in the work. The purpose of the work is to develop a method for detecting sugar beet roots on an image of the surface of a truck embankment at the receiving point of sugar factories. A neural network was chosen as the raw material recognition method due to the extremely diverse nature of the resulting images, which recognition using a threshold transformation cannot cope with. Algorithms (options such as SSD, YOLO, R-CNN) and architectures (options such as AlexNet, VGGNet, GoogleNet, ResNet) of various neural networks are considered. The most suitable neural network for the required tasks has been identified. The optimal size of the database for training has been determined. As a result of training and testing the neural network, the need to create additional filters was identified. Filters have been created and described that clarify the work of the neural network: filtering out “stuck together” objects, objects with low class membership, objects with an impossible area (too small or large), as well as with an aspect ratio of less than 0.2 or more than 5. A neural network capable to find a sufficient number of sugar beet roots in incoming images and to meet the requirements for high-quality functioning of the technical vision system, was trained based on the results of the work performed.