Comparative analysis of mineral mapping for hyperspectral and multispectral imagery

The fusion of the hyperspectral image (HSI) and the multispectral image (MSI) is commonly employed to obtain a high spatial resolution hyperspectral image (HR-HSI); however, existing methods often involve complex feature extraction and optimization steps, resulting in time-consuming fusion processes. Additionally, these methods typically require parameter adjustments for different datasets. Still, reliable references for parameter adjustment are often unavailable in practical scenarios, leading to subpar fusion results compared to simulated scenarios. To address these challenges, this paper proposes a fusion method based on a correlation matrix. Firstly, we assume the existence of a correlation matrix that effectively correlates the spectral and spatial information of HSI and MSI, enabling fast fusion. Subsequently, we derive a correlation matrix that satisfies the given assumption by deducing the generative relationship among HR-HSI, HSI, and MSI. Finally, we optimize the fused result using the Sylvester equation. We tested our proposed method on two simulated datasets and one real dataset. Experimental results demonstrate that our method outperforms existing state-of-the-art methods. Particularly, in terms of fusion time, our method achieves fusion in less than 0.1 seconds in some cases. This method provides a practical and feasible solution for the fusion of hyperspectral and multispectral images, overcoming the challenges of complex fusion processes and parameter adjustment while ensuring a quick fusion process.

show abstract

“…Here, we will show the derivation process of Equations (10) to (11). Based on Equation (10), we can obtain the following function:…”

Section: Data Availability Statementmentioning

confidence: 99%

“…Hyperspectral images have contributed significantly to various fields, including agriculture [1][2][3][4], environmental monitoring [5,6], image processing [7,8], mining [9][10][11], and urban planning [12][13][14]. Two commonly used imaging techniques in remote sensing are hyperspectral imaging and multispectral imaging.…”

Section: Introductionmentioning

confidence: 99%

Correlation Matrix-Based Fusion of Hyperspectral and Multispectral Images

Lin

Peng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…A comparison between the spectral signatures acquired from space and the ground represents the proper way to identify the minerals composing the SPp by means of hyperspectral remote-sensed data processing techniques for land, mineral, and bare soil applications, which have been developed since the early 70s [18,19]. In the above-mentioned domains, the availability of a continuous spectrum enhances the effectiveness of algorithms in identifying particular absorption features and enables an improved retrieval of surface properties [20][21][22]. In this paper, we compared the performance of the standard L2 TOA reflectance products provided by the agencies (ASI for PRISMA and DLR for EnMAP) [23,24] in the range 0.4-2.5 um with ground truth data acquired on 18 July 2023 on the SPp.…”

Section: Introductionmentioning

confidence: 99%

Comparison of ASI-PRISMA Data, DLR-EnMAP Data, and Field Spectrometer Measurements on “Sale ‘e Porcus”, a Salty Pond (Sardinia, Italy)

Musacchio,

Silvestri,

Romaniello

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

A comparison between the ASI-PRISMA (Agenzia Spaziale Italiana-PRecursore IperSpettrale della Missione Applicativa) DLR-EnMAP (German Aerospace Center—Environmental Mapping and Analysis Program) data and field spectrometer measurements has been performed. The test site, located at the “Sale ‘e Porcus” pond (hereafter SPp) in Western Sardinia, Italy, offers particularly homogenous characteristics, making it an ideal location not only for experimentation but also for calibration purposes. Three remote-sensed data acquisitions have been performed by these agencies (ASI and DLR) starting on 14 July 2023 and continuing until 22 July 2023. The DLR-EnMAP data acquired on 22 July overestimates both that of the ASI-PRISMA and the 14 July DLR-EnMAP radiance in the VNIR region, while all the datasets are close to each other, up to 2500 nm, for all considered days. The average absolute mean difference between the reflectance values estimated by the ASI-PRISMA and DLR-EnMAP, in the test area, is around 0.015, despite the small difference in their time of acquisition (8 days); their maximum relative difference value occurs at about 2100 nm. In this study, we investigate the relationship between the averaged ground truth value of reflectance, acquired by means of a portable ASD FieldSpec spectoradiometer, characterizing the test site and the EO reflectance data derived from the official datasets. FieldSpec measurements confirm the quality of both the ASI-PRISMA and DLR-EnMAP’s reflectance estimations.

show abstract

“…The methods of classifying rocks and minerals with TASI images are currently focused on traditional methods, which can have some drawbacks. Traditional lithology classification algorithms are mainly aimed at the spectra, and they can be grouped into two aspects: based on spectral similarity and spectral characteristics [15][16][17]. To the former, the main idea of the spectral comparison is to construct a spectral similarity measure to accomplish the lithology classification.…”

Section: Introductionmentioning

confidence: 99%

Lithology Classification Using TASI Thermal Infrared Hyperspectral Data with Convolutional Neural Networks

Liu

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In recent decades, lithological mapping techniques using hyperspectral remotely sensed imagery have developed rapidly. The processing chains using visible-near infrared (VNIR) and shortwave infrared (SWIR) hyperspectral data are proven to be available in practice. The thermal infrared (TIR) portion of the electromagnetic spectrum has considerable potential for mineral and lithology mapping. In particular, the abovementioned rocks at wavelengths of 8–12 μm were found to be discriminative, which can be seen as a characteristic to apply to lithology classification. Moreover, it was found that most of the lithology mapping and classification for hyperspectral thermal infrared data are still carried out by traditional spectral matching methods, which are not very reliable due to the complex diversity of geological lithology. In recent years, deep learning has made great achievements in hyperspectral imagery classification feature extraction. It usually captures abstract features through a multilayer network, especially convolutional neural networks (CNNs), which have received more attention due to their unique advantages. Hence, in this paper, lithology classification with CNNs was tested on thermal infrared hyperspectral data using a Thermal Airborne Spectrographic Imager (TASI) at three small sites in Liuyuan, Gansu Province, China. Three different CNN algorithms, including one-dimensional CNN (1-D CNN), two-dimensional CNN (2-D CNN) and three-dimensional CNN (3-D CNN), were implemented and compared to the six relevant state-of-the-art methods. At the three sites, the maximum overall accuracy (OA) based on CNNs was 94.70%, 96.47% and 98.56%, representing improvements of 22.58%, 25.93% and 16.88% over the worst OA. Meanwhile, the average accuracy of all classes (AA) and kappa coefficient (kappa) value were consistent with the OA, which confirmed that the focal method effectively improved accuracy and outperformed other methods.

show abstract

Comparative analysis of mineral mapping for hyperspectral and multispectral imagery

Cited by 16 publications

References 24 publications

Correlation Matrix-Based Fusion of Hyperspectral and Multispectral Images

Correlation Matrix-Based Fusion of Hyperspectral and Multispectral Images

Comparison of ASI-PRISMA Data, DLR-EnMAP Data, and Field Spectrometer Measurements on “Sale ‘e Porcus”, a Salty Pond (Sardinia, Italy)

Lithology Classification Using TASI Thermal Infrared Hyperspectral Data with Convolutional Neural Networks

Contact Info

Product

Resources

About