GÓMEZ ROJAS, J. Implementace strojového vidění ve výrobním systému UVSSR PORTABLE CELL [online]. Brno: Vysoké učení technické v Brně. Fakulta strojního inženýrství. 2024.

Posudky

Posudek vedoucího

Bražina, Jakub

The main objective of the presented thesis was to implement machine vision in the UVSSR PORTABLE CELL. This solution is also intended to serve as a demonstration in teaching or at other PR events of the Institute of the Production Machines, Systems and Robotics. Even though the student started the solution relatively late, he successfully completed the main objective and all sub-objectives. The student consulted regularly. It should be noted that the developed solution is applicable in a real workplace, although it was tested in a virtual environment due to the lack of a license for the IoT Gateway on the real robot. Although the technical solution is more than sufficient, the student started late with the creation of the text part of the thesis, which was not consulted with the supervisor and could have been better handled. It should be appreciated that the student managed to meet all the objectives without significant prior experience with machine vision and programming in higher programming languages such as python. Based on the afore mentioned, I give the thesis a very positive review and recommend it for defense with an overall grade of excellent A.

Dílčí hodnocení
Kritérium Známka Body Slovní hodnocení
Splnění požadavků a cílů zadání B
Postup a rozsah řešení, adekvátnost použitých metod A
Vlastní přínos a originalita A
Schopnost interpretovat dosažené výsledky a vyvozovat z nich závěry A
Využitelnost výsledků v praxi nebo teorii A
Logické uspořádání práce a formální náležitosti B
Grafická, stylistická úprava a pravopis B
Práce s literaturou včetně citací A
Samostatnost studenta při zpracování tématu A
Navrhovaná známka
A

Posudek oponenta

Kroupa, Jiří

The introduced diploma thesis focuses on the implementation of machine vision in the UVSSR Portable Cell production system. The first part of the work describes the technical background of the proposed field. The main issue with this section is the lack of an overview and comparison of methods generally used for object detection, gesture recognition, and facial recognition. The student chose methods without any further investigation; if such an investigation was conducted, it is not described in the thesis. The second part of the thesis focuses on the implementation of machine vision methods in the production system and the evaluation of the results. The outcome of this part is a working solution for controlling a robot through hand gestures if the user is authorized via facial recognition and tracking the position of pieces in pallets. The user verification created within the thesis can be considered a "preliminary study"; it is not suitable for real production as it is neither secure nor reliable. The student acknowledges that the implemented facial recognition could be easily fooled. While it is understandable because the student worked with limited hardware resources, I would expect at least some proposals on how to improve security. The thesis also contains several formal issues, such as text formatting and missing figure descriptions (e.g., Figures 4.1, 4.7 – 4.11) and the figures are not explicitly referenced in the text. Despite these criticisms, the student has fulfilled all the goals of the assignment, so I recommend the thesis for defense.

Dílčí hodnocení
Kritérium Známka Body Slovní hodnocení
Splnění požadavků a cílů zadání A
Postup a rozsah řešení, adekvátnost použitých metod C
Vlastní přínos a originalita C
Schopnost interpretovat dosaž. výsledky a vyvozovat z nich závěry C
Využitelnost výsledků v praxi nebo teorii C
Logické uspořádání práce a formální náležitosti D
Grafická, stylistická úprava a pravopis B
Práce s literaturou včetně citací A
Navrhovaná známka
C

Otázky

eVSKP id 157468