基于CPU和GPU协同处理的光学卫星遥感影像正射校正方法

›› 2013, Vol. 42 ›› Issue (5): 668-675.

基于CPU和GPU协同处理的光学卫星遥感影像正射校正方法

方留杨¹,王密²,李德仁²

1. 武汉大学
2. 武汉大学测绘遥感信息工程国家重点实验室

收稿日期:2012-08-21 修回日期:2013-01-18 出版日期:2013-10-20 发布日期:2014-01-23
通讯作者: 方留杨 E-mail:fangliuyang@whu.edu.cn
基金资助:
中央高校基本科研业务费专项资金

A CPU-GPU Co-processing Orthographic Rectification Approach for Optical Satellite Imagery

Received:2012-08-21 Revised:2013-01-18 Online:2013-10-20 Published:2014-01-23

摘要/Abstract

摘要： 本文系统地探讨了基于CPU和GPU协同处理的光学卫星遥感影像正射校正方法。首先使用“层次性分块”策略设计了基于CPU和GPU协同处理的正射校正方法，然后通过配置选择优化和存储层次性访问等手段进一步提高了方法执行效率。在Tesla M2050 GPU上对资源三号卫星下视全色影像进行正射校正的实验结果表明，本文方法大幅提高了光学卫星遥感影像正射校正效率，与传统串行正射校正算法相比，加速比最高达到110倍以上，相应的处理时间压缩至5s以内，可满足对大数据量光学卫星遥感影像进行快速正射校正的要求。

关键词: 正射校正, CPU和GPU协同处理, 层次性分块, 配置选择优化, 存储层次性访问

Abstract: A new CPU-GPU co-processing orthographic rectification approach for optical satellite imagery is proposed in this paper. First, “hierarchical tiling” strategy is applied to form the basic algorithm flow; then the algorithm performance is further improved in the respect of configuration optimization and memory hierarchical access. The algorithm is applied to the orthographic rectification of ZY-3 nadir panchromatic imagery and the experimental data is collected. By analyzing the data we find that the processing time of our algorithm on Tesla M2050 GPU is less than 5 seconds and the highest speedup ratio to the traditional serial algorithm is more than 110 times. This result demonstrates that our algorithm significantly improves the orthographic rectification efficiency and fully satisfies the requirement of fast orthographic rectification for large data optical satellite imagery.

Key words: Orthographic Rectification, CPU-GPU Co-processing, Hierarchical Tiling, Configuration Optimization, Memory Hierarchical Access

中图分类号:

P237

方留杨王密李德仁. 基于CPU和GPU协同处理的光学卫星遥感影像正射校正方法[J]. , 2013, 42(5): 668-675.

