Newest papers

A Flexible ROI Analysis Tool for Spatially Consistent Vegetation Index Extraction from Turfgrass Imagery

Kibon Ku, Thai Thanh Tuan, Jinhyun Ahn · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26719 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La imagen multispectral de serie de tiempo se utiliza ampliamente para evaluar la condición de la turba; sin embargo, la extracción de los valores del índice de vegetación (VI) de nivel de parcelas sigue siendo laborable cuando las posiciones de la cámara varían entre las adquisiciones y el seguimiento automatizado de parcelas es poco fiable. Hemos desarrollado una herramienta de software de código abierto que incluye (i) una interfaz gráfica de usuario (GUI) para la colocación interactiva de las regiones de interés ajustables de orientación (ROI) con subdivisión de $N-way para coincidir con la geometría de parcelas y (ii) un script de procesamiento de parcelas que calcula los valores medios de VI de nivel de parcelas a partir de rastros de puntos flotantes de banda única

Machine translation (Meta M2M100); the English original follows.

Abstract

Time-series multispectral imaging is widely used to assess turfgrass condition; however, extracting plot-level vegetation index (VI) values remains labor-intensive when camera positions vary between acquisitions and automated plot tracking is unreliable. We developed an open-source software tool comprising (i) a graphical user interface (GUI) for the interactive placement of orientation-adjustable regions of interest (ROIs) with $N$-way subdivision to match plot geometry and (ii) a batch-processing script that computes plot-level mean VI values from single-band floating-point rasters and exports measurements and ROI coordinates in JSON format for reuse. Saved coordinates can be reapplied to measure NDVI, NDRE, and SAVI from identical pixel regions within a single time point without re-delineating ROIs. In a demonstration using rail-mounted multispectral turfgrass imagery (18 images), plot-level mean values were extracted in a single session, with coordinates reused directly for NDRE and SAVI rasters. The system reads non-georeferenced pixel-coordinate rasters natively, does not require GIS expertise, and supports reproducible VI quantification where static sensor deployment is impractical.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Multispectral image, Computer vision, Pixel, Remote sensing, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange