na študijskem programu 2. stopnje Izobraževalno računalništvo
Peter Bernad (Author), Jurij Rakun (Mentor)

Abstract

Avtomatizacija zamudnih procesov je aktualna problematika že stoletja. Človeštvo je vedno poskušalo opraviti delo na čim bolj enostaven in učinkovit način. Z razvojem računalniškega vida je računalništvo v industrijskih panogah izboljšalo nekatere procese na načine, ki so bili prej skorajda nemogoči. V magistrskem delu smo obravnavali uporabo računalniškega vida v agrikulturi in izdelali prototipne multispektralne kamere na osnovi mikroračunalnika Raspberry Pi. Najprej smo pregledali uporabo računalniškega vida nasploh v industrijskih panogah in teoretično pregledali vpliv valovnih dolžin elektromagnetnega valovanja na rastline, da smo lahko določili ustrezno opremo za konstrukcijo multispektralne kamere ter uporabo ustrezne formule za ocenjevanje zdravja rastlin. Po konstrukciji in testiranju multispektralne kamere smo ocenili njeno uporabnost in možno vključitev v šolstvu. Ugotovitve kažejo, da je izdelava cenovno ugodne multispektralne kamere mogoča, vendar prezahtevna na osnovnošolskem nivoju. Uporaba ter analiza podatkov pa bi vsekakor bila ustrezna v sklopu raziskovalne naloge.

Keywords

Multispekralna kamera;računalniški vid;strojni vid;Raspberry Pi;vegetacijski indeks;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FNM - Faculty of Natural Sciences and Mathematics
Publisher: [P. Bernard]
UDC: 004.8(043.2)
COBISS: 87265795 Link will open in a new window
Views: 646
Downloads: 46
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Development of a multispectral camera system based on the Raspberry Pi microcomputer
Secondary abstract: Automation of time-consuming processes has been a challenge for centuries. Mankind has always tried to do work as easy and efficient as possible. With the development of computer vision, computing in industries has improved some processes in ways that were previously almost impossible. In the master's thesis, we discussed the use of computer vision in agriculture and produced prototype multispectral cameras based on the Raspberry Pi microcomputer. We first examined the use of computer vision in general in industries and theoretically examined the influence of electromagnetic waves on plants in order to determine the appropriate equipment for the construction of a multispectral camera and the use of correct formula to determine the plant health. After the construction and testing of the multispectral camera, we assessed its usefulness and possible inclusion in education. The findings show that the production of an affordable multispectral camera is possible, but too demanding at the primary school level. The use and analysis of data would certainly be appropriate as part of the research task.
Secondary keywords: multispectral camera;computer vision;machine vision;Raspberry Pi;vegetation index;Računalništvo;Informacijsko-komunikacijska tehnologija;Računalniški vid;Univerzitetna in visokošolska dela;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za naravoslovje in matematiko, Oddelek za matematiko in računalništvo
Pages: VI f., 43 str.
ID: 13408656