基于GPU的遥感图像几何校正算法设计与实现  

Design and Implementation of Geometric Correction Algorithm for Remote Sensing Image Based on GPU

作　　者：吴敌 汪红强 邹同元 Wu Di;Wang Hongqiang;Zou Tongyuan(Institute of China Academy of Space Technology,Beijing 100095,China)

机构地区：[1]中国空间技术研究院第503研究所,北京100095

出　　处：《信息与电脑》2020年第3期38-40,43,共4页Information & Computer

摘　　要：随着遥感卫星分辨率的不断提高和卫星数量急剧增加,遥感卫星图像处理的数据量越来越庞大,同时对于卫星数据处理的精度和速度的要求不断提高,面对如此庞大的计算量,传统的CPU处理已经不能够满足更高的需求。针对遥感图像处理中几何校正的重采样过程,对每个像素点都要进行重采样处理,需要进行大量重复计算,通过使用GPU进行并行化处理可以显著提高重采样处理速度。基于CUDA编程模型,GPU可以看作一个执行效率非常高的并行线程设备,它作为CPU的一个协处理器,可以充分利用CPU和GPU的资源。With the continuous improvement of the resolution of remote sensing satellites and the sharp increase in the number of satellites,the amount of data for remote sensing satellite image processing is getting larger and larger,and at the same time,the requirements for the accuracy and speed of satellite data processing are constantly increasing.Such a huge amount of calculation is traditional CPU processing Can no longer meet the higher demand.In the resampling process for geometric correction in remote sensing image processing,each pixel must be resampled,which requires a lot of repetitive calculations.The parallel processing using GPU can significantly improve the resampling processing speed.This article is based on the CUDA programming model.The GPU can be regarded as a device that executes a very high number of parallel threads.As a coprocessor of the CPU,it can make full use of the resources of the CPU and GPU.

关 键 词：遥感图像数据 并行计算 几何校正 CUDA 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]