Architecture Recognition by Means of Convolutional Neural Networks

Andrianaivo, Louis Nantenaina; D'Autilia, Roberto; Palma, Valerio

doi:10.5194/isprs-archives-xlii-2-w15-77-2019

Cited by 5 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…La fusione dei campi disciplinari è anche il punto di partenza per un cambiamento culturale che non distingue più tra discipline umanistiche, scientifi che e artistiche. (Andrianaivo et al, 2019). Dato lo scarso coinvolgimento dei ricercatori in ambito umanistico nella progettazione di infrastrutture su materiali del patrimonio storico, l'applicazione di metodi di IA nei progetti urbani e architettonici può migliorare la partecipazione degli utenti fi nali di tali strumenti.…”

Section: Stato Dell'arteunclassified

“…The blending of disciplinary fi elds is also the starting point for a cultural change that no longer differentiates between humanities, science and art disciplines. (Andrianaivo et al, 2019). Since the lack of involvement of the researcher in the humanities in the design of infrastructures on historical heritage material, the application of AI methods in urban and architecture projects can improve the participation of the fi nal users of such tools.…”

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

La documentazione del patrimonio culturale perduto mediante fotogrammetria e intelligenza artifi ciale

Condorelli¹

2023

Revista Mimesis

View full text Add to dashboard Cite

This research aims to give an analysis and assessment through the extraction of metricinformation from historical images and to experiment with its potentialities in the heritage fi eldwith the aim of valorising historical iconographical documentation. In particular the paperdeals with photogrammetry applied to historical images. A classifi cation and a state of the artof historical archives material considering their possible use in metric documentation and thussuitable for photogrammetry is performed. A photogrammetric workfl ow is proposed to processhistorical images and the maximum metric quality level reachable by the photogrammetricprocessing is investigated. Two case studies in Paris were chosen: the UNESCO HeritageTour Saint Jacques and the pavilions of Les Halles of the architect Victor Baltard. The twostudies represent different situations of heritage because the tower was transformed over timebut still exists and the pavilions were destroyed in 1971. Thus, it is possible to compare thedifferent results obtained from the implementation of the workfl ow to the two case studies.

show abstract

Section: Stato Dell'arteunclassified

Section: State Of the Artmentioning

confidence: 99%

La documentazione del patrimonio culturale perduto mediante fotogrammetria e intelligenza artifi ciale

Condorelli¹

2023

Revista Mimesis

View full text Add to dashboard Cite

show abstract

“…The highest accuracies achieved for monument recognition were 99.88% using MobileNet Architecture (11) and 99.4% in using InceptionV3 architecture (1). Andrianaivo, D'Autilia (11) used a manually collected dataset for 46 Monuments for the Central Archaeological Area in Rome.…”

Section: Literature Reviewmentioning

confidence: 99%

Indian Monument Recognition Using Deep Learning

et al. 2022

View full text Add to dashboard Cite

Monuments are physical structures built or created dedicated to a person or event. Their importance to the region they belong to makes their documentation and preservation important. Monuments being 3D objects, pose is an issue in terms of the difference in perception of the monument images. There can be an immense variation because of the viewpoint from which the image is being taken. To overcome this issue, Data Augmentation is used in this study. Random Flip, Random Rotation, Random Translation and Random Zoom, Random Contrast, Random Hue, Random Brightness, and Random Saturation operations under Data Augmentation are applied on the dataset. This research uses Deep Learning architectures on a hybrid dataset of “Indian Monument Recognition Dataset” and “Qutub Complex Monuments' Images Dataset.” InceptionV3, MobileNet, ResNet50, AlexNet, and VGG16 recognize the monuments with an accuracy of 97.79%, 93.73%, 86.47%, 68.88%, and 61.33% respectively.

show abstract

Digital Excavation of Mediatized Urban Heritage: Automated Recognition of Buildings in Image Sources

Mager

Hein

2020

View full text Add to dashboard Cite

Digital technologies provide novel ways of visualizing cities and buildings. They also facilitate new methods of analyzing the built environment, ranging from artificial intelligence (AI) to crowdsourced citizen participation. Digital representations of cities have become so refined that they challenge our perception of the real. However, computers have not yet become able to detect and analyze the visible features of built structures depicted in photographs or other media. Recent scientific advances mean that it is possible for this new field of computer vision to serve as a critical aid to research. Neural networks now meet the challenge of identifying and analyzing building elements, buildings and urban landscapes. The development and refinement of these technologies requires more attention, simultaneously, investigation is needed in regard to the use and meaning of these methods for historical research. For example, the use of AI raises questions about the ways in which computer-based image recognition reproduces biases of contemporary practice. It also invites reflection on how mixed methods, integrating quantitative and qualitative approaches, can be established and used in research in the humanities. Finally, it opens new perspectives on the role of crowdsourcing in both knowledge dissemination and shared research. Attempts to analyze historical big data with the latest methods of deep learning, to involve many people—laymen and experts—in research via crowdsourcing and to deal with partly unknown visual material have provided a better understanding of what is possible. The article presents findings from the ongoing research project ArchiMediaL, which is at the forefront of the analysis of historical mediatizations of the built environment. It demonstrates how the combination of crowdsourcing, historical big data and deep learning simultaneously raises questions and provides solutions in the field of architectural and urban planning history.

show abstract

Architecture Recognition by Means of Convolutional Neural Networks

Cited by 5 publications

References 18 publications

La documentazione del patrimonio culturale perduto mediante fotogrammetria e intelligenza artifi ciale

La documentazione del patrimonio culturale perduto mediante fotogrammetria e intelligenza artifi ciale

Indian Monument Recognition Using Deep Learning

Digital Excavation of Mediatized Urban Heritage: Automated Recognition of Buildings in Image Sources

Contact Info

Product

Resources

About