Educational Computer Vision Materials for Classification and Tracking of Objects

Ziga Emersic, Gregor Hrastnik, Natasa Meh Peer, Vasja Lev Kirn, Aljaz Justin, Jovana Videnovic, Luka Markicevic, Peter Peer

Abstract: With the rise of artificial intelligence (AI), the need for AI curriculum rose as well. In order to tackle the problem, AIM@VET (Artificial Intelligence Modules for Vocational Education and Training) EU project, was initiated. This paper presents a comprehensive set of teaching materials designed to introduce pre-university students to the fundamental techniques and concepts in object tracking and classification within the field of computer vision. The materials cover key topics including the basics of object tracking, region of interest selection, single and multiple object tracking methods, evaluation metrics, motion prediction, classification, and advanced concepts such as deep neural networks. By mastering these skills, students are equipped to contribute to real-world technological advancements and are well-prepared for future academic and professional pursuits in computer vision and related disciplines.

External IDs:dblp:conf/ideal/EmersicHPKJVMP24a