Meshlets based data model for real-time interaction and analysis with hyper-spectral vegetation data

Hyperspectral sensors are revolutionizing precision agriculture by capturing spectral responses across a broad range of the spectrum. Furthermore, the integration of these data with three-dimensional information is increasingly crucial for generating enriched spatial and spectral datasets, enabling the application of more sophisticated analytical techniques. However, the analysis of this information lacks agility, and its visualization and interactive exploration are not integrated within a unified framework. The high dimensionality and volume of the fused information pose significant computational and visualization constraints for real-time processing. This paper presents the methodologies that makes possible advanced analysis of hyperspectral data fused with 3D point clouds to achieve advanced analysis. We introduce GEU, a novel interactive framework, which facilitates real-time interaction, visualization and spectral and spatial analysis. To achieve efficient handling of the fused data, this approach leverages meshlets, implemented directly on GPUs, for optimized spatial data management. A parallel data structure, termed Meanlet, representing the average spectral behavior of these spatial clusters, is maintained in main memory. The results in an integrated framework enabling real-time visualization, interaction, and analysis of hyperspectral data, including spectral information fused with 3D point clouds. • Hyperspectral data fused with 3D point clouds are traditionally massive data. • The Meanlet data structure is able to manage interactively and in real-time this data. • The Meanlet is based on meshlets for spatial and spectral clustering. • Advanced and accurate spectral analysis through a graphical user interface.