Automatsko izuzimanje objekata temeljem oblika

undergraduate thesis

• Title (english): Automatic separation of objects based on shape
• Author: Vid Pavlović
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-03-02, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Računalni i strojni vid postaju jedne od najkorištenijih područja umjetne inteligencije u
industriji. Temeljni princip računalnog vida sastoji se od prepoznavanja rubova, te detekcije
kontura i oblika. Cilj ovog rada je predstaviti osnove računalnog vida, Cannyev algoritam za
prepoznavanje rubova, uvod u mikrokontrolere i vrste osvjetljenja u primjeni računalnog vida.
Aplikacija za prepoznavanje oblika napravljena je pomoću Python programskog jezika i
OpenCV biblioteke. Sustav sortiranja upravljan je pomoću Arduino mikrokontrolera.
Konstruirano je kupolno svjetlo i nosač za kameru pomoću tehnologije 3D printanja i
aluminijskih profila. Sustav je povezan tako da Python program prepoznaje oblik koji pošalje
Arduino mikrokontroleru, koji će predmet sa pokretne trake sortirati na prikladno mjesto. Za
svaki dio sustava analizirane su prednosti i nedostaci.

Abstract (english)

Computer and machine vision are becoming one of the most used areas of artificial intelligence
in industry. The fundamental principle of computer vision consists of edge recognition and
contour and shape detection. The aim of this paper is to present the basics of computer vision,
Canny's algorithm for edge recognition, an introduction to microcontrollers and types of
lighting in the application of computer vision. The shape recognition application was made
using the Python programming language and the OpenCV library. The sorting system is
controlled by an Arduino microcontroller. The dome light and camera stand was constructed
using 3D printing technology and aluminum profiles. The system is configured so that the
Python program recognizes the shape and sends it to the Arduino microcontroller, which will
sort the object from the conveyor belt into the appropriate place. Advantages and disadvantages
were analyzed for each part of the system.

• Keywords: Canny algoritam; detekcija kontura; OpenCV; Arduino; servo motori; pokretna traka; serijska komunikacija; nosač za kameru i osvjetljenje; kupolno svjetlo
• Keywords (english): Canny algorithm; contour detection; OpenCV; servo motors; conveyor belt; serial communication; camera and lighting mount; diffuse dome light
• Language: croatian
• URN:NBN: urn:nbn:hr:235:931124
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-02-23 10:14:35