Research on Corner Matching-Based Video Localization by Robots in RoboCup


Article Preview

In this paper, a corner matching-based localization algorithm is brought forward, which refers to doing corner matching every two frames for the video documents generated in the operation of the robot and calculating the corner offset between two frames so as to realize the self-localization of the robot. It turns out in tests that the localization by this algorithm is featured by little error and high robustness



Advanced Materials Research (Volumes 588-589)

Edited by:

Lawrence Lim




B. Z. Deng and Z. Cao, "Research on Corner Matching-Based Video Localization by Robots in RoboCup", Advanced Materials Research, Vols. 588-589, pp. 1560-1564, 2012

Online since:

November 2012




[1] Deng Benzai. Research on Robot's Panoramic Vision-Based Self-Localization Methods [D]. Changsha: Changsha University of Science and Technology (2009).

[2] C. G. Harris, M. J. Stephens. A combined corner and edge detector [A]. Proceedings Fourth Alvey Vision Conference [C]. Manchester, U. K, (1988).


[3] Cheng Dezhi and others. Image Matching Based on Improved SIFT Algorithm [J]. Computer Simulation 2011, (07): 21-24.

[4] Zhang Bianlian. Matching Technology Based on SUSAN Corner Detection [J]. Journal of Xi'an University of Arts: Natural Science Edition 2009, 12 (04): 55-58.

[5] Chen Lijun. Research on Image Corner Detection and Matching Algorithm[D]. Xian: Xi'an Electronic and Science University, 2004, 1(09): 34-37.

[6] Liu Bo and others. Improved Algorithm Based on Obscure Slack Iterative Layered Image [J]. Optical Technique 2009, 35 (1): 131-135.

[7] ZHANG Z Y. A robust technique for matching two uncalibrated images through recovery of the unknown epipolar geometry [R]. Technical Report, INRIA, (1994).