虚拟现实投影匹配的单幅图像卡车体积测量

李鹏慧; 孙伟; 李大健; 贾伟; 刘宏娟

doi:10.3788/OPE.20152313.0669

您当前的位置：

首页 >

文章列表页 >

虚拟现实投影匹配的单幅图像卡车体积测量

更新时间：2020-08-13

- 虚拟现实投影匹配的单幅图像卡车体积测量
- Measurement of truck volume by virtual reality projection matching
- 光学精密工程 2015年23卷第10z期页码：668-675
- 作者机构：
  
  1. 西安电子科技大学空间科学与技术学院,陕西西安,710118
  2. 西北工业大学第365研究所, 陕西西安 710065
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61201290)();教育部直属高校基本科研业务费专项资金资助项目(No.JB141307)()
- DOI：10.3788/OPE.20152313.0669
  中图分类号： TB92;TP391.4
- 收稿日期：2015-06-05，
  
  修回日期：2015-06-21，
  
  纸质出版日期：2015-11-14
- 稿件说明：
移动端阅览
李鹏慧, 孙伟, 李大健等. 虚拟现实投影匹配的单幅图像卡车体积测量[J]. 光学精密工程, 2015,23(10z): 668-675

LI Peng-hui, SUN Wei, LI Da-jian etc. Measurement of truck volume by virtual reality projection matching[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 668-675
李鹏慧, 孙伟, 李大健等. 虚拟现实投影匹配的单幅图像卡车体积测量[J]. 光学精密工程, 2015,23(10z): 668-675 DOI： 10.3788/OPE.20152313.0669.

LI Peng-hui, SUN Wei, LI Da-jian etc. Measurement of truck volume by virtual reality projection matching[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 668-675 DOI： 10.3788/OPE.20152313.0669.

摘要

提出了一种单幅图像自动卡车体积测量方法

以降低卡车车厢体积的测量成本。该方法使用主动开关模型(ASM)算法定位目标特征点;利用卡车3D模型和相机的内部参数计算被测卡车所在地平面并建立目标成像的虚拟现实环境。然后

利用EPnP算法求解目标模型的初始位姿

并通过几何校正算法使卡车3D模型投影与被测卡车自动匹配。在地面方程和投影控制点匹配的约束下

本方法提出的虚拟现实环境中的卡车3D模型与被测卡车相同。最后

通过计算3D模型的体积得到了被测卡车的体积。实验结果表明:该方法通过单幅卡车图像即可自动测量出卡车的体积

系统结构简单

具有良好的实时性和可操作性

卡车车厢体积测量值和真实值的误差小于5%

很有实用价值。

Abstract

An automatic measurement method by using a single image is presented based on image processing to reduce the cost of truck's box volume measurement. The method locates feature points of a target with an Active Shape Model(ASM) algorithm and calculates the ground surface that the truck is placed and establishes virtual reality environments by using the camera's intrinsic parameters and a 3D model. Then

the truck's initial pose is estimated with EPnP algorithm

and a geometry correction algorithm is used to correct the geometry of the 3D model to match the truck automatically. Under the constraints of ground surface's equations and control points

the 3D model in a virtual reality enviroment is the same as the real truck. Finally

the truck's box volumes is figured out by calculating the 3D model's box volume. Experiment results show that the proposed method can measure the volume of the truck's box automatically with a single truck image and the error of truck's box volume is within 5%. The measuring system is simple

and has good real-time performance and important practical values.

关键词

Keywords

references

XU C, HE Y, KHANNA N, et al.. Model-based food volume estimation using 3D pose[C]. 2013 20th IEEE International Conference on Image Processing(ICIP2013), 2013:2534-2538.

CASTILLO-CASTANEDA E, TURCHIULI C. Volume estimation of small particles using three-dimensional reconstruction from multiple views[J]. Lecture Notes in Computer Science, 2008:218-225.

WEI Z, DING B, WANG W. Modifications in SIFT-based 3D reconstruction from image sequence[C]. International Society for Optics and Photonics, 2014:93010A-93010A-10.

KEMPKES M, VETTER T, MAZZOTTI M. Measurement of 3D particle size distributions by stereoscopic imaging[J]. Chemical Engineering Science, 2010,65(4):1362-1373.

WANG C, HAN Y. Design of dynamic volume measure system based on binocular vision[C]. IEEE, 2010:V10-289-V10-293.

WU L, WU B. Research on estimation of trees crown volume by 3D laser scanning system[J]. International Conference on Computer Distributed Control & Intelligent Environmental Monitoring, 2011:265-268.

FURUKAWA Y, PONCE J. Accurate, dense and robust multi-view stereopsis[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007,32(8):1362-1376.

SAKAI S, ITO K, AOKI T, et al.. An efficient image matching method for multi-view stereo[J]. Lecture Notes in Computer Science, 2013.

ZHANG Z, YANG Y, YUE Y, et al.. Food volume estimation from a single image using virtual reality technology[J]. IEEE Annual Northeast Bioengineering Conference, 2011:1-2.

BURDEA G. Virtual reality technology an introduction[C]. IEEE Computer Society, 2005:307.

SUN W, SUN N, GUO B, et al.. An auxiliary gaze point estimation method based on facial normal[J]. Formal Pattern Analysis & Applications, 2014.

COOTES T F, Taylor C J, Cooper D H, et al.. Active shape models-their training and application[J]. Computer Vision & Image Understanding, 1995,61(1):38-59.

WANG W,SHAN S G, GAO W, et al.. An improved active shape model for face alignment[C]. Fourth IEEE International Conference on Multimodal Interfaces, Processings, IEEE, 2002:523-528.

IGUAL L, Perez-Sala X, ESCALERA S, et al.. Continuous generalized procrustes analysis[J]. Pattern Recognition, 2014,47(2):659-671.

NEALEN A, SORKINO O. A sketch-based interface for detail-preserving mesh editing[J]. Acm Transactions on Graphics, 2005, 24(3):págs. 1142-1147.

ALEXA O S M. As-rigid-as-possible surface modeling[J]. Eurographics Symposium on Geometry Processing, 2007.

KHOLGADE N, SIMON T, EFROS A, et al.. 3D object manipulation in a single photograph using stock 3D models[J]. ACM Transactions on Graphics(TOG), 2014,33(4):127.

LEPETIT V, MORENO-NOGUER F, FUA P. EPnP:An accurate O(n) solution to the PnP problem[J]. International Journal of Computer Vision, 2009,81(2):155-166.

SCHAEFER S, MCPHAIL T, WARREN J. Image deformation using moving least squares[J]. Acm Transactions on Graphics, 2006,25(3):533-540.

浏览量

358

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

圆投影及消失点约束下的卡车厢体体积测量

基于机器视觉的透明软管内微量液体体积测量

虚拟现实中视觉诱发晕动症时空多特征评价

大型散货堆体积的快速测量

高精度光学头部位置定位系统