基于GPU并行计算的巨幅遥感影像坐标转换研究与实现

Research and Implementation of Huge Remote Sensing Image Coordinate Transformation Based on GPU Parallel Computing

随着航空航天遥感技术的不断发展,以遥感影像为代表的栅格数据分辨率越来越高,遥感影像处理呈现出数据量大、复杂度高的特点。近年来,通用GPU的运算性能不断提高为加速密集运算提供了新的途径,目前,采用GPU并行技术进行遥感影像处理成为新的研究热点。本文提出了基于GPU并行计算的巨幅遥感影像坐标转换方法,实践证明,相比于传统的转换方法基于GPU的算法有较为明显的提速。

With the continuous development of aerospace remote sensing technology, the resolution of remote sensing images as raster data is more and more high, the remote sensing image processing shows the characteristics of large amount of data and high complexi- ty. In recent years, the continuous improvement of the operation performance of general GPU provides a new way to accelerate the computation intensive, at present, processing remote sensing image based on GPU parallel computing is becoming a new research fo- cus. This paper presents a method for huge remote sensing image coordinate transformation based on GPU parallel computing, practice has proved that, the transform speed is obvious improved compared with the traditional methods.