Statistička procjena površine objekta iz snimke s aditivnom greškom

Taler, Petar

doctoral thesis

Statistička procjena površine objekta iz snimke s aditivnom greškom

Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. urn:nbn:hr:200:657972

Taler, Petar

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

APA 6th Edition

Taler, P. (2019). Statistička procjena površine objekta iz snimke s aditivnom greškom (Doctoral thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:657972

MLA 8th Edition

Taler, Petar. "Statistička procjena površine objekta iz snimke s aditivnom greškom." Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:657972

Chicago 17th Edition

Harvard

Taler, P. (2019). 'Statistička procjena površine objekta iz snimke s aditivnom greškom', Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 14 September 2024, https://urn.nsk.hr/urn:nbn:hr:200:657972

Vancouver

Taler P. Statistička procjena površine objekta iz snimke s aditivnom greškom [Doctoral thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2024 September 14] Available at: https://urn.nsk.hr/urn:nbn:hr:200:657972

IEEE

P. Taler, "Statistička procjena površine objekta iz snimke s aditivnom greškom", Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:657972

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:657972

Please login to the repository to save this object to your list.

Metadata

Title	Statistička procjena površine objekta iz snimke s aditivnom greškom
Title (english)	Statistical estimation of the surface of an object from a snapshot with additive error
Author	Petar Taler
Mentor	Emmanuel Karlo Nyarko (mentor)
Committee member	Mirta Benšić (predsjednik povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Computer Engineering and Automation) (Chair of Automation and Robotics) Osijek
Defense date and country	2019-05-20, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Electrical Engineering Automation and Robotics
Universal decimal classification (UDC)	621.3 - Electrical engineering
Abstract	Detekcija kružnog ili elipsoidnog objekta snimljenog na slici aktualan je problem u segmentu računalnog vida. U literaturi je predstavljeno nekoliko metoda koje se bave tim problemom, no pokazalo se da one ne daju zadovoljavajuće rezultate kod slika na kojima je prisutan šum. U sklopu istraživanja predstavljenog u ovom radu primijenjen je statistički model za procjenu širine uniformne distribucije za podatke zagađene aditivnom greškom kako bi se spomenutom problemu pristupilo na inovativan način. Inicijalno je razvijena metoda za procjenu duljine presjeka objekta s proizvoljnim pravcem. Njezinim je korištenjem moguće procijeniti skup rubnih točaka kružnog ili elipsoidnog objekta na slici. U taj se skup točaka potom optimalno smješta kružnica ili elipsa te izračuna njezina površina - aproksimacija površine samoga objekta. Moguće je također procijeniti i površinu kružnog ili elipsoidnog objekta predstavljenog numerički skupom točaka u ravnini. Predstavljena metoda je implementirana i javno objavljena kao paket za programski jezik R. Izvršeno je njezino opsežno testiranje na problemu procjene površine objekata snimljenih RGB-D kamerom. Snimkama s kamere je dodavana različita količina šuma, te su rezultati procjene površine uspoređeni s dobivenima od ranije poznatih metoda. Analiza rezultata testiranja pokazala je da ovdje predstavljena metoda daje kvalitativno najbolje rezultate procjene površine objekata snimljenih na slikama sa šumom.
Abstract (english)	Detection of circular or ellipsoidal object on an image is a current issue in computer vision. Several methods that address this problem have been previously presented, but it turned out that they do not give satisfactory results when dealing with noisy images. As part of the research presented in this paper, a statistical model for estimating the width of uniform distribution for data contaminated with additive error was applied in order to approach mentioned problem in an innovative manner. Initially, a method for length estimation of intersection of the object with an arbitrary line has been developed. It is possible to estimate the set of edge points of the circular or ellipsoidal object by using this method. Further, a circle or an ellipse is fitted in that set of points, and its area is calculated, which approximates the area of on object itself. It is also possible to estimate the area of a circular or ellipsoidal object represented by a set of numerical points in the plane. The presented method was implemented and publicly released as a package for the programming language R. The method has been extensively tested on the problem of estimating the area of objects recorded using RGB-D camera. Different noise levels were added to the captured images, and estimation results were compared with the ones obtained by a several established methods. The test results analysis showed that the method presented in this paper gives qualitatively the best results of area estimation when dealing with noisy images.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:657972
Promotion	2019-06-14
Study programme	Title: Postgraduate doctoral study programme; specializations in: branch Power Engineering and Communications, branch Informatics Course: branch Informatics Study programme type: university Study level: postgraduate Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika (doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Repository	Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Created on	2019-09-03 12:30:07