参考文献

[1] Jiang Yanhuang, Yang Xuejun, Yi Huizhan. Parallel Algorithm of Geometrical Correction for Satellite Images[J], Chinese Journal of Computers, 2004,27(7): 944-951.（蒋艳凰，杨学军，易会战. 卫星遥感图像并行几何校正算法研究[J]，计算机学报，2004,27(7): 944-951）
[2] Xiao Han, Zhang Zuxun, Parallel Image Matching Algorithm Based on GPGPU [J]. Acta Geodaetica et Cartographica Sinica, 2010,39(1): 46-51.（肖汉，张祖勋. 基于GPGPU的并行影像匹配算法 [J]，测绘学报，2010,39(1): 46-51）
[3] Fang Xudong. CPU-GPU Heterogenenous Parallel Technology: Oriented On Large Scale Scientific Calculation [D]. Changsha: The National University of Defense Technology, 2009.（方旭东. 面向大规模科学计算的CPU-GPU异构并行技术研究[D]，长沙：国防科学技术大学，2009）
[4] Yang Jingyu, Zhang Yongsheng, Li Zhengguo, Gong Hui, GPU-CPU Cooperate Processing of RS Image Ortho-Rectification [J]. Geomatics and Information Science of Wuhan University, 2011,36(9): 1043-1046. （杨靖宇，张永生，李正国，龚辉. 遥感影像正射纠正的GPU-CPU协同处理研究[J]，武汉大学学报?信息科学版，2011,36(9): 1043-1046）
[5] Yang Jingyu. Study on Parallel Processing Technologies of Photogrammetry Data Based on GPU [D]. Zhengzhou: Information Engineering University, 2011.（杨靖宇. 摄影测量数据GPU并行处理若干关键技术研究[D]，郑州：信息工程大学，2011）
[6] Chen Chao, Chen Bin, Meng Jianpin, Geometric Correction of Remote Sensing Images Based on Graphic Processing Unit [J].Command Information System and Technology,2012,3(1): 76-80.（陈超，陈彬，孟剑萍. 基于GPU大规模遥感图像的几何校正[J]，指挥信息系统与技术，2012,3(1): 76-80）
[7] Hou Yi, Shen Yannan, Wang Ruisuo, Yu Zongchao, The Discussion of GPU-Based Digital Differential Rectification [J]. Modern Surveying and Mapping, 2009,32(3): 10-12. （侯毅，沈彦男，王睿索，余宗超.基于GPU的数字影像的正射纠正技术的研究[J]，现代测绘，2009,32(3): 10-12）
[8] Fang Liuyang, Wang Mi, Li Deren, Zhang Bingxian. Research on GPU-Based Real-Time MTF Compensation Algorithm [C]. ISPRS WG VII/6 Conference Proceedings. TengChong: The 2011 International Symposium on Image and Data Fusion, 2011.
[9] Milosz Ciznichi, Michal Kierzynka, Piotr Kopta, Krzysztof Kurowski, Pawel Gepner. Benchmarking data and compute intensive applications on modern CPU and GPU architectures [J]. Procedia Computer Science, 2012,12: 1900-1909.
[10] Yang Jingyu, Zhang Yongsheng, Zhang Honglan, Ji Song. Remote Sensing Image Parallel Processing based on GPU [J]. Engineering of Surveying and Mapping, 2008,17(3): 22-27.（杨靖宇，张永生，张宏兰，纪松 . 基于可编程图形硬件的遥感影像并行处理研究 [J]，测绘工程，2008,17(3): 22-27）
[11] Sui Haigang, Peng Feifei, Xu Chuan, Sun Kaimin, Gong Jianya. GPU-accelerated MRF Segmentation Algorithm for SAR Images [J]. Computers & Geosciences, 2012, 43: 159-166.
[12] Xu Xuegui, Zhang Qing. Efficiently Processing Parallel Remote Sensing Imagery Using CUDA [J]. Geospatial Information, 2011,9(6): 47-53.（许雪贵，张清. 基于CUDA的高效并行遥感影像处理 [J]，地理空间信息，2011,9(6): 47-53）
[13] David B.Kirk, Wen-mei W.Hwu, Programming Massively Parallel Processors [M]. Amsterdam: Elsevier, 2010.
[14] Zhang Shu, Chu Yanli. GPU high performance computing – CUDA [M]. Beijing: China Waterpower Press, 2009.（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）
[15] Zhao Jin. Study of Remote Sensing Image Parallel Processing Algorithms based on GPU and Optimization Techniques [D]. Changsha: The National University of Defense Technology, 2011.（赵进. 基于GPU的遥感图像并行处理算法及其优化技术研究[D]，长沙：国防科学技术大学，2011）
[16] Lu Fengshun, Song Junqiang, Yin Fukang, Zhang Lilun. Survey of CPU/GPU Synergetic Parallel Computing [J]. Computer Science, 2011,38(3): 5-10.（卢风顺，宋君强，银福康，张理论. CPU/GPU协同并行技术研究综述[J]，计算机科学，2011,38(3): 5-10）
[17] Zhang Guo, Li Deren. The Algorithm of Computation RPC Model’s Parameters for Satellite Imagery [J]. Journal of Image and Graphics, 2007,12(12): 2080-2088.（张过，李德仁 . 卫星遥感影像RPC参数求解算法研究 [J]，中国图像图形学报，2007,12(12): 2080-2088）
[18] Zhu Xiaoyong, Zhang Guo, Qin Xuwen. The Formulation of RPC for Domestic Optical Satellite Imagery[J]. Remote Sensing For Land & Resources, 2011,2: 32-34.（祝小勇，张过，秦绪文 . 国产光学卫星影像RPC制作[J]，国土资源遥感，2011,2: 32-34）
[19] Zhang Guo, Li Fangting, Jiang Wanshou, Zhai Liang, Tang Xinming. Study of Three-dimensional Geometric Model and Orientation Algorithms for Systemic Geometric Correction Product of Push-broom Optical Satellite Image [J]. Acta Geodaetica et Cartographica Sinica, 2010,39(1): 34-38.（张过，厉芳婷，江万寿，翟亮，唐新明. 推扫式光学卫星影像系统几何校正产品的3维几何模型及定向算法研究[J]，测绘学报，2010,39(1): 34-38）
[20] Li Deren, Wang Shugen, Zhou Yueqin. An Introduction to Photogrammetry and Remote Sensing (Second Edition) [M]. Beijing: Surveying and Mapping Press, 2008.（李德仁，王树根，周月琴. 摄影测量与遥感概论（第二版） [M] . 北京: 测绘出版社, 2008）