Pasar al contenido principal

NUEVOS METODOS PARA ESTIMACIONES DE EMISION DE CARBONO EN INCENDIOS MEDIANTE INTELIGENCIA ARTIFICIAL APLICADA A NUBES DE PUNTOS TERRESTRES EN 3D

PRE2022-104159

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Desarrollar, Atraer y Retener Talento
Subprograma Subprograma Estatal de Formación
Convocatoria Contratos Predoctorales
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

SegmentedForests: a labelled dataset of terrestrial LiDAR point clouds for semantic segmentation of forests

  • Laino, Diego
  • Cobo, Carlos
  • Ordóñez, Celestino
  • Bolaños, Rodolfo
  • Janvier, Romain
  • Giulioni, Federico
  • Hermannn, Miriam
  • Hudak, Andrew
  • Parsons, Russell
  • Santín, Cristina
Semantic segmentation of point clouds using deep learning (DL) has been the subject of research in forestry in recent years due to its potential applications. Several scientific and management disciplines, such as biodiversity monitoring, ecosystem carbon assessments, or forest management could benefit from this technique. However, it requires manual segmentation of point clouds to be used as training data. This process is highly labour-intensive and time-consuming, and there is a notable lack of publicly available datasets to support the development of accurate DL semantic segmentation models for forestry and forest ecology applications. Here, we present SegmentedForests, a curated dataset of manually segmented ground-based point clouds from forest plots, specifically designed to facilitate the training and validation of semantic segmentation models. This publicly available dataset contains >920 million labelled points from 14 forest plots, acquired using both terrestrial laser scanning (TLS) and mobile laser scanning (MLS) technologies. It covers two hectares of broadleaf, conifer, and mixed stands from different bioclimatic regions and features >1600 trees across 16 tree species. Each point cloud is labelled into multiple vegetation classes (up to 16), such as tree stems, branches, grass, shrubs, and down wood, as well as non-vegetation elements commonly present in forest scenes, including rocks, people, and stakes. Data splits to facilitate DL model development using our dataset are provided as well. The dataset is available at https://zenodo.org/records/17396681. By releasing this annotated dataset, we seek to address the critical need for publicly available, high-quality training data for DL models that perform semantic segmentation of ground-based point clouds in forest ecosystems., This work was supported by the UK NERC project (NE/T001194/1): ‘Advancing 3D Fuel Mapping for Wildfire Behaviour and Risk Mitigation Modelling’, the Spanish Knowledge Generation project (PID2021-126790NB-I00): ‘Advancing carbon emission estimations from wildfires applying artificial intelligence to 3D terrestrial point clouds’, (grant PRE2022-104159) funded by MCIN/AEI/10.13039/501100011033 and FSE+, research grant ‘FIREPROs’ (IDE/2024/000780) funded by the Principality of Asturias Government (Spain), COST Action 3DForEcoTech CA20118 supported by COST (European Cooperation in Science and Technology) and the US DoD SERDP/ESTCP projects (RC20-1025), (RC23-7626), and (RC20-1046)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Datos de investigación Set de datos (Dataset)

SegmentedForests: a labelled dataset of terrestrial LiDAR point clouds for semantic segmentation of forests [Dataset]

