US 12,322,076 B2
Remote sensing image geometric normalization method and apparatus
Xiaojun Shan, Beijing (CN); Ping Tang, Beijing (CN); Changmiao Hu, Beijing (CN); Hongyi Li, Beijing (CN); Zheng Zhang, Beijing (CN); and Ke Zheng, Beijing (CN)
Assigned to AEROSPACE INFORMATION RESEARCH INSTITUTE, CHINESE ACADEMY OF SCIENCES, Beijing (CN)
Appl. No. 17/641,671
Filed by AEROSPACE INFORMATION RESEARCH INSTITUTE, CHINESE ACADEMY OF SCIENCES, Beijing (CN)
PCT Filed Oct. 17, 2019, PCT No. PCT/CN2019/111567
§ 371(c)(1), (2) Date Sep. 16, 2022,
PCT Pub. No. WO2021/046964, PCT Pub. Date Mar. 18, 2021.
Claims priority of application No. 201910856936.7 (CN), filed on Sep. 10, 2019.
Prior Publication US 2023/0005109 A1, Jan. 5, 2023
Int. Cl. G06T 5/80 (2024.01); G06T 7/00 (2017.01)
CPC G06T 5/80 (2024.01) [G06T 7/0002 (2013.01); G06T 2207/10032 (2013.01); G06T 2207/20016 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/30168 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A remote sensing image geometric normalization method, comprising:
constructing a pyramid tile structure including tiles for a reference remote sensing image of remote sensing images, and releasing reference tile data, wherein the reference tile data is data of tails in the pyramid tile structure corresponding to tiles of the reference remote sensing image;
calculating a level of a tile to be downloaded and a name of the tile to be downloaded according to a resolution and geographic coordinates of a remote sensing image to be subjected to geometrical normalization of the remote sensing images, and downloading corresponding data corresponding to the tile to be downloaded from the reference tile data according to the level of the tile to be downloaded and the name of the tile to be downloaded, to obtain a standard tile data set including data corresponding to the tile to be downloaded;
performing a first geometric correction on the remote sensing image to be subjected to geometrical normalization and tiles in the standard tile set, to obtain a first image processing result;
matching the first image processing result with the tiles in the standard tile set, to obtain a plurality of control points, and calculating a result evaluation precision by using the plurality of control points; and determining whether to perform a second geometric correction on the first image processing result, according to the result evaluation precision.