基于GPU的无人机遥感影像快速拼接

Fast Stitching of UAV Remote Sensing Images Based on GPU

近年来,无人机遥感技术得到较快的发展,无人机遥感技术有着实时性强、灵活性强、低成本以及获取影像分辨率高的特点,在处理应急响应任务时,运用无人机遥感技术,优势极为明显。在无人机进行对地航拍时,所获取的是单张影像,由于像幅的限制,影像并不能覆盖完整的目标区域,相邻的多张影像都有着一定的重叠度,利用重叠区域来将多幅影像依次拼接,获得目标区域的一幅完整影像。随着各种传感器技术的提升,无人机上的相机所获取到的影像的分辨率越来越高,这对影像拼接的速度提出了新的要求。基于无人机遥感影像的特点,采用SIFT算子对无人机遥感影像进行拼接工作,并在CUDA平台下对配准算法进行加速处理,从而提高影像拼接的速度。

With the upgrading of various sensor technologies, the camera on the UAV acquired higher resolution images which put forward some new demands to the speed of image stitching. In this paper, based on the characteristics of UAV remote sensing image, we used SIFT operator to mosaic UAV remote sensing images, and made a program to accelerate the process of registration algorithm to improve the speed of image stitching in the CUDA platform.