1,720,983 research outputs found
Processing historical photographs and film footage with Photogrammetry and Artificial Intelligence for Cultural Heritage documentation and virtual reconstruction
Full text linkThe specific objective of this thesis is to offer an excursion through the metric potentialities of different data available in historical archives, by considering the essential role of photogrammetry. The aim is to explore how metric information about buildings which no longer exist or transformed over time could be extracted from old photographs and videos of different quality, for their 3D virtual reconstruction analysing the material stored in historical archives to support researchers and experts in historical research of Cultural Heritage.In order to process these data and to obtain metrically certified results, a modification of the algorithms of the standard photogrammetric pipeline was necessary. This purpose was achieved with the use of open-source Structure-from-Motion algorithms and the creation of a specific benchmark to compare the results.Besides the processing of historical photograph, photogrammetry is combined with Artificial Intelligence to improve ways to search for architectural heritage in video material and to reduce the effort of manually examining them by the operator in the archive in terms of efficiency and time
Photogrammetry and Deep Learning to improve Cultural Heritage records: extracting 3D metric information from historical images
Full text linkL'abstract è presente nell'allegato / the abstract is in the attachmen
Una prima proposta per un algoritmo per la valutazione degli errori delle restituzioni fotogrammetriche (A first proposal of an algorithm for the evaluation of the error in the photogrammetric restitution)
No full textL’errore è qualcosa di non controllabile ‘a prescindere’, quasi sempre di natura incerta e che non può essere mai del tutto eliminato; eppure, proprio per queste sue caratteristiche intrinseche ha da sempre affascinato filosofi, scrittori, psicologi, scienziati e matematici che hanno elaborato teorie, studi e ricerche su questo tema, con un atteggiamento quasi di sfida per la sua complessa natura.
Gli errori oggetto di questo lavoro riguardano il rilievo architettonico, in particolare, l’implementazione di tecniche image-based svolte con la collaborazione del Laboratorio de Arqueología y Arquitectura de la Ciudad di Granada del Prof. Antonio Almagro Gorbea. Il caso di studio è stata la Sacra Capilla del Salvador di Úbeda, manufatto dichiarato patrimonio mondiale dell’umanità dall’UNESCO nel lontano 2003, magnifico esempio di architettura e urbanistica rinascimentale.
È nata così l’idea di sviluppare una sperimentazione per la codifica di un algoritmo per la valutazione della propagazione degli errori che si generano con le tecniche fotogrammetriche; infatti, se in ambito topografico esiste una affermata e consolidata trattatistica sulla teoria degli errori (o delle misurazioni), strettamente correlata a studi probabilistici e statistici, per i rilievi image-based sono pochi i riferimenti in letteratura circa queste problematiche e su come gli errori si generano durante il processo e su quanto influiscono sulle misure e con che peso. È banale osservare empiricamente come con l’uso di paradigmi fotogrammetrici avanzati vi sia un maggior controllo nominale di questi errori; tuttavia il ricorso a pipeline che prevedono l’implementazione in serie o parallelo di più ambienti software può condurre, se non controllato, alla generazione di gravi incertezze. Nella proposta avanzata ha assunto particolare importanza la valutazione e l’interpretazione dei dati da parte dell’operatore – in maniera soggettiva ma non arbitraria –, con un approccio matematico che incorpora nella descrizione dell’informazione l’incertezza, definendo, tramite la logica Fuzzy, un grado di appartenenza e affidabilità alle tecniche fotogrammetriche (nel caso di studio, rispetto a quelle range-based). Secondo questa ipotesi e dopo aver passato in rassegna le fasi che compongono il processo, è stato affrontato un resoconto sugli strumenti hardware utilizzati per il rilievo di fattispecie, proseguendo, poi, con l’analisi degli applicativi software, classificati a seconda se destinati all’elaborazione indiretta dei dati o alla restituzione grafica. Successivamente, dopo uno studio della tipologia degli errori generabili in ogni singolo step e da ogni singolo strumento, sono stati delineati e assegnati i pesi, per una stima finale dell’errore.
Infine, dopo averne determinato la propagazione si è proceduto a testare l’algoritmo mediante un confronto tridimensionale, con l’intento di validare analiticamente l’approccio proposto in base alla convergenza dei primi risultati restituiti.Errors cannot be controlled, they are usually uncertain in nature and cannot be completely eliminated. Due to these intrinsic characteristics, errors have always fascinated philosophers, writers, psychologists, scientists and mathematicians who have developed theories, studies and research on this topic despite the complexity of its nature.
