Title :
Fast Depth Estimation Method from a Pair of Retified Images
Author :
Fang-Hsuan Cheng ; Tzu-Hao Kuo ; Yea-shuan Huang
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Chung Hua Univ., Hsinchu, Taiwan
Abstract :
This paper proposes a line segment method to estimate the depth information from a pair of rectified images. The proposed method can achieve real-time and high quality stereo-matching. We first use a simple edge detection to find out the line segments in the reference image and then calculate the color difference of each line segment from a pair of rectified images. Finally, the minimum difference of each line segment is found out as the corresponding points. Unfortunately the line segments matching method is susceptible to cause error in occluded areas, so three methods are developed to refine the depth map. From the experiments, it is proved that the proposed method can accurately estimate the depth information in real-time.
Keywords :
edge detection; estimation theory; image matching; image segmentation; edge detection; fast depth estimation method; high quality stereo matching; line segment matching method; retified images; Belief propagation; Computer vision; Dynamic programming; Image color analysis; Image edge detection; Image segmentation; Stereo vision; depth information; occluded area; stereo matching;
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012 Eighth International Conference on
Conference_Location :
Piraeus
Print_ISBN :
978-1-4673-1741-2
DOI :
10.1109/IIH-MSP.2012.97