Publicación: Generación automática de modelos 3D con escáneres y tecnologías inteligentes
Cargando...
Archivos
Fecha
2013-12-19
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Ingeniería de Software y Sistemas Informáticos
Resumen
La obtención de modelos de información de edificios habitados a partir de escáneres láser constituye una línea de investigación emergente en el ámbito de la ingeniería inversa. La generación de estos modelos se ha llevado a cabo durante los últimos años de una forma manual, lo que supone un trabajo complejo y tedioso y pone de manifiesto la necesidad de buscar la automatización de este proceso. En esta tesis se presenta un trabajo dedicado a la reconstrucción automática de escenarios interiores. En primer lugar se han procesado nubes de puntos obtenidas mediante escáneres láser desde ubicaciones estratégicas en diferentes escenarios, con el objetivo de segmentar las paredes y proporcionar modelos 3D de representación de contorno (o B-Rep), en los cuales se establece una relación entre los diferentes elementos constructivos identificados en un edificio: muros, suelos, techos, columnas, puertas y ventanas. Pero, además de estos componentes de tipo constructivo, las habitaciones contienen en su interior una serie de elementos de mobiliario básico que también es preciso reconocer y ubicar. Durante los últimos años se han desarrollado para este fin diferentes algoritmos de identificación y posicionamiento 3D de objetos en entornos interiores. Sin embargo, estos procesos suelen ser complejos, computacionalmente costosos y de resultados poco precisos. En la tesis se proponen soluciones más flexibles y originales a este problema, planteadas a partir de la combinación de escáneres láser con tecnologías inteligentes. Más concretamente, se han utilizado sistemas de identificación por radio frecuencia (RFID). Mediante la utilización de este tipo de sistemas puede obtenerse información relacionada con la geometría de las piezas de mobiliario, a través de la lectura de un conjunto de etiquetas RFID que, adheridas a los muebles, almacenan estos datos. El procesamiento de esta información facilita, en gran medida, la identificación y el posicionamiento de estos elementos en una nube de puntos. A partir de esta propuesta se lleva a cabo un detallado análisis de diferentes entornos, así como una evaluación en profundidad de los resultados logrados en cada uno de ellos. Del trabajo desarrollado se concluye que los modelos 3D obtenidos de forma automática, a través de la técnica mixta escáner-RFID, poseen una precisión aceptable y podrían ser utilizados para otros procesos posteriores relacionados con el conocimiento de un escenario.
The automatic generation of building information models with laser scanners is an emergent research line in the reverse engineering field. The creation of this kind of models has been made by hand during the last years, leading to suppose a complex and tedious work. Therefore, the automation of this process is an interesting challenge. In this thesis, a work focused on the automatic reconstruction of inhabited interiors is presented. Firstly, 3D point clouds, which are acquired from strategic positions, are processed in order to identify and pose the structural components of the scene. Then, a boundary representation (B-Rep) model is created. These models contain the location and relationships of structural elements of inhabited scenarios such as walls, ceilings, floors, columns, doors and windows. The scene, enclosed by the calculated B-Rep model, is also composed of a set of basic pieces of furniture. These “non-permanent” elements, which can be relocated or removed in the scene, are also identified and positioned. Some authors have developed different algorithms in order to localize objects in interior environments. However, these processes (mainly based on Computer Vision) are complex, computationally expensive and the results are unaccurate. In this dissertation, a more flexible and novel solution to this problem is proposed, combining laser scanners and radio-frequency identitication (RFID) technologies. The general strategy consists of carrying out a selective and sequential segmentation of the point cloud by means of different algorithms which depend on the information that the RFID tags provide. These tags, attached to pieces of furniture, store geometrical information of the objects, making the identification and positioning of basic elements in the scene faster and easier. This method has been tested in real scenes yielding promising results. An in depth assessment has been performed, analyzing how reliably these elements can be detected and how accurately they are modeled. Finally, we can conclude that this proposal yields accurate 3D models which may be used for further purposes related to the scene understanding.
The automatic generation of building information models with laser scanners is an emergent research line in the reverse engineering field. The creation of this kind of models has been made by hand during the last years, leading to suppose a complex and tedious work. Therefore, the automation of this process is an interesting challenge. In this thesis, a work focused on the automatic reconstruction of inhabited interiors is presented. Firstly, 3D point clouds, which are acquired from strategic positions, are processed in order to identify and pose the structural components of the scene. Then, a boundary representation (B-Rep) model is created. These models contain the location and relationships of structural elements of inhabited scenarios such as walls, ceilings, floors, columns, doors and windows. The scene, enclosed by the calculated B-Rep model, is also composed of a set of basic pieces of furniture. These “non-permanent” elements, which can be relocated or removed in the scene, are also identified and positioned. Some authors have developed different algorithms in order to localize objects in interior environments. However, these processes (mainly based on Computer Vision) are complex, computationally expensive and the results are unaccurate. In this dissertation, a more flexible and novel solution to this problem is proposed, combining laser scanners and radio-frequency identitication (RFID) technologies. The general strategy consists of carrying out a selective and sequential segmentation of the point cloud by means of different algorithms which depend on the information that the RFID tags provide. These tags, attached to pieces of furniture, store geometrical information of the objects, making the identification and positioning of basic elements in the scene faster and easier. This method has been tested in real scenes yielding promising results. An in depth assessment has been performed, analyzing how reliably these elements can be detected and how accurately they are modeled. Finally, we can conclude that this proposal yields accurate 3D models which may be used for further purposes related to the scene understanding.
Descripción
Categorías UNESCO
Palabras clave
Citación
Centro
Facultades y escuelas::Escuela Internacional de Doctorado
Departamento
No procede