1. 东北大学资源与土木工程学院，辽宁 沈阳 110819
2. School of Arts, Humanities and Social Sciences, The University of Edinburgh, Edinburgh EH6 6ED, England
3. 东北大学江河建筑学院，辽宁 沈阳 110819
Fusion Algorithm Research Based on Imaging Spectrum of Anshan Iron Ore
MAO Ya-chun1, WEN Jie1*, CAO Wang1, DING Rui-bo1, WANG Shi-jia2, FU Yan-hua3, XU Meng-yuan1
1. School of Resources and Civil Engineering, Northeastern University, Shenyang 110819, China
2. School of Arts, Humanities and Social Sciences, The University of Edinburgh, Edinburgh EH6 6ED, England
3. School of Architecture, Northeastern University, Shenyang 110819, China
Abstract：Iron ore resources are the foundation of our economic development and social progress. In the process of iron ore mining, the rapid and accurate determination of iron ore grade has an important influence on the mining decision and economic benefit. Hyperspectral imaging technology has the advantages of wide image coverage and high accuracy and has been widely used in ore classification and composition inversion. However, the band range of existing hyperspectral imaging sensors mainly includes visible and shortwave infrared (Vis-SWIR) and near-infrared (NIR). The two data types are mostly acquired independently, lacking continuity, and the accuracy of the model built with single data is often low. Therefore, the fusion of spectral data obtained by multiple sensors can effectively solve the problems of the small band range of a single sensor and few bands containing target characteristics and improve the accuracy of iron ore grade inversion based on hyperspectral imaging technology. In this study, Pika L and Pika NIR-320 hyperspectral imagers were used to collect imaging spectral data of Anshan iron ore in Vis-SWIR and NIR bands, respectively, and a spectral series fusion method based on mutual information (MI) was proposed. Firstly, the two groups of spectral data were preprocessed. Then, mutual information is calculated on the processed data to conduct a series fusion of spectral data. Finally, Vis-SWIR, NIR, and spectral data based on the series fusion of different bands were used as data sources to establish RBF neural network grade inversion models, and the accuracy and precision of the models based on spectral data before and after fusion were used as the discrimination index of the effectiveness of the fusion algorithm. The results show that the accuracy and precision of the model built after series fusion of spectral data is higher than that built using Vis-SWIR and NIR spectral data alone. Compared with the spectral data based on series fusion of other bands, the accuracy and precision of the model established based on the mutual information calculation of series fusion spectral data at 959.89 nm are the highest, R2 0.88, RPD 2.97, RMSE 4.464, MAE 3.32. This study proposes a new idea for multi-sensor spectral fusion, which has practical significance for the application of imaging spectrum technology in the inversion of iron ore grade.
Key words：Anshan iron ore; Spectral fusion; Mutual information; Visible light-near infrared spectroscopy; Radial-Basis function
毛亚纯，文 杰，曹 旺，丁瑞波，王世佳，付艳华，徐梦圆. 基于鞍山式铁矿成像光谱的融合算法研究[J]. 光谱学与光谱分析, 2024, 44(09): 2620-2625.
MAO Ya-chun, WEN Jie, CAO Wang, DING Rui-bo, WANG Shi-jia, FU Yan-hua, XU Meng-yuan. Fusion Algorithm Research Based on Imaging Spectrum of Anshan Iron Ore. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(09): 2620-2625.
[1] Galdames Francisco J, Perez Claudio A, Estévez Pablo A, et al. Chemometrics and Intelligent Laboratory Systems, 2022, 224: 104538.
[2] Mishra Gaurav, Govil Himanshu, Srivastava Prashant Kumar. Quaternary Science Advances, 2021, 4: 100036.
[3] Song Kun, Wang Ende, Yao Yuzeng, et al. Applied Sciences, 2020, 10(23): 8369.
[4] Neave David A, Black Martin, Riley Teal R, et al. Economic Geology，2016, 111: 641.
[5] Moros Javier, Laserna J Javier. Talanta, 2015, 134: 627.
[6] XU Wei-jie, WU Zhong-chen, ZHU Xiang-ping, et al(徐伟杰，武中臣，朱香平，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(6): 1926.
[7] Terra Fabrício S, Viscarra Rossel Raphael A, Demattê José A M. Geoderma, 2019, 335: 35.
[8] Xu Xuebin, Du Changwen, Ma Fei, et al. Geoderma, 2019, 355: 113905.
[9] Xu Dongyun, Chen Songchao, Viscarra Rossel R A, et al. Geoderma, 2019, 352: 61.
[10] LI Zhi-gang, PENG Si-long, YANG Ni, et al(李志刚，彭思龙，杨 妮，等). Chinese Journal of Analytical Chemistry(分析化学), 2016, 44(3): 437.
[11] YANG Xiao-yu, BAO Ni-sha, CAO Yue, et al(杨晓宇，包妮沙，曹 粤，等). Geography and Geo-Information Science(地理与地理信息科学), 2021, 37(5): 38.
[12] Shen Qiang，Xia Ke，Zhang Shiwen, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 222: 117191.
[13] Murphy Richard J, Monteiro Sildomar T. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 75: 29.
[14] Barger Artem, Feldman Dan. Algorithms, 2020, 13(4): 92.
