Analiza prometnih scena iz infracrvenih video snimki

undergraduate thesis

• Title (english): Traffic scene analysis from infrared video
• Author: Marko Mijatović
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Committee member: Pavle Prentašić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisan je postupak detektiranja objekata iz infracrvenih video snimki. Postupak detekcije odvija se u dvije faze. Prva faza detekcije orjentirana je na analizu zasebnog vremenskog okvira video snimke, s ciljem izdvajanja objekata od okoline. Izdvajanje objekata postiže se analizom temperaturne razlike između objekata od interesa i okoline. U drugoj fazi rada, fokus je na detekciji objekata u pokretu, kako su upravo objekti koji se kreću sudionici u prometu. Praćenje pokreta postiže se analizom niza vremenskih okvira, te primjenom Kalmanova filtera, za procjenu sljedeće pozicije objekta.

Implementirano je programsko rješenje u radnom okruženju Matlab. Korištene su brojne implementirane funkcije Matlab-ova "Image processing toolbox-a". Uz kratak osvrt na sam program, ujedno su i opisani rezultati detekcije.

Abstract (english)

This paper describes the object detection tehnique from infrared video footage. Procedure of detection is divided in to two phases. The first phase of detection is oriented on analysis of a single frame of the footage, with intention of extracting the object from the background. Object extraction is accomplished by analysing temperature difference between the object of interes and the background. In the second phase of work, focus is mainly on objects in motion, as moving objects are primarily associated with traffic. Motion detection is accomplished by analysing a sequence of frames and applying Kalman filter for estimation of next location of the object.

Program solution is implemented in Matlab workspaces. For motion detection and image analysis, a number of implemented functions from "Matlab Image Processing Toolbox" were used. Besides a review of the program solution, there are descriptions of computed results.

• Keywords: obrada infracrvenih snimki; detekcija objekata u pokretu; Kalmanov filter; Matlab
• Keywords (english): analysis of infrared footage; motion detection; Kalman filter; Matlab
• Language: croatian
• URN:NBN: urn:nbn:hr:168:420625
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-05 17:45:38