  • Laino, Diego
  • Cobo, Carlos
  • Ordóñez, Celestino
  • Bolaños, Rodolfo
  • Janvier, Romain
  • Giulioni, Federico
  • Hermannn, Miriam
  • Hudak, Andrew
  • Parsons, Russell
  • Santín, Cristina
The point clouds are stored in LAZ files. 3DFin configuration files (.INI) with the parameters used to process each point cloud are also included., SegmentedForests is a curated dataset of manually segmented ground-based point clouds from forest plots, specifically designed to facilitate the training and validation of semantic segmentation models. This publicly available dataset contains >920 million labelled points from 14 forest plots, acquired using both terrestrial laser scanning (TLS) and mobile laser scanning (MLS) technologies. It covers two hectares of broadleaf, conifer, and mixed stands from different bioclimatic regions and features >1600 trees across 16 tree species. Each point cloud is labelled into multiple vegetation classes (up to 16), such as tree stems, branches, grass, shrubs, and down wood, as well as non-vegetation elements commonly present in forest scenes, including rocks, people, and stakes. Data splits to facilitate DL model development using our dataset are provided as well., NERC Environmental Bioinformatics Centre; Advancing 3D Fuel Mapping for Wildfire Behaviour and Risk Mitigation ModellingNE/T001194/1; Ministerio de Ciencia, Innovación y Universidades Advancing carbon emission estimations from wildfires applying artificial intelligence to 3D terrestrial point cloudsPID2021-126790NB-I00; Agencia Estatal de Investigación MCIN/AEI/10.13039/501100011033; Gobierno del Principado de Asturias FIREPROsIDE/2024/000780; Strategic Environmental Research and Development Program RC20-1025; Strategic Environmental Research and Development Program RC23-7626; Strategic Environmental Research and Development Program RC20-1046, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Vegetation Biomass Estimation Using 3D Ground-Based Point Clouds: A Systematic Review

  • Bolaños, Rodolfo
  • Santín, Cristina
  • Laino, Diego
  • Lines, Emily R.
  • Ordóñez, Celestino
  • Álvarez Toboada, Flor
  • Loudermilk, E. Louise
  • Cabo, Carlos
[Purpose of Review] Ground-based 3D point cloud technologies, including static terrestrial laser scanning (TLS), mobile laser scanning (MLS), and close-range photogrammetry, are increasingly used for estimation of aboveground vegetation biomass as they provide detailed structural representations across vegetation types; however, a comprehensive synthesis of how point-cloud data are translated into biomass estimates remains lacking. This review evaluates current approaches, performance patterns, and methodological gaps in biomass estimation using 3D ground-based point clouds., [Recent Findings] We systematically reviewed and analyzed 160 research articles (comprising 171 device-specific studies) published until the end of 2025 (first appearing in 2010). Research was dominated by tree-based applications (74%), with limited attention to shrubs, grasslands or crops. TLS was the prevailing acquisition technology (78%), although MLS adoption is growing. Biomass estimation primarily relied on allometric equations, volume-based reconstructions (e.g., quantitative structure models, voxelizations, convex hull), and parametric regression models. Reported model performance was generally high in tree- and shrub-based studies (median R2 > 0.8), but more variable in non-woody vegetation types. Despite rapid advances in 3D sensing, point-cloud-native deep-learning approaches remain rarely implemented in biomass estimation workflows., [Summary] Ground-based 3D sensing is maturing technically, yet methodological heterogeneity persists. Many workflows still depend on destructive calibration data, semi-manual preprocessing, and non-standardized modelling strategies, limiting reproducibility and cross-study comparability. Multi-sensor integration is emerging but lacks consistent upscaling frameworks. Future research should expand coverage of underrepresented vegetation types, promote standardized and automated processing pipelines, and systematically evaluate point-cloud-native deep learning architectures, both for extracting structural proxies and for assessing their capacity to estimate biomass directly., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was supported by Grant [PRE2022-104159] funded by MICIU/AEI/10.13039/501100011033 and “ESF + ”; by the project “Advancing carbon emission estimations from wildfires applying artificial intelligence to 3D terrestrial point clouds” [PyroCarbon3D, PID2021-126790NB-I00]; the UK-RI NERC project grant [NE/T001194/1]: “Advancing 3D Fuel Mapping for Wildfire Behaviour and Risk Mitigation Modelling”; and by the research grant ‘FIREPROs’ [IDE/2024/000780] funded by the Principality of Asturias Government (Spain), Emily R Lines was funded by a UKIR Future Leaders Fellowship (MR/Y033981/1)., Peer reviewed