The errors considered in this paper were taken from an architectural survey and concern in particular, the implementation of image-based techniques. The experimentation with these techniques was carried out in collaboration with Prof. Antonio Almagro Gorbea’s Laboratorio de Arqueología y Arquitectura de la Ciudad in Granada (Spain). The case study was the Holy Chapel of the Saviour in Úbeda (Spain), a superb example of urban renaissance architecture, which was declared World Heritage by UNESCO in 2003.
It was in the context of these activities that the idea of developing of an algorithm for the evaluation of error propagation generated in image-based and range-based survey techniques was conceived. In the topographic field there is an established and consolidated treatise on the theory of errors (or measurements) closely related to probabilistic and statistical studies; but for image-based and range-based survey, there are few references in the literature about this topic. In particular, it is interesting to note how errors are generated during the survey process and how and to what extent they influence the measurements. It is banal to observe empirically that with the use of advanced photogrammetric paradigms there is a greater nominal control of these errors. However, the use of pipelines that provide for the implementation of several software environments in series or in parallel, if not controlled, can lead to the generation of serious uncertainties.
In this proposal, the evaluation and interpretation of data by the operator - in a subjective but not arbitrary way – is considered particularly important. The mathematical approach adopted incorporates the uncertainty in the description of the information, by defining, through Fuzzy logic, a degree of reliability and belonging for the photogrammetric techniques (in the case study, compared to laser scanners). According to this hypothesis, and after examining the phases of the process, a report on the hardware tools used in the survey case was compiled, , then, w the analysis of software, was classified according to whether it was intended for indirect data processing or graphic restitution. Subsequently, after a study of the types of errors that can be generated in each single step and from each individual instrument, the relative weights were outlined and assigned (according to what was previously highlighted), for a final estimate of the error.
Thus, after determination of the propagation, a test of the algorithm by a three-dimensional comparison was performed with the aim of analytically validating the proposed approach according to the convergence of the first results returned
Integration of 3D modelling with photogrammetry applied on historical images for cultural heritage.
Full text linkThe recovery of past architecture through 3D modelling is an important challenge today to the preservation of heritage. Decisive support for the interpretation of architecture can certainly come from historical images and old photographs that fix a portion of space at a specific time, keeping it unchanged over the years. This acquisition is decisive for studying architectures of the past that can be reinterpreted and analysed. Photos, in fact, capture the advance of time and the life of a building at a precise historical moment, becoming essential documents for the study and knowledge of heritage. An additional advantage is when these old images can be processed through Structure for Motion procedures and, the results obtained, used as support for a 3D model of buildings that no longer exist. The work shows an interesting pipeline applied to the Caltanissetta Centrale Station and the possibility of “recovering”, even if virtually, a phase of its architectural evolution through the integration of photogrammetry from historical images and 3D modelling. The case study is an opportunity to analyse the procedure still under development, as well as to identify the main difficulties encountered in this process and possible future developments
A Neural Networks Approach to Detecting Lost Heritage in Historical Video
Full text linkDocumenting Cultural Heritage through the extraction of 3D measures with photogrammetry is fundamental for the conservation of the memory of the past. However, when the heritage has been lost the only way to recover this information is the use of historical images from archives. The aim of this study is to experiment with new ways to search for architectural heritage in video material and to save the effort of the operator in the archive in terms of efficiency and time. A workflow is proposed to automatically detect lost heritage in film footage using Deep Learning to find suitable images to process with photogrammetry for its 3D virtual reconstruction. The performance of the network was tested on two case studies considering different architectural scenarios, the Tour Saint Jacques which still exists for the tuning of the networks, and Les Halles to test the algorithms on a real case of an architecture which has been destroyed. Despite the poor quantity and low quality of the historical images available for the training of the network, it has been demonstrated that, with few frames, it was possible to reach the same results in terms of performance of a network trained on a large dataset. Moreover, with the introduction of new metrics based on time intervals the measure of the real time saving in terms of human effort was achieved. These findings represent an important innovation in the documentation of destroyed monuments and open new ways to recover information about the past
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
