Abstract—In this paper, we propose the method extracts regions with excessive disparities in 3D stereoscopic images using block based disparity calculation for fatigue evaluation. The proposed method calculates the disparity-map using not pixel based method but block based method. The disparity-map’s resolution is decreased in proportion to block size. In the proposed method, first, the disparity-map is calculated based on BMA (block matching algorithm). The normalized cross-correlation is used as the cost function. The excessive disparity regions are extracted using the automatically decided threshold with Otsu algorithm in the disparity-map. Next, to eliminate the small regions, the extracted regions are post processed by morphological filter, erosion and dilation. The sum of the disparities in the object regions which is normalized with image size is used as parameter in fatigue evaluation model. To extract the exact object, the object regions will be segmented in 3D stereoscopic left image using region growing.
Index Terms—Block based, Otsu threshold, 3D stereoscopic images, discomfort and fatigue.
S. H. Kim is with the Department of Computer Engineering of the University of Young-San at Yangsan, Kyungnam, Korea (e-mail: ksh50@ysu.ac.kr).
J. Y. Kim is with the School of Undeclared Majors, University Collage of the University of Young-San at Busan, Korea (e-mail: neocopy@ysu.ac.kr).
G. J. So is with the Department of Cyber & Police Science of the University of Young-San at Yangsan, Kyungnam, Korea (e-mail: kjso@ysu.ac.kr).
[PDF]
Cite:Sang Hyun Kim, Jeong Yeop Kim, and Gil Ja So, "Extraction of Region with Excessive Disparities Using Block Based Disparity Calculation," International Journal of Computer Theory and Engineering vol. 8, no. 4, pp. 343-349, 2016.