image: This study proposes an optimized sampling method based on surface complexity. By calculating local complexity scores, stratifying samples using quantiles, and applying weighted sampling probabilities, this approach ensures greater sample representativeness. It effectively reduces sampling bias, enhances the accuracy of remote sensing intelligent interpretation, and provides an optimized sample selection strategy for analyzing complex surface environments.
Credit: Beijing Zhongke Journal Publising Co. Ltd.
The Journal of Geo-information Science recently published an online article on research led by researcher Lianfa Li and researcher Xiaomei Yang (Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences). The study introduces a novel complexity-based sampling optimization method, designed to enhance the accuracy and reliability of remote sensing interpretation in complex and heterogeneous environments.
Accurate sample selection is critical for remote sensing applications, including land-use classification, environmental monitoring, and disaster assessment. However, traditional sampling methods often fail to capture the full range of terrain diversity, spectral variation, and spatial heterogeneity, leading to biased and unreliable interpretation results. Addressing these challenges, the research team developed a stratified sampling approach based on remote sensing complexity, integrating surface complexity metrics, spatial heterogeneity indicators, and multi-scale morphological transformations to optimize sample representativeness.
The study systematically reviews sampling methods for labeled data, techniques for augmenting samples through multi-scale morphological transformations, and evaluation strategies for labeled sample quality. By incorporating terrain complexity and weighted stratified sampling, the method significantly reduces sampling bias and improves classification accuracy. Multi-scale morphological transformations further expand sample diversity, strengthening the robustness of remote sensing models.
Experimental results demonstrate that this complexity-based sampling approach significantly outperforms traditional methods in capturing land surface variations and improving interpretation precision. "By improving sample representativeness through complexity-aware sampling and morphological transformations, we can enhance the reliability of remote sensing applications in challenging environments," said researcher Lianfa Li.
This study provides a theoretical and technical foundation for advancing remote sensing-based intelligent interpretation. The optimized sampling strategy offers practical applications for disaster monitoring, ecological assessment, and natural resource management, paving the way for more accurate and data-driven decision-making in complex environmental contexts.
For more details, please refer to the original article:
Sampling Method for Complex Scene Samples in the Intelligent Interpretation of Natural Resources Remote Sensing. https://www.sciengine.com/JGIS/doi/10.12082/dqxxkx.2024.240278（If you want to see the English version of the full text, please click on the “iFLYTEK Translation” in the article page.）
Article Title
Research on Sampling Method of Complex Scenes in Natural Resources Remote Sensing Intelligent Interpretation
Article Publication Date
25-Feb-2025