Browse > Article
http://dx.doi.org/10.9728/dcs.2017.18.2.383

Real-time 3D model generation system using multi-view images  

Park, Jeong-Sun (Department of KonanLink, KONAN Technology)
Son, Hyung-Jae (Department of KonanLink, KONAN Technology)
Park, Jeung-Chul (SMEs Support Section, Electronics and Telecommunications Research Institute (ETRI))
Oh, Il-Seok (Division of Computer Science and Engineering, Chonbuk National University)
Publication Information
Journal of Digital Contents Society / v.18, no.2, 2017 , pp. 383-392 More about this Journal
Abstract
This paper introduces a real-time 3D model generation system that can process in real time from multi-view image acquisition to image-based 3D model generation. This system describes how to collect, transmit, and manage the HD images input from 18 cameras and explain the background separation and smooth 3D volume model generation process. This paper proposes a new distributed data transmission and reception method for real-time processing of HD images input from 18 cameras. In addition, we describe a codebook-based background separating algorithm and a modified marching cube algorithm using perspective difference interpolation to generate smooth 3D models from multi-view images. The system is currently being built with a throughput rate of 30 frames per second.
Keywords
Distributed data collection; Background subtraction; 3D modeling; Volume model;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 W. Matusik, C. Buehler, R. Raskar, et al., "Image-based visual hulls," SIGGRAPH '00 Proceedings of the 27th annual conference on Computer graphics and interactive techniques, pp. 369-374, 2000.
2 Y. Ohta, I. Kitahara, Y. Kameda, H. Ishikawa, and T. Koyama, "Live 3D Video in Soccer Stadium," International Journal of Computer Vision, Vol. 75, No. 1, pp. 173-187, 2007.   DOI
3 A. Chapiro, S. Heinzle, et al., "Optimizing Stereo-to-Multiview Conversion for Autostereoscopic Displays," Computer graphics forum, Vol. 33, No. 2, pp. 63-72, May 2014.   DOI
4 Cheon Lee, Yo-Sung Ho, "Depth-tuned Intermediate View Generation for Comfortable 3D Video," 2012 KICS, Vol. 6, pp. 349-350, 2012.
5 Lang, Manuel., et al., "Nonlinear Disparity Mapping for Stereoscopic 3D," ACM Transactions on Graphics (TOG), Vol. 29, Issue 4, Article No. 75, July 2010
6 C.Kim, A. Hornung, S. Heinzle, et al., "Multi-Perspective Stereoscopy from Light Fields," Proceeding SA '11 Proceedings of the 2011 SIGGRAPH Asia Conference, Vol. 30, Issue 6, Article No. 190, December 2011.
7 D. E. C. P. R. Fergus, "Depth map prediction from a single image using a multi-scale deep network," NIPS'14 Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 2366-2374, 2014.
8 P. Gargallo, P. Sturm, "Bayesian 3D modeling from images using multiple depth maps," CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 885-891, 2005.
9 Malvar, Henrique S., Li-wei He, and Ross Cutler, "High-quality linear interpolation for demosaicing of Bayer-patterned color images," Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP'04). IEEE International Conference on., Vol. 3, pp. 482-485, 2004.
10 Jae-young Jung, "Codebook-Based Foreground Extraction Algorithm with Continuous Learning of Background," Journal of Digital Contents Society, Vol. 15, No. 4, pp. 449-455, 2014.   DOI
11 K. Kim, et al., "Background Modeling and Subtraction by Codebook Construction," Image Processing, 2004. ICIP'04. 2004 International Conference on., Vol. 5, pp. 3061-3064, 2004.