GEOBIA is an alternative to create and update land cover maps. In this work we assessed the combination of geographic datasets of the Cajas National Park (Ecuador) to detect which is the appropriate dataset-algorithm combination for the classification tasks in the Ecuadorian Andean region. The datasets included high resolution data as photogrammetric orthomosaic, DEM and derivated slope. These data were compared with free Sentinel imagery to classify natural land covers. We evaluated two aspects of the classification problem: the appropriate algorithm and the dataset combination. We evaluated SMO, C4.5 and Random Forest algorithms for the selection of attributes and classification of objects. The best results of kappa in the comparison of algorithms of classification were obtained with SMO (0.8182) and Random Forest (0.8117). In the evaluation of datasets the kappa values of the photogrammetry orthomosaic and the combination of Sentinel 1 and 2 have similar values using the C4.5 algorithm.
Resumen a conservación del patrimonio edificado y el mantenimiento de las áreas verdes son actividades de importancia en la planificación de un territorio urbano. Los métodos tradicionales de recolección de cartografía suelen demandar elevados costos y períodos de tiempo relativamente largos. Con el uso de vehículos aéreos no tripulados (VANT) se aspira obtener productos cartográficos y modelos 3D. El uso de técnicas fotogramétricas puede convertir las fotografías capturadas por el dron en información digital como ortofotos, modelos digitales de superficies o modelos 3D. La información de estos bienes urbanos, en series temporales, permitirá evaluar los daños y cambios de los mismos a lo largo del tiempo y, de esta manera, ejecutar acciones de protección y mitigación de sus impactos.Palabras clave: áreas verdes, dron, modelos 3D, ortofotos, patrimonio Abstract:The conservation of the built heritage and the maintenance of the green areas are important activities in the planning of an urban territory. Traditional methods of mapping often require high costs and relatively long periods of time. The use of unmanned aerial vehicles (UAVs) aims to obtain cartographic products and 3D models. The use of photogrammetric techniques can convert photographs captured by the dron into digital information such as orthophotos, digital surface models or 3D models. The information of these urban goods in time series will allow to evaluate the damages and changes of the same over time and thus to execute actions of protection and mitigation of their impacts in a timely manner.
el estándar Web Processing Service provee de reglas para servicios de procesamiento de datos geoespaciales, desarrollado en esta investigación como un prototipo para visualización y consultas sobre una capa de la infraestructura de datos espaciales de la Universidad del Azuay. Se implementó la aplicación CropCoverage y Affine, mediante el protocolo HTTP, con el métodoPOST. Estas operaciones mostraron facilidad para recortar cobertura libremente basándose en geometrías; y sencillez para modificaciones lineales y traslaciones en el espacio, respectivamente. La simplicidad y efectividad de la aplicación de las operaciones se vieron disminuidas por lo redundante de ingresar los datos cada vez que se requería ejecutarlos. Palabras clave: Web Processing Service, CropCoverage, Affine AbstractThe Web Processing Service standard, provides rules for geospatial data processing services, developed in this research as a prototype for visualization and queries on a layer of the Spatial Data Infrastructure of the University of Azuay. CropCoverage and Affine, through the HTTP protocol, were implemented with the POST method; These operations showed ease of trimming coverage freely based on geometries; And simplicity for linear modifications and translations in space, respectively. The simplicity and effectiveness of the application of the operations were reduced by the redundancy of entering the data each time it is required to execute them. Keywords: Web Processing Service, CropCoverage, Affine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.