Using artificial intelligence for object detection (first part)

Abstract

The dominance of artificial intelligence is becoming more and more important in everyday life and in the field of scientific discourses, and security technology and security science are no exception. In the first – theoretical – part of our study we deal with machine vision, the history of technical and information science of machine vision, neural networks, and the teaching of networks. In a separate section we discuss the common types of tasks in computer vision (image classification, object localization, object detection), as well as the hardware and development environment (Intel Neural Compute Stick, OpenVINO Toolkit, Raspberry Pi), through which we were able to implement the developments and their results, will be published in the next part of our study. We conclude our theoretical study with an introduction to the concepts of artificial intelligence, machine learning, and deep learning.