基于稀疏特征点的单视点深度图像校准

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 191-195.

基于稀疏特征点的单视点深度图像校准

郭庆慧,梁秀霞,张锐

山东财经大学计算机科学技术学院济南250014 山东省数字媒体技术重点实验室济南250014;山东财经大学计算机科学技术学院济南250014 山东省数字媒体技术重点实验室济南250014;山东财经大学计算机科学技术学院济南250014 山东省数字媒体技术重点实验室济南250014

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61020106001,61272431,61103117,61202364),教育部人文社会科学研究项目(13YJC860023),中青年科学家奖励基金(BS2011DX024,BS2012DX028)资助

Calibration for Single Viewpoint Depth Image Based on Sparse Feature Points

GUO Qing-hui,LIANG Xiu-xia and ZHANG Rui

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 高效而精确的校准是基于深度图像三维重建的关键问题。针对Kinect摄像头获得同步的彩色图像和深度图像,提出基于稀疏特征点的校准方法。将其中的彩色图像作为参考图像,根据深度图像和彩色图像的几何对应关系计算相应矩阵转换参数,然后利用稀疏特征点对确定校准参数,由此得到彩色图像和深度图像间的映射关系,最后实现深度信息的校准。实验结果表明,深度图像相对彩色图像的变换近似满足线性关系,计算复杂度低,精确度高,易于实现,适合在相关领域中得到进一步推广。

关键词: 深度图像,图像校准,稀疏特征点,特征点匹配,机器视觉中图法分类号TP37文献标识码A

Abstract: Efficient and accurate calibration is the key issue for 3D model reconstruction based on the depth image．Based on the synchronous color image and depth image obtained from the Kinect camera,a calibration method based on the sparse feature point was presented．We took the color image as a reference image,used the geometric relation between the depth image and the color image to calculate the corresponding matrix transformation parameters．Then we extracted corresponding sparse feature points of the two types of data to determine the calibration parameters,and thus obtain a mapping relationship between the two data．Finally,we achieved the calibration of depth information according to the determined parameters．The results show that the relative transformation between the depth image and the color image meets a linear approximation conversion．This method has low computational complexity,high accuracy and easy to realize．So it is suitable for further promotion in related fields.

Key words: Depth image,Image calibration,Sparse feature points,Feature points matching,Machine vision

郭庆慧,梁秀霞,张锐. 基于稀疏特征点的单视点深度图像校准[J]. 计算机科学, 2014, 41(Z6): 191-195. https://doi.org/

GUO Qing-hui,LIANG Xiu-xia and ZHANG Rui. Calibration for Single Viewpoint Depth Image Based on Sparse Feature Points[J]. Computer Science, 2014, 41(Z6): 191-195. https://doi.org/

参考文献

[1] 向学勤,潘志庚,童晶．Depth camera in computer vision and computer graphics:An overview[J]．Journal of Frontiers of Computer Science and Technology,2011,33(6):5-16
[2] Fusiello A E,Trucco A V．Rectification with unconstrained ster-eo geometry[C]∥Proceedings of the British Machine Vision Conference．University of Essex,UK,1997:400-409
[3] Fusiello A E,Trucco A V．A compact algorithm forrectification of stereo pairs[J]．Machine Vision and Application,2000,22(12):16-12
[4] 郭永刚,葛庆平,冯平,等．一种基于控制点自动提取的图像畸变校正算法[J]．计算机工程与应用,2007,43(2):214-216
[5] 刘军,胡振伟,张达,等.基于控制点鲁棒提取的视觉成像畸变校准方法[J]．东北大学学报:自然科学版,2011,31(3):331-333
[6] 赵小川,罗庆生,韩宝玲.四边形分片逼近控制点的图像畸变校正算法[J].光电工程,2009,36(5):78-81
[7] 刘堂友,董爱华.精确校正图像的径向畸变和倾斜失真[J].中国图象图形学报,2007,12(10):1935-1938
[8] 李久芳．基于标准棋盘格的图像校准方法[J].电子工业专用设备,2010,190:4-6
[9] 林明汉,胡贤龙.大视场CMOS相机图像的畸变校正[J]．科学技术与工程,2009,9(18):1671-1819
[10] Kang Y-S,Ho Y-S．Efficient stereo image rectification method using horizontal baseline[M]．sdvances in image and video technology,Springer Berlin Heidelberg,2012:301-310
[11] Sun Chang-ming．Uncalibrated three-view imagerectification[J]．Image and Vision Computing,2003,21(3):259-269
[12] Khosravani A,Lingenfelder M,Wenzel K,et al．Co-registration of Kinect point clouds based on image and object space obervations．http://www.ifp.uni_stuttgart.delpublications/2012/LC3D-2012-khosraianiEtAl.pdf
[13] Henry P,Krainin M,Herbst E．XiaofengRen,Dieter Fox．RGB-D mapping:Using Kinect-style depth cameras for dense 3D mo-deling of indoor environments[J]．The International Journal of Robotics Research,2012,31(5):647-663
[14] 王学伟,徐庆九,葛先军.红外光学系统几何畸变效应模拟[J].激光与红外,2012,42(5):544-546
[15] 苏晋.摄像机标定方法研究[D]．沈阳:东北大学,2010:7-14
[16] 徐丽燕,王静,邱军,等.基于特征点的多光谱遥感图像配准[J].计算机科学,2011,8(7):280-282
[17] 王权岱.压印对正系统中标记图像儿何畸变的校正[J].光学精密工程,2007,15(3):422-427

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed