Praćenje plovila u radarskim snimkama

master's thesis

• Title (english): Tracking objects in radar images
• Author: Mauro Barešić
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Committee member: Siniša Šegvić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sustavi za detekciju i praćenje plovila koriste se za povećanje sigurnosti plovidbe. Takvi sustavi koriste razne senzore među kojima su optičke kamere, termalne kamere te radarski sustavi. Radarski sustavi koriste specijalizirane algoritme koji estimiraju i predviđaju trajektorije plovila kako bi ih što uspješnije detektirali i pratili. U ovom diplomskom radu implementiran je jedan takav algoritam temeljen na proširenom Kalmanovu filtru. Korišteni model gibanja plovila temeljen je na modelu krivocrtnog gibanja. U radarskim snimkama nalazi se velika prisutnost šuma čiji utjecaj na kvalitetu rada sustava nije zanemariv te se zato koriste algoritmi za obradu binarne slike kako bi se šum umanjio.

Abstract (english)

Vessel detection and tracking systems are used to improve maritime safety. Such systems use a variety of sensors, including optical cameras, thermal imaging and radar systems. Radar systems use specialised algorithms that estimate and predict vessel trajectory to improve detection and tracking. Such algorithm, based on the extended Kalman filter, is implemented in this thesis. Vessel model is based on the curvilinear motion model. There is a large presence of noise in radar images whose effect on the quality of the system is not negligible and, therefore, algorithms for processing the binary image are used in order to minimize the noise.

• Keywords: radar; praćenje plovila; prošireni Kalmanov filtar; estimacija trajektorije; model krivocrtnog gibanja; uspoređivanje s pragom; segmentacija slike; radarska slika
• Keywords (english): radar; vessel tracking; extended Kalman filter; trajectory estimation; curvilinear motion model; thresholding; image segmentation; radar image
• Language: croatian
• URN:NBN: urn:nbn:hr:168:378634
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 07:44:27