Issue |
E3S Web Conf.
Volume 520, 2024
4th International Conference on Environment Resources and Energy Engineering (ICEREE 2024)
|
|
---|---|---|
Article Number | 03020 | |
Number of page(s) | 5 | |
Section | New Progress in New Energy and Resource Utilization Technology | |
DOI | https://doi.org/10.1051/e3sconf/202452003020 | |
Published online | 03 May 2024 |
A Feature Window Weighted Correlation Spectral Matching Method for Rock and Mineral Resources
1 School of Computer Engineering, Chengdu Technological University, Chengdu 611730, China
2 School of Network and Communication Engineering, Chengdu Technological University, Chengdu 611730, China
a 873158916@qq.com
*b Corresponding author’s email: 362631406@qq.com
This paper proposes a feature window weighted correlation spectral matching method for rocks and minerals, which includes the following steps: (1) Assuming that the error caused by the natural environment is a random normal distribution, the remote sensing image is based on each band, and within the reflectance range, the reflectance of each band is extended to the range of 0 to 1 according to the normal distribution law, forming a matrix dataset X; (2) Using the standard spectral curve as a benchmark for each band, within the reflectance range, the reflectance of each band is extended to the range of 0 to 1 according to the normal distribution pattern, forming a matrix dataset Y; (3) Within the full wavelength range, classify the sensitivity intervals of rocks and minerals based on standard spectral curves, form feature windows, and set predetermined weight coefficients; (4) Calculate the correlation coefficient r of the feature window and combine it with the weight coefficient in step (3) to obtain the comprehensive correlation coefficient K; (5) Using the comprehensive correlation coefficient K as the final basis for identifying rock and mineral types.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.