研究目的
To propose a novel method for directly assessing the distribution of materials and elements in hyperspectral images by means of a structural optimization approach for accurate and reliable characterization of urban materials and extents.
研究成果
The proposed method based on structural optimization and the p-complete mixture model (pCMM) provides accurate and reliable characterization of urban materials and extents, outperforming other nonlinear mixture models in estimating anthropogenic extents in hyperspectral datasets.
研究不足
The study is limited by the computational costs associated with the structural optimization approach and the need for high-performance computing platforms to enhance efficiency.
1：Experimental Design and Method Selection:
The study employs a structural optimization approach based on the globally convergent method of the moving asymptotes (GCMMA) for nonlinear unmixing of hyperspectral images.
2：Sample Selection and Data Sources:
Two real images recorded by the Hyperion sensor on board of the EO-1 satellite over Shanghai (P.R.C.) and Ankara (Turkey) regions were used.
3：List of Experimental Equipment and Materials:
Hyperion sensor on board of the EO-1 satellite.
4：Experimental Procedures and Operational Workflow:
The method involves nonlinear programming for estimating the abundances of materials in urban areas, using a novel metric based on the estimated coefficients to identify anthropogenic extents.
5：Data Analysis Methods:
The performance of the proposed method was compared with linear mixture model (LMM), linear-quadratic mixture model (LQM), and order-5 harmonic mixture model (5HMM).
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
