Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (11): 2061-2067    DOI: 10.3785/j.issn.1008-973X.2012.11.018
    
A three-dimensional reconstruction algorithm for complex
background image and its medical applications
LAI Xiao-bo1, ZHU Shi-qiang2, FANG Chun-jie1
1. College of Information Technology, Zhejiang Chinese Medical University, Hangzhou 310053, China;
2. State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

 Aiming at the problem that the vast majority of three-dimensional reconstruction algorithms under complex background have low reliability and weak robustness, a three-dimensional reconstruction algorithm suitable for complex background is proposed. General framework in three-dimensional reconstruction calculation of  spatial points was investigated, and  specific implementation procedures were analyzed. To improve the reliability and robustness of  three-dimensional reconstruction under complex background, the confidence filter,  leftright filter and  uniqueness filter were adopted to eliminate the false matching points for the textureless regions or low texture regions,  occluded regions and  depth discontinuity regions in initial disparity map, respectively. Spatial points-three-dimensional reconstruction of the filtered dense disparity map was implemented, the depth information of the image points under complex background was obtained. The experiment results show that the proposed method is efficient and has strong robustness, satisfactory three-dimensional reconstruction accuracy also can be obtained even if the image background conditions change dynamically and it can provide reliable depth information for computer assisted surgery diagnostic system．

Published: 11 December 2012
CLC:  TP 751.1  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LAI Xiao-bo, ZHU Shi-qiang, FANG Chun-jie. A three-dimensional reconstruction algorithm for complex
background image and its medical applications. J4, 2012, 46(11): 2061-2067.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2012.11.018     OR     http://www.zjujournals.com/eng/Y2012/V46/I11/2061


一种复杂背景图像三维重建算法及其医学应用

针对复杂背景下绝大多数三维重建算法的可靠性不高和鲁棒性不强的问题,提出一种适合复杂背景图像的三维重建算法.研究空间点三维重建计算的一般性框架,并分析具体的实现过程；为了提高复杂背景下三维重建的可靠性和鲁棒性,对初始视差图中的无纹理或低纹理区域、遮挡区域和深度不连续区域分别运用置信滤波器、左右一致性滤波器和唯一性滤波器进行预处理,剔除伪匹配点；将滤波后的致密视差图进行空间点的三维重建,得到复杂背景图像点的深度信息.实验结果表明,该算法计算效率高,具有很强的稳健性,即使图像背景条件发生动态变化也能够获得满意的三维重建精度,能够为计算机辅助外科诊断系统提供可靠的深度信息.

［1］ CHUCK T, MARTIAL H, TAKEO K, et al.Toward autonomous driving: The CMU navlab. part II: system and architecture ［J］. IEEE Expert, 1991, 6(4): 44-52．
［2］ SHOEMAKER C M, BOMSTEIN J A. The Demo III UGV program: a testbed for autonomous navigation research ［C］ ∥Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation. Gaithersburg, MD, USA： IEEE, 1998: 644-651．
［3］ 郑军, 诸静. 基于自适应遗传算法的图像匹配［J］. 浙江大学学报: 工学版, 2003, 37(6): 689-692．
ZHENG Jun, ZHU Jing. Image match based on adaptive genetic algorithm ［J］. Journal of Zhejiang University: Engineering Science, 2003, 37(6): 689-692．
［4］ PARK J S. Interactive 3D reconstruction from multiple images: a primitivebased approach ［J］. Pattern Recognition Letters, 2005, 26(16): 2558-2571．
［5］ 王炜强, 徐进, 杜歆, 等. 基于宽基线立体视觉的远距离三维重建［J］. 浙江大学学报: 工学版, 2010, 44(6): 1073-1078．
WANG Weiqiang, XU Jin, DU Xin, et al. Long range 3D reconstruction based on widebaseline stereo vision［J］. Journal of Zhejiang University: Engineering Science, 2010, 44(6): 1073-1078．
［6］ 刘钢, 彭群生, 鲍虎军.基于图像建模技术研究综述与展望［J］.计算机辅助设计与图形学学报, 2005, 17(1): 18-24．
LIU G, ,PENG Q S, BAO H J. Review and prospect of imagebased modeling techniques［J］. Journal of ComputerAided Design & Computer Graphics, 2005, 17(1): 18-24．
［7］ 蓝章礼, 曹建秋, 梁爽. 复杂背景下视频序列中的人脸定位方法［J］. 计算机科学, 2008, 35(5): 255-257．
LAN Z L, CAO J Q, LIANG S. Face location algorithm in video sequences with complex background［J］. Computer Science, 2008, 35(5): 255-257．
［8］ MAO G Z, WU Y L, HOR M K, et al. Realtime hand detection and tracking against complex background［C］∥ International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Washington, DC, USA, IEEE Computer Society, 2009: 905-908．
［9］ VIOLA P, JONES M.Robust realtime object detection［J］. International Journal of Computer Vision, 2002, 57(2): 137-154．
［10］ GE X W, CUI Y P. Edge detection and target recognition from complex background ［C］∥ International Conference on Advanced Computer Control. Shenyang:IEEE, 2010: 441-444．
［11］ LI L, HUANG W, IRENE Y H, et al.Foreground object detection from videos containing complex background ［C］∥ Proceedings of the 11th ACM International Conference on Multimedia. NewYork, USA, IEEE, 2003: 2-10．
［12］ LONGUET H C. A computer algorithm for reconstructing a scene from two projections［J］. Nature, 1981, 293(10): 133-135．
［13］ 赖小波, 朱世强, 曹新星. 基于OpenCV的焊缝跟踪系统中摄像机标定方法［J］. 焊接学报, 2010, 31(7): 75-78．
LAI Xiaobo, ZHU Shiqiang, CAO Xinxing. OpenCV based camera calibration methods for seam tracking systems ［J］. Transactions of the China Welding Institution, 2010, 31(7): 75-78．
[1] LI Xiao-run, ZHU Jie-er, WANG Jing, ZHAO Liao-ying. Hyperspectral image classification based on compsite kernels support vector machine[J]. J4, 2013, 47(8): 1403-1410.
[2] MA Li-gang, ZHANG Le-ping, DENG Jing-song, WANG Ya-jie, WANG Ke. Land use classification using ZY1-“02C” remote sensing images[J]. J4, 2013, 47(8): 1508-1516.
[3] CHE Hong-kun, LV Fu-zai, XIANG Zhan-qin. Time-frequency optimal feature extraction method
based on SFFS algorithm for defects recognition[J]. J4, 2011, 45(12): 2235-2239.
[4] HAN Ning, ZHANG Xiu-Yang, WANG Xiao-Meng, CHEN Li-Su, WANG Ke. Identification of distributional information Torreya Grandis Merrlllii
using high resolution imagery[J]. J4, 2010, 44(3): 420-425.