大尺寸动态视觉测量系统的并行加速

董明利; 许晓臣; 王君; 孙鹏; 燕必希

doi:10.3788/OPE.20152310.2909

您当前的位置：

首页 >

文章列表页 >

大尺寸动态视觉测量系统的并行加速

信息科学 | 更新时间：2020-08-13

- 大尺寸动态视觉测量系统的并行加速
- Parallel acceleration of large scale dynamic vision measurement system
- 光学精密工程 2015年23卷第10期页码：2909-2918
- 作者机构：
  
  1. 北京信息科技大学光电测试技术北京市重点实验室北京,100192
  2. 北京邮电大学信息光子学与光通讯研究院北京,100876
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.51175047, No.51475046)()
- DOI：10.3788/OPE.20152310.2909
  中图分类号： TP391;TP242.6
- 收稿日期：2015-02-10，
  
  修回日期：2015-04-27，
  
  纸质出版日期：2015-10-25
- 稿件说明：
移动端阅览
董明利, 许晓臣, 王君等. 大尺寸动态视觉测量系统的并行加速[J]. 光学精密工程, 2015,23(10): 2909-2918

DONG Ming-li, XU Xiao-chen, WANG Jun etc. Parallel acceleration of large scale dynamic vision measurement system[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10): 2909-2918
董明利, 许晓臣, 王君等. 大尺寸动态视觉测量系统的并行加速[J]. 光学精密工程, 2015,23(10): 2909-2918 DOI： 10.3788/OPE.20152310.2909.

DONG Ming-li, XU Xiao-chen, WANG Jun etc. Parallel acceleration of large scale dynamic vision measurement system[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10): 2909-2918 DOI： 10.3788/OPE.20152310.2909.

摘要

由于现有以大数据量和计算量为基础的大尺寸动态视觉测量系统处理速度较慢

本文建立了一个高速大尺寸动态视觉测量系统

并对该系统涉及的特征点中心定位、编码点识别、相机定向等算法进行了并行化研究。首先

分析了在不同测量条件下各个主要算法的时间消耗情况及每个主要算法的并行性;然后

对常规的特征点中心定位和编码点识别算法做了介绍

分别提出了特征点中心并行快速定位和编码点并行快速识别算法

并详细说明了这两种并行快速算法的实现原理。最后

针对大量原子操作的问题

提出了线程束集体原子操作的优化方法。实验结果表明:在不损失定位精度和识别率的前提下

图像中包含300个点时的并行方案比串行方案的时间开销减少了42%

当点数达到20 000时

时间开销减少91%以上。实验显示提出的并行设计方案有效地提高了处理速度

解决了大尺寸动态视觉测量系统实时性差的问题。

Abstract

As existing large scale dynamic vision measurement systems based on large amount of data processing and computing have a lower data processing speed

a high speed and large scale dynamic vision measurement system was proposed. The parallel optimization techniques involving in the system such as target locating

code detecting

camera orientation and other systematic algorithms were researched. Firstly

time consumptions of corresponding key algorithms under different considerations were analyzed. Then

the traditional target centroid and code detecting algorithms were introduced

their parallelisms were analysis

and the fast target center location algorithm and code recognition algorithm under the general parallel architecture were put forward. Moreover

the implement methods of the two parallel algorithms were explained in detail. Finally

the Warp Atom Operation Optimization (WAOO) method for massive atomic operations was proposed. The experimental results under the same location precision and recognition rate show that the processing time is reduced by 42% and 91% for 300 and 20 000 targets respectively when the parallel algorithm is used to replace the traditional serial algorithm. The algorithms proposed in this paper are verified effective in accelerating the processing speed and improving the real-time problem in large scale vision measurement systems.

关键词

Keywords

references

陈竹梅,平丽浩,徐东海,等. 机载大尺寸天线平面度控制与测试研究[J]. 现代雷达,2010,32(4):82-87. CHEN ZH M, PING L H, XU D H, et al.. A study on control measures and measurement technology of flatness of airborne large size antenna [J]. Modern Radar, 2010,32(4):82-87. ( in Chinese)

李潜,刘子强. 大型飞机研制需要的风动试验技术[C]. 中国航空学会2007年学术年会气动专题,1-10. LI Q, LIU Z Q. Pneumatic test technology for large aircraft development needs[C]. Chinese Aviation Association 2007 Annual Meeting of the Academic Pneumatic Special,1-10. (in Chinese)

李磊刚,梁晋,唐正宗,等. 飞机结构件运动数据的动态视觉测量系统[J]. 光学精密工程,2012,20(9):1929-1938. LI L G,LIANG J,TANG ZH Z, et al.. Optical and dynamic measuring system for movement data of aircraft structural parts[J].Opt. Precision Eng., 2012,20(9):1929-1938. (in Chinese)

THOMPSON E A,ANDERSON T R. A CUDA implementation of the continuous space language model[J]. Journal of Supercomputing, 2014, 68(1):65-86.

