ANALYSIS OF EFFICIENCY OF USE OF HARRIS AND KANADE–LUCAS–TOMASI DETECTORS FOR VISUAL NAVIGATION TASKS
DOI:
https://doi.org/10.18372/2306-1472.64.9047Keywords:
Direct Linear Transformation (DLT) method, Harris detector, homography matrix, Kanade–Lucas– Tomasi (KLT) feature tracker, Speed-Up Robust Feature (SURF)Abstract
The article examines methods of images analysis based on computer vision. We made a comparison between the detectors of feature points determined by Harris and Kanade–Lucas–Tomasi (KLT) methods. Found points are represented by Speed-Up Robust Feature (SURF) descriptor and then used to determine homography matrix. Analyses of accuracy of visual navigation is done by estimation of a camera rotation angle via factorization of homography matrix obtained from two detector methods. Errors of visual navigation follow the normal distribution for the given sample.References
Kusainov A. A. Development of control system unmanned aerial vehicle along a predetermined path. – Novosibirsk, 2013. – 60 p.
Hartley R., Zisserman A. Multiple view geometry in computer vision. – Australian National University, Canberra, Australia. – Cambridge University Press 2000, 2003. – 673 p.
Svoboda T. Kanade–Lucas–Tomasi Tracking (KLT tracker). – Czech Technical University, Prague. – 2008.–29 p.
Faugeras O. Three-Dimensional Computer Vision: A Geometric Approach, MIT Press, 1996, pp. 33- 68
Herbert Bay, Tinne Tuytelaars, Luc Van Gool. SURF: Speeded Up Robust Features. – Katholieke Universiteit Leuven. – 2007. –13 p.
Conte G., Doherty P. A visual navigation system for UAS based on geo-referenced imagery. – Linkoping University, SWEDEN, 2011. – 6 p.
Karpov D.P. Cross-linking of images obtained as a result of aerial photography. – St. Petersburg National Research University, Information Technologies, Mechanics and Optics
Faculty of Information Technology and Software Engineering. Department of Computer Technology. – 2010. – 25 p.
Zuliani M. RANSAC for Dummies (With examples using the RANSAC toolbox for Matlab). Los Gatos, CA – 2012. – 101 p.
Tsai R.Y. A Versatile Camera Calibration Technique for 3D Machine Vision, IEEE J. Robotics & Automation, RA-3, No. 4, August 1987, 334 p.
Szeliski R. Computer vision: algorithms and applications. – 2010. – 979 p.
Zolotukhin D.A. Using MATLAB for prototyping stage of the algorithm three-dimensional reconstruction of micro-objects. - National Research Nuclear University, Moscow Engineering Physics Institute, Moscow. – 2012. – 3 p.
