Abstract
Geological objects are characterized by a high complexity inherent to a strong compositional variability at all scales and usually unclear class boundaries. Therefore, dedicated processing schemes are required for the analysis of such data for mineralogical mapping. On the other hand, the variety of optical sensing technology reveals different data attributes and therefore multi-sensor approaches are adapted to solve such complicated mapping problems. In this paper, we devise an adapted multi-optical sensor fusion (MOSFus) workflow which takes the geological characteristics into account. The proposed processing chain exhaustively covers all relevant stages, including data acquisition, preprocessing, feature fusion, and mineralogical mapping. The concept includes (i) a spatial feature extraction based on morphological profiles on RGB data with high spatial resolution, (ii) a specific noise reduction applied on the hyperspectral data that assumes mixed sparse and Gaussian contamination, and (iii) a subsequent dimensionality reduction using a sparse and smooth low rank analysis. The feature extraction approach allows one to fuse heterogeneous data at variable resolutions, scales, and spectral ranges and improve classification substantially. The last step of the approach, an SVM classifier, is robust to unbalanced and sparse training sets and is particularly efficient with complex imaging data. We evaluate the performance of the procedure with two different multi-optical sensor datasets. The results demonstrate the superiority of this dedicated approach over common strategies.
Highlights
Mineral mapping constitutes an important tool in many geological applications and related industry fields
For HyMiNoR, the tuning parameter was selected as λ = 1 while the default value used in [18] was λ = 10, as we found λ = 1 more suitable for the close-range imagery compared to remote sensing images used in [18]
For Sparse and smooth low-rank analysis (SSLRA), the tuning parameters were set as λ1 = λ2 = 0.05 and the number of features for the hyperspectral images was set to r = 10, and the final number of features that were fed to SVM was 77 (27 from RGB plus 50 from hyperspectral sensors)
Summary
Mineral mapping constitutes an important tool in many geological applications and related industry fields. Mineral exploration and mining are dependent on the accurate localization and characterization of target or indicator minerals at different scales of observation. Extensive sampling campaigns delivering kilometers of drill core or remote sensing data and minerals, often indistinguishable by eye, are only two of the logistical and technical challenges of traditional approaches. Fast, and non-invasive imaging techniques form the forefront of today’s developments to support geologists with this arduous task. Reflectance spectroscopy allows the rapid characterization of mineralogical samples by the analysis of reflected light over a specific wavelength range. Hyperspectral images, which are represented by hundreds of spectral channels, can be considered as a stack of several pixel vectors in which each pixel vector represents a spectrum in detail at a range of wavelengths.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