HAVEL J, DUBSKA M,HEROUT A. Real-time detection of lines using parallel coordinates and CUDA [J]. Journal of Real-Time Image Processing, 2014,9(1SI):205-216.

GOLDSWORTHY M J. A GPU-CUDA based direct simulation Monte Carlo algorithm for real gas flows [J]. Computers & Fluids,2014,94:58-68.

李大禹,胡立发,穆全全,等. CUDA 架构下的液晶自适应波面数值解析[J]. 光学精密工程,2010,18(4):848-854. LI D Y,HU L F,MU Q Q, et al.. Wavefront calculation of liquid crystal adaptive optics based on CUDA [J]. Opt. Precision Eng., 2010,18(4):848-854. ( in Chinese)

王晶,李仕. 运动模糊视频图像在图形处理器平台上的实时恢复[J]. 光学精密工程,2010,18(10):2262-2268. WANG J, LI SH. Real-time restoration of motion-blurred video images on GPU[J]. Opt. Precision Eng., 2010,18(10):2262-2268. ( in Chinese)

连远锋,赵剡,何晖光. 自适应耦合变分模型及其GPU 实现[J]. 仪器仪表学报,2013,34(11):2520-2525. LIAN Y F, ZHAO Y,HE H G. Adaptive coupled variation model and its GPU implementation[J]. Chinese Journal of Scientific Instrument, 2013,34(11):2520-2525. ( in Chinese)

李仕,张葆,孙辉. 航空斜视成像异速像移的实时恢复[J]. 光学精密工程,2009,17(4):895-900. LI SH, ZHANG B,SUN H. Real-time restoration for aerial side-oblique images with different motion rates [J]. Opt. Precision Eng., 2009,17(4):895-900. ( in Chinese)

许晓臣,董明利,王君,等. 基于CUDA的动态视觉测量像面特征点中心快速定位算法[J]. 计算机工程与科学,2014,36(12):2378-2385. XU X CH, DONG M L, WANG J, et al..A fast target center location algorithm for dynamic vision measurement based on CUDA[J].Computer Engineering & Science, 2014,36(12):2378-2385.(in Chinese)

ZHUANG W, DONG M L, SUN P, et al.. A variable weighted centroid method for retro reflective target locating[C].Proc of the sixth International Symposium on Precision Mechanical Measurements,2013.

SHORTIS M R, CLARKE T A, SHORT T.A comparison of some techniques for the subpixel location of distance target images[C].3rd Conference on Videometrics,Boston,MA,1994.

DONG M L, XU L,WANG J,et al.. Variable-weighted grayscale centroiding and accuracy evaluating [J].Advances in Mechanical Engineering,2013, 428608.

王灿进,孙涛,陈娟. 局部不变特征匹配的并行加速度技术研究[J]. 液晶与显示,2014,29(2):266-274. WANG C J,SUN T,CHEN J.Speeding up local invariant feature matching using parallel technology[J].Chinese Journal of Liquid Crystals and Displays,2014,29(2):266-274.(in Chinese)

王林波,王延杰,邸男,等. 基于几何特征的圆形标志点亚像素中心定位[J]. 液晶与显示,2014,6(6):1003-1009. WANG L B,WANG Y J,DI N,et al..Subpixel location of circle target center based on geometric features[J].Chinese Journal of Liquid Crystals and Displays,2014,6(6):1003-1009.(in Chinese)

王洪涛,李丹. 基于改进粒子群算法的图像边缘检测研究[J] 液晶与显示,2014,29(5):800-804. WANG H T,LI D.Image edge detection research based on improved particle swarm optimization algorithm[J].Chinese Journal of Liquid Crystals and Displays,2014,29(5):800-804.(in Chinese)

浏览量

489

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种航空斜视成像异速像移实时恢复算法

大尺寸测量中多传感器融合的研究

位相板在大型几何量形位误差测量中的应用

航空成像像移补偿的并行计算