计算机科学 ›› 2014, Vol. 41 ›› Issue (7): 306-309.doi: 10.11896/j.issn.1002-137X.2014.07.063

• 图形图像与模式识别 • 上一篇    下一篇

面向OpenCL架构的Harris角点检测算法

肖汉,马歌,周清雷   

  1. 郑州大学信息工程学院 郑州450001;郑州师范学院信息科学与技术学院 郑州450044;郑州师范学院信息科学与技术学院 郑州450044;郑州大学信息工程学院 郑州450001
  • 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(41171357),中国博士后科学基金(2012M510176),河南省重点科技攻关项目(132102310003),河南省教育厅科学技术研究重点项目(13A520354)资助

Harris Corner Detection Algorithm on OpenCL Architecture

XIAO Han,MA Ge and ZHOU Qing-lei   

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

摘要: Harris角点检测算法是计算机视觉领域中使用非常广泛的点特征提取算法,它计算简单,稳定性强,但运算速度慢。当前已有算法优化研究一般只针对单一硬件平台,它们很难实现在不同平台上的高效运行。为此提出一种基于开放式计算语言(OpenCL)设计思想的Harris角点检测并行算法,其采用图形处理器(GPU)中共享存储器、常量存储器和锁页内存机制在OpenCL框架下完成影像角点检测的全过程。实验结果表明,基于OpenCL的Harris角点检测并行算法相比CPU上的串行算法可获得 的加速比 高达77倍,执行效率明显提高,对于大规模数据处理表现出良好的实时处理能力。

关键词: 图形处理器,开放式计算语言,影像,角点检测,Harris算子 中图法分类号TP391,P237文献标识码A

Abstract: Harris corner detection algorithm is widely used for extracting feature points in the field of computer vision.It is simple and stable,but inefficient.Currently most of the researches on algorithm optimization are aimed at a single hardware platform,and difficult to achieve the efficient running on different platforms.In this paper,parallel algorithm of Harris corner detection based on the core concept of Open Computing Language (OpenCL) was proposed,so that the whole image corner detection process can be implemented in OpenCL architecture.Finally,implementation of the parallel algorithm using mechanism of shared memory and constant memory and pinned host memory in Graphic Processing Unit (GPU) was detailed.The experiments show that the parallel algorithm of Harris corner detection based on OpenCL demonstrates substantial improvement up to 77times speedup than the serial algorithm running in the CPU,has high efficiency compared with CPU counterpart algorithm,and exhibits great potential for large-scale data processing in real-time processing.

Key words: Graphic processing unit (GPU),Open computing language (OpenCL),Image,Corner detection,Harris operator

[1] Kitchen L,Rosenfeld A.Gray-level corner detection [J].Pattern Recognition Letters,1982,1(2):95-102
[2] Mokhtarian F,Suomela R.Robust image corner detection th-rough curvature scale space [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381
[3] Freeman H,Davis L S.A corner finding algorithm for chain-coded curves [J].IEEE Transaction on Computers,1977,C-26(3):297-303
[4] Wang H,Brady M.Real-time corner detection algorithm for motion estimation [J].Image and Vision Computing,1995,13(9):695-703
[5] Harris C G,Stephens M J.A Combined Corner and Edge Detector [C]∥Proceedings the Fourth Alvey Vision Conference.Manchester,UK,1988:147-151
[6] Moravec H P.Towards automatic visual obstacle avoidance [C]∥Proceedings of International Joint Conference on Artificial Intelligence.Cambridge,MA,USA,1977:584-590
[7] Trajkovic M,Hedley M.Fast corner detection [J].Image and Version Computing,1998,16(2):75-87
[8] Smith S M,Brady M.SUSAN—a new approach to low level ima-ge processing [J].International Journal of Computer Version,1997,23(1):45-78
[9] Amir F,Fouzhan H.Image processing applications on a lowpower highly parallel SIMD architecture[C]∥IEEE Aerospace Conference Proceedings.2011:1-12
[10] Suárez M,Brea V M,Fernández-Berni J,et al.CMOS-3D Smart Imager Architectures for Feature Detection [J].IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2012,2(4):723-736
[11] 王渝,王刚,梅员.基于FPGA的改进Harris角点检测方法[J].通信技术,2010,43(4):158-160
[12] Saidani T,Lacassagne L,Falcou J,et al.Parallelization schemes for memory optimization on the cell processor:A case study on the Harris corner detector[J].Lecture Notes in Computer Science,2011,6590:177-200
[13] Teixeira L,Celes W,Gattass M.Accelerated corner-detector algorithms[EB/OL].http://www.comp.leeds.ac.uk/bmvc2008/proceedings/papers/45.pdf,2008
[14] 谢洪涛,高科,张勇东,等.基于GPU的快速图像拷贝检测[J].计算机辅助设计与图形学学报,2010,22(9):1483-1490
[15] Chen Gang,Li Guo-bo,Wu Bai-feng.Program restructuring targeting GPU memory optimization [J].Journal of Chinese Computer Systems,2011,32(10):1921-1927
[16] ATI stream computing OpenCL programming guide [M].AMD Corporation,March 2010
[17] Leonid D,Igor M,et al.Accelerating clustering coefficient calculations on a GPU using OPENCL[J].Communications in Computer and Information Science,2011,83,276-285
[18] Jorn H,Karim E-L,et al.Simulating biological inspired spiking neural networks with OpenCL [J].Lecture Notes in Computer Science,2010,6352:184-187

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!