Obrada slike na ugradbenom sustavu u svrhu analize zamućenosti vode

undergraduate thesis

• Title (english): Image Processing on an Embedded Sydtem for the Purpose of Anayzing Water Turbitdity
• Author: Ana Cej Gagović
• Mentor: Nikola Mišković (mentor)
• Committee member: Nikola Mišković (predsjednik povjerenstva)
• Committee member: Zoran Vukić (član povjerenstva)
• Committee member: Anja Babić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U okviru završnog rada obavljena je osnovna konfiguracija pločice Raspberry Pi te napravljena skripta za obradu slike u svrhu analize zamućenosti vode brojanjem čestica koje plutaju u određenom volumenu vode. Skripta je pisana u programskom jeziku Python korištenjem biblioteke OpenCV. Glavno rješenje problema analize zasniva se primjenom klase „SimpleBlobDetector“ implementirane u OpenCV koja svojim algoritmom detektira i prebrojava plutajuće čestice u vodi. Zbog energetske učinkovitosti, pločica Raspberry Pi ne radi cijelo vrijeme već periodički uzima i obrađuje sliku. Glavni rezultat je postotak zamućenosti. U radu je detaljno opisan postupak obrade slike, podataka i dobivanje rezultata. Naveden je i mogući smjer daljnjeg razvoja postupka obrade podataka primjenom strojnog učenja.

Abstract (english)

In this BSc thesis, a basic configuration of Raspberry Pi has been described and a script for image processing in order to analyze water turbidity by counting the particles that float in a given volume of water, has been made. The script is written in Python using the OpenCV library. The main solution to the problem analysis is based on applying OpenCV class "SimpleBlobDetector" whose algorithm detects and counts particles floating in the water. In order to increase the energy efficiency, Raspberry Pi does not work all the time, but periodically takes and does image processing. The main result is the percentage of pollution. Paper described in detail the procedure of image and data processing and the given results. Here is a possible direction for further development of data processing using machine learning.

• Keywords: Raspberry Pi; obrada slike; zamućenost vode; analiza zamućenosti vode; OpenCV; Python
• Keywords (english): Raspberry Pi; image processing; water turbidity; water turbidity analysis; OpenCV; Python
• Language: croatian
• URN:NBN: urn:nbn:hr:168:869238
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 08:10:13