prikaz prve stranice dokumenta Usporedba metoda za kalibraciju kamera
  Download
PDF 2.16 MB
undergraduate thesis
Usporedba metoda za kalibraciju kamera
Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. urn:nbn:hr:126:447780
Šarlija, Dino
Josip Juraj Strossmayer University of Osijek
Department of Mathematics
Chair of Applied Mathematics and Computer Science
Computer Science and Machine Learning Research Group

Institutional repository: Repository of School of Applied Mathematics and Computer Science

Cite this document

Šarlija, D. (2020). Usporedba metoda za kalibraciju kamera (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:447780

Šarlija, Dino. "Usporedba metoda za kalibraciju kamera." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:447780

Šarlija, Dino. "Usporedba metoda za kalibraciju kamera." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:447780

Šarlija, D. (2020). 'Usporedba metoda za kalibraciju kamera', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 04 August 2024, https://urn.nsk.hr/urn:nbn:hr:126:447780

Šarlija D. Usporedba metoda za kalibraciju kamera [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2020 [cited 2024 August 04] Available at: https://urn.nsk.hr/urn:nbn:hr:126:447780

D. Šarlija, "Usporedba metoda za kalibraciju kamera", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:126:447780

Metadata
TitleUsporedba metoda za kalibraciju kamera
Title (english)Comparison of Camera Calibration Methods
AuthorDino Šarlija
MentorDomagoj Matijević (mentor)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
(Chair of Applied Mathematics and Computer Science)
(Computer Science and Machine Learning Research Group)
Osijek
Defense date and country2020-09-29, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Mathematical Logic and Accounting
Abstract
Problem kalibracije tj. određivanje parametara kamere iz slika gotovo je nezaobilazan korak u primjeni računalnog vida. U ovome radu prikazane su 3 najčešće korištene različite metode kalibracije kamere, a to su direktna linearna transformacija (DLT), Tsai-eva te Zhangova metoda. Svaka od metoda je detaljno opisana u okviru projekcijskog modela kamere uz parametre potrebne za kalibraciju. Metode su testirane na skupu slika pripremljenih za test, a rezultati su međusobno uspoređeni. Rezultati pokazuju da je Tsai-eva metoda najbolja kod slika sa značajnom radijalnom distorzijom, dok je Zhangova metoda najtočnija kod upotrebe vise slika, a DLT metoda je općenito najbrža. Sve tri metode daju solidne rezultate, a izbor metode koja će se koristiti u određenoj primjeni ovisi o broju dostupnih slika za kalibraciju te potrebnoj brzini izvođenja.
Abstract (english)
The problem of calibration i.e. determining the camera parameters from the images, is an almost unavoidable step in the application of computer vision. In this paper, 3 most commonly used different methods for camera calibration are presented, namely direct linear transformation (DLT), Tsai’s and Zhang’s method. Each of the methods is described in detail within the projection model of the camera with the parameters required for calibration. The methods were tested on a set of images prepared for the test, and the results were compared with each other. The results show that the Tsai method is best for images with significant radial distortion, while the Zhang method is most accurate when using multiple images, and the DLT method is generally the fastest. All three methods give solid results and the choice of method which will be used in a particular application depends on the number of images available to calibrate and the required execution speed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:447780
Study programmeTitle: Bachelor of Mathematics and Computer Science
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-11-02 07:37:36