| abstract |
The invention discloses a land cover classification method for high-resolution remote sensing images based on a parallel algorithm, comprising: S1 segmenting high-resolution remote sensing image data according to the number of computers to obtain segmented high-resolution remote sensing images block; S2 allocates all high-resolution remote sensing image blocks to m processors based on the OpenMP parallel framework, and performs land cover classification processing concurrently; S3 merges all high-resolution remote sensing image block data according to the principle of data segmentation to obtain Final land cover classification results. The method of the present invention automatically divides the data according to the size of the data and the use of the computer memory, uses the configuration file to organize the classification algorithm flow, and realizes the parallel classification algorithm, so that it can adapt to the high-resolution surface with extremely large data volume and finely divided ground object space Override mapping tasks. |