Object-level ground feature sample adaptive generation method and system based on dual-condition quality constraint

• Main Authors: ZHANG SHENGBIN, LUO BOREN, ZHUANG JIAFENG, YU SHUNXIN, YAO JINXI, XU QIAO, LIU DEQIANG, YU SHAOHUAI, YU FEI
• Format: Patent
• Language: Chinese; English
• Published: 24.11.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention provides a dual-condition quality constrained object-level ground feature sample adaptive generation method and system, and the method comprises the following steps: obtaining pixels with unchanged ground feature types in a set time period based on a land utilization data product, and forming a land utilization type pixel map; acquiring a center pixel of each land class sample based on the land utilization type pixel map; taking the center pixel of each type of surface feature as a representative sample point, combining the sample size to obtain a sample block of each type of surface feature, and forming a sample set of each type of surface feature; based on the multi-source features of each sample block, evaluating the quality of the sample set by taking the sample separability and the vegetation index correlation value as indexes; and if not, re-acquiring the central pixels and the sample blocks of the various ground features to generate a new sample set until the sample set reaches the standa