The Performance of Presented Subpixel Corner Detection Approach in Context of Camera Stereo Pair Displacement Determination

This paper deals with the comparison of the presented approach to the another subpixel corner detectors. The our proposed and considered detection method uses the regular cornerness map obtained from the usual corner detectors as initial step. The main idea is to use the cornerness values from a neighboring area around found corner point as a 3D profile object and to find the coordinates of its centroid. As the subject of this comparison the determination procedure of the mutual displacement between two corresponding cameras using image stereo pair and prior information coming from camera calibration was used. This whole process of distance estimation consists of multiple steps which are also briefly explained on the next pages. The all results were statistically analyzed, listed in a table and turned into specific findings and conclusions. Keywords-subpixel corner detection; cornerness map; image stereo pair; 3D reconstruction

[1]  Wei Wang,et al.  A SVD decomposition of essential matrix with eight solutions for the relative positions of two perspective cameras , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Daniel Oram.  Rectification for any epipolar geometry , 2001, BMVC.

[3]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[4]  Weixing Zhu,et al.  A Fast and Accurate Algorithm for Chessboard Corner Detection , 2009, 2009 2nd International Congress on Image and Signal Processing.

[5]  Michael Lamperth,et al.  Sub-pixel localisation of passive micro-coil fiducial markers in interventional MRI , 2009, Magnetic Resonance Materials in Physics, Biology and Medicine.

[6]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[7]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[9]  Duane C. Brown,et al.  Close-Range Camera Calibration , 1971 .

[10]  Lukas Sroba,et al.  A New Approach to Obtain Corner Point Coordinates in Subpixel Accuracy , 2016 .

[11]  Yujing Qiao,et al.  Improved Harris sub-pixel corner detection algorithm for chessboard image , 2013, Proceedings of 2013 2nd International Conference on Measurement, Information and Control.

[12]  Dean Brown,et al.  Decentering distortion of lenses , 1966 .

[13]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .