Distortion correction algorithm for UAV remote sensing image based on CUDA

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Wenhao, Zhang^1,2 ; Yingcheng, Li^1,2 ; Delong, Li^1,3 ; Changsheng, Teng^1 ; Jin, Liu^1,3

China TopRS Technology Co., Ltd, Beijing 100039, China^1

Chinese Academy of Surveying and Mapping, Beijing 100039, China^2

Beijing Institute of Civil Engineering and Architecture, Beijing 100044, China^3

关键词: Compute Unified Device Architecture(CUDA);    Distortion correction;    Emergency response capabilities;    Geo-spatial informations;    Geometric deformations;    Image distortion corrections;    Major natural disasters;    Remote sensing system;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012190/pdf
DOI  :  10.1088/1755-1315/17/1/012190

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

In China, natural disasters are characterized by wide distribution, severe destruction and high impact range, and they cause significant property damage and casualties every year. Following a disaster, timely and accurate acquisition of geospatial information can provide an important basis for disaster assessment, emergency relief, and reconstruction. In recent years, Unmanned Aerial Vehicle (UAV) remote sensing systems have played an important role in major natural disasters, with UAVs becoming an important technique of obtaining disaster information. UAV is equipped with a non-metric digital camera with lens distortion, resulting in larger geometric deformation for acquired images, and affecting the accuracy of subsequent processing. The slow speed of the traditional CPU-based distortion correction algorithm cannot meet the requirements of disaster emergencies. Therefore, we propose a Compute Unified Device Architecture (CUDA)-based image distortion correction algorithm for UAV remote sensing, which takes advantage of the powerful parallel processing capability of the GPU, greatly improving the efficiency of distortion correction. Our experiments show that, compared with traditional CPU algorithms and regardless of image loading and saving times, the maximum acceleration ratio using our proposed algorithm reaches 58 times that using the traditional algorithm. Thus, data processing time can be reduced by one to two hours, thereby considerably improving disaster emergency response capability.