SD&A 2017: Real time depth estimation method using hybrid camera system

This presentation was delivered at the 28th annual Stereoscopic Displays and Applications conference (30 January – 1 February 2017) held in Burlingame, CA USA.

Title: Real time depth estimation method using hybrid camera system (SD&A-367)

Speaker: Eu-Tteum Baek

Biography: Eu-Tteum Baek received his B.S. degree in computer science and engineering from Chonbuk National University, Korea, in 2012 and M.S. degree in Information and Communication Engineering at the Gwangju Institute of Science and Technology (GIST), Korea, in 2015. He is currently working towards his Ph.D. degree in the Department of Information and Communications at GIST, Korea. His research interests are 3D digital image processing, depth estimation, and realistic broadcasting.

Abstract: In this paper, we present a new real time depth estimation method using stereo color camera and ToF depth sensor. First, we obtain an initial depth information from ToF depth sensor. Exploiting initial depth information to narrow the disparity range by performing 3-D warping from the position of ToF camera to the position of stereo camera due to accelerate the algorithm. We construct cost volume by calculating intensity difference and truncated absolute difference of gradients. After aggregating cost volume, we use an inverse Gaussian weight function to decrease cost near by the initial depth. Experimental results show that the proposed method can represent the disparity detail and improve the quality in the vulnerable areas of stereo matching.

© 2017, Society for Imaging Science and Technology (IS&T).