Predikce výskytu ozbrojených osob z obrazových záznamů s využitím strojového učení

Abstract

This thesis deals with artificial intelligence and its applications in security. The focus of this thesis is the implementation of an intelligent system utilizing machine learning that will be capable of evaluating dangerous situations in a MATLAB simulation environment based on data from an image database. The first part of this thesis covers the general fundamentals of artificial intelligence and specific applications of this technology in security systems. This is followed by the second part of the thesis, which focuses on the implementation of a predictive model capable of detecting weapons in image recordings. The model will be progressively trained and tested under various parameter settings, and an analysis of the model’s performance will be conducted. In conclusion, possible improvements will be proposed for potential further research.