CUDA架构下高效红外图像背景预测方法

doi:10.3969/j.issn.1001-2400.2011.06.007

Abstract

Abstract:

Background prediction in infrared is a classical method for small and dim target detection. Taking account of the convolution's time-consuming property, an efficient method for infrared image background prediction based on CUDA (Compute Unified Device Architecture) is proposed. By considering the feature of CUDA and analyzing the process of background prediction, it is re-realized. Using the framework of CUDA and taking advantage of the powerful parallel computing ability of GPU (Graphic Processing Unit), background prediction from infrared images is rapidly and efficiently completed. For further raising the efficiency of the method, the inseparable convolution matrix used by background prediction is broken up into several separable matrices, where a general method for separating the convolution matrix is presented. Applying this method to actual infrared image's background prediction, the computation efficiency is raised more than 130 times compared with the traditional method based on CPU.

Key words: infrared detection, high performance computing, background prediction, separable convolution

CLC Number:

TP391.41

WU Xin;ZHANG Jianqi;LIU Delian;HUANG Xi;HE Guojing. Efficient infrared image background prediction in CUDA[J].J4, 2011, 38(6): 44-51.

References

［1］徐军. 红外图像中弱小目标检测技术研究［D］. 西安: 西安电子科技大学, 2003.
［2］汪大宝, 刘上乾, 张峰. 一种新的红外复杂背景自适应抑制算法［J］. 西安电子科技大学学报, 2010, 37(5): 927-933.
Wang Dabao, Liu Shangquan, Zhang Feng. New Adaptive Infrared Strong Cluttered Background Suppression Algorithm［J］. Journal of Xidian University, 2010, 37(5): 927-933.
［3］朱红, 赵亦工. 基于背景自适应预测的红外弱小运动目标检测［J］. 红外与毫米波学报, 1999(4): 305-310.
Zhu Hong, Zhao Yigong. Detection of Weak and Small Moving Infrared Targets by Adaptive Prediction of Background［J］. Journal of Infrared and Millimeter Waves, 1999(4): 305-310.
［4］郭伟. 基于非参数统计的云层背景描述与红外弱小目标检测［J］. 红外与毫米波学报, 2008(5): 383-388.
Guo Wei. New Method for Cloud Description and Dim Small Infrared Target Detection Based on Nonparametric Statistics［J］. Journal of Infrared and Millimeter Waves, 2008(5): 383-388.
［5］李凡, 刘上乾, 洪鸣, 等. 基于背景预测的红外弱小目标检测新算法［J］. 西安电子科技大学学报, 2009, 36(6): 1075-1078.
Li Fan, Liu Shangqian, Hong Ming, et al. Dim Infrared Targets Detection Based on Background Prediction［J］. Journal of Xidian University, 2009, 36(6): 1075-1078.
［6］张舒, 褚艳利. GPU 高性能运算之CUDA［M］. 北京: 中国水利水电出版社, 2009.
［7］ Ren N. GPU-based Monte Carlo Simulation for Light Propagation in Complex Heterogeneous Tissues［J］. Opt Express, 2010, 18(7): 6811-6823.
［8］ Pan Lei, Gu Lixu, Xu Jianrong . Implementation of Medical Image Segmentation in CUDA［C］//IEEE, International Conference on Information Technology and Applications in Biomedicine. Shenzhen: IEEE, 2008: 82-85.
［9］ Kelly R. GPU Computing for Atmospheric Modeling［J］. Computing in Science ＆ Engineering, 2010, 12(4): 26-33.
［10］ Datla S, Gidijala N S. Parallelizing Motion JPEG 2000 with CUDA［C］//IEEE, Second International Conference on Computer and Electrical Engineering. Dubai: IEEE, 2009: 630-635.
［11］ Pachnicke S. Fast Parallel Simulation of Fiber Optical Communication Systems Accelerated by A Graphics Processing Unit［C］//IEEE, 2010 12th International Conference on Transparent Optical Networks (ICTON). Munich: IEEE, 2010: 1-4.
［12］冈萨雷斯 R C. 数字图像处理［M］. 北京: 电子工业出版社, 2003.
［13］ Nvidia C. Compute Unified Device Architecture Programming Guide［EB/OL］. ［2010-10-3］. http://developer.download.nvidia.com/compute/cuda/2_0/docs/NVIDIA_CUDA_Programming_Guide_2.0.pdf.

[1]	CHAI Guobei;ZHANG Jianqi;HUANG Xi;GUO Bingtao;TIAN Limin. Study of the dynamic scenes model for laser imaging radar simulation [J]. J4, 2014, 41(2): 107-113.
[2]	LI Fan;LIU Shang-qian;HONG Ming;QIN Han-lin. Dim infrared targets detection based on background prediction [J]. J4, 2009, 36(6): 1075-1078.

Efficient infrared image background prediction in CUDA

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 2

Metrics

Comments

Recommended 10