Abstract—This paper presents an aligned epipolar line for stereo images with analysis of multiple size region of interest in selected area or segment of depth maps in application of computer vision. Epipolar line works as a reference line for two same views of images during the process of pixel matching. Then the depth maps (disparity mapping) could be produced with almost similar position to each other. The mapping is about to deal with the intensities of pixels which allocate the depths of an image and can be extracted to get the distance values. This region is a reference view of the stereo camera and stereo vision baseline is based on horizontal configuration. The block matching technique is briefly described with the performance of its output. The disparity mapping is generated by the algorithm with the reference to the left image coordinate. The algorithm uses Sum of Absolute Differences (SAD) which is developed using Matlab software. The rectification and block matching processes are also briefly described in this paper.
Index Terms—Stereo camera; disparity mapping; region of interest; rectification; block matching algorithm
R. A. Hamzah is with UTeM, Malaysia, e-mail: rostamaffendi@utem.edu.my).
M. S. Hamid is with UTeM, Malaysia, e-mail: mohdsaad@utem.edu.my).
H. N. Rosly is with UTeM, Malaysia, e-mail: hasrul@utem.edu.my).
N. M.Z. Hashim is with UTeM, Malaysia, e-mail: nikzarifie@utem.edu.my).
Z. A. F. M. Napiah is with UTeM, Malaysia, e-mail: zulatfyi@utem.edu.my).
Cite: R. A. Hamzah, M. S. Hamid, H. N. Rosly, N. M. Z. Hashim and Z. A. F. M. Napiah, "An Aligned Epipolar Line for Stereo Images with Multiple Sizes ROI in Depth Maps for Computer Vision Application," International Journal of Information and Education Technology vol. 1, no. 1, pp. 15-19, 2011.