Many projects concerning the protection, conservation, restoration, and dissemination of cultural heritage are being carried out around the world due to its growing interest as a driving force of socio-economic development. The existence of reliable, digital three-dimensional (3D) models that allow for the planning and management of these projects in a remote and decentralized way is currently a growing necessity. There are many software tools to perform the modeling and complete three-dimensional documentation of the intervened monuments. However, the Architecture, Engineering and Construction (AEC) sector has adopted the Building Information Modeling (BIM) standard over the last few decades due to the progress that has been made in its qualities and capabilities. The complex modeling of cultural heritage through commercial BIM software leads to the consideration of the concept of Heritage BIM (H-BIM), which pursues the modeling of architectural elements, according to artistic, historical, and constructive typologies. In addition, H-BIM is considered to be an emerging technology that enables us to understand, document, advertize, and virtually reconstruct the built heritage. This article is a review of the existing literature on H-BIM and its effective implementation in the cultural heritage sector, exploring the effectiveness and the usefulness of the different methodologies that were developed to model families of elements of interest.

Abstract:The classification of the images taken during the measurement of an architectural asset is an essential task within the digital documentation of cultural heritage. A large number of images are usually handled, so their classification is a tedious task (and therefore prone to errors) and habitually consumes a lot of time. The availability of automatic techniques to facilitate these sorting tasks would improve an important part of the digital documentation process. In addition, a correct classification of the available images allows better management and more efficient searches through specific terms, thus helping in the tasks of studying and interpreting the heritage asset in question. The main objective of this article is the application of techniques based on deep learning for the classification of images of architectural heritage, specifically through the use of convolutional neural networks. For this, the utility of training these networks from scratch or only fine tuning pre-trained networks is evaluated. All this has been applied to classifying elements of interest in images of buildings with architectural heritage value. As no datasets of this type, suitable for network training, have been located, a new dataset has been created and made available to the public. Promising results have been obtained in terms of accuracy and it is considered that the application of these techniques can contribute significantly to the digital documentation of architectural heritage.

In this paper, a new approach for the virtual modeling and reconstruction of Architectural Heritage is presented. The graphic and semantic information required to determine the conservation status of the analyzed buildings, obtained from point clouds and historical and bibliographical data, are combined. The modeled components are used to create a library of parametric elements under the concept of Heritage Building Information Modeling (HBIM). This represents a solution for the 3D modeling of a wide range of buildings in the same style, due to the flexibility of the modeled elements which can change in shape and proportions, thus adapting to new requirements. Moreover, technical documentation and quantitative and qualitative information can be produced, allowing detailed analysis in a remote and multidisciplinary way within the general framework of "Smart heritage".

No abstract

No abstract