CROP WEEDS DETECTION USING NEURAL NETWORK MODELS

Weeds are one of the most important factors affecting agricultural production. Environmental pollution caused by the application of herbicides over the entire agricultural land surface is becoming more and more obvious. Accurately distinguishing crops from weeds by machines and achieving precise treatment of only weed species is one possibility to reduce the use of herbicides. However, precise treatment depends on the precise identification and location of weeds and cultivated plants. The aim of the work was to describe and point out the importance of deep learning models for the detection and classification of weeds, in order to enhance their application in real conditions.