A Neural Networks Approach to Detecting Lost Heritage in Historical Video

Condorelli, Francesca; Rinaudo, Fulvio; Salvadore, Francesco; Tagliaventi, Stefano

doi:10.3390/ijgi9050297

Cited by 13 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reduced data will then be presented to help the authors correlate the novelties of the research to the past studies regarding the 2019 Election, especially women's participation in the event. The conclusion will then be drawn out when the researchers obtained a novelty within the study based on data reduction and the correlation to the past research (Condorelli et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

Evaluating Communication Patterns of Women Legislative Successors of Karawang in 2019 Election

Mayasari

Darmayanti

Tayo

et al. 2022

NJOC

View full text Add to dashboard Cite

IIn the dynamics of general elections, the discussion of women legislative candidates has always been an interesting topic because the proportion of 30% of women candidates’ minimum requirement is always difficult to fulfill by any political party. The difficulty of women legislative candidates penetrating parliamentary seats is a problem that must be resolved. Therefore, it is necessary to conduct qualitative research to formulate how the communication patterns carried out by women politicians in the Karawang Regency, who have succeeded in penetrating parliamentary seats through case study techniques during the research. The communication pattern that marks the women’s success in election contestation can be a guide or reference when other women party politicians enter politics and advance to become legislature members. This research is limited to women members of the legislature who come from the Golkar Party. The results showed that the success of women members of the Regional Legislative Assembly (DPRD) from the Golkar party in occupying seats in the DPRD was partly due to the communication patterns they succeeded in establishing. They build vertical, horizontal, formal, and informal communication patterns that apply more social and cultural approaches. The uniqueness is when social media is used as a tool for political campaigns today, the communication strategy developed by those women legislative candidates of the Golkar party does not take advantage of social media. This is because the targeted constituents are people in remote areas, so the communication pattern through a direct face-to-face approach is much more impactful than social media.Keywords: Women DPRD members of Karawang Regency, political communication patterns, 2019 general election ABSTRAKDalam dinamika pemilihan umum (pemilu) pembahasan mengenai calon anggota legislatif perempuan selalu menjadi topik yang menarik karena adanya proporsi 30% caleg perempuan yang selalu sulit dipenuhi oleh setiap partai politik. Sulitnya calon anggota legislatif perempuan menembus kursi parlemen merupakan masalah yang harus dicarikan solusinya. Dengan demikian, perlu dilakukan penelitian dengan menggunakan metode kualitatif untuk merumuskan bagaimana pola komunikasi yang telah dilakukan oleh para politisi perempuan di Kabupaten Karawang yang telah berhasil menembus kursi parlemen dengan studi kasus sebagai teknik penelitian. Pola komunikasi yang menandai keberhasilan kaum perempuan dalam kontestasi pemilu ini dapat menjadi pedoman ataupun acuan ketika pihak lain yang juga perempuan akan terjun ke dunia politik dan akan maju menjadi anggota legislatif. Penelitian ini dibatasi hanya pada anggota legislatif perempuan yang berasal dari Partai Golkar. Hasil penelitian menunjukkan bahwa keberhasilan para anggota DPRD perempuan dari Partai Golkar dalam menduduki kursi di DPRD salah satunya disebabkan oleh pola komunikasi yang berhasil mereka bangun. Adapun pola komunikasi yang mereka bangun tersebut adalah pola komunikasi vertikal, horizontal, formal, informal yang lebih cenderung menerapkan pendekatan sosial dan budaya. Saat media sosial dijadikan alat kampanye politik dewasa ini, strategi komunikasi yang dibangun para calon anggota legislatif perempuan di Kabupaten Karawang yang berasal dari Partai Golkar ini tidak memanfaatkan media sosial. Hal ini disebabkan konstituen yang menjadi sasarannya adalah masyarakat pelosok yang belum memiliki pemahaman awam terhadap teknologi sehingga pola komunikasi melalui tatap mula langsung jauh lebih berdampak dibandingkan dengan penggunaan media sosial.Kata Kunci: Anggota DPRD perempuan Kabupaten Karawang, pola komunikasi politik, Pemilu 2019

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluating Communication Patterns of Women Legislative Successors of Karawang in 2019 Election

Mayasari

Darmayanti

Tayo

et al. 2022

NJOC

View full text Add to dashboard Cite

show abstract

“…As an additional perspective, there is also ongoing research regarding historical aerial images (Verhoeven and Vermeulen, 2016; Feurer and Vinatier, 2018; Giordano et al, 2018) as well as historical video material (Condorelli et al, 2020). However, the algorithms used in these works are not always transferable to terrestrial urban images.…”

Section: Related Researchmentioning

confidence: 99%

An automatic workflow for orientation of historical images with large radiometric and geometric differences

Maiwald

Maas

2021

The Photogrammetric Record

View full text Add to dashboard Cite

This contribution proposes a workflow for a completely automatic orientation of historical terrestrial urban images. Automatic structure from motion (SfM) software packages often fail when applied to historical image pairs due to large radiometric and geometric differences causing challenges with feature extraction and reliable matching. As an innovative initialising step, the proposed method uses the neural network D2‐Net for feature extraction and Lowe’s mutual nearest neighbour matcher. The principal distance for every camera is estimated using vanishing point detection. The results were compared to three state‐of‐the‐art SfM workflows (Agisoft Metashape, Meshroom and COLMAP) with the proposed workflow outperforming the other SfM tools. The resulting camera orientation data are planned to be imported into a web and virtual/augmented reality (VR/AR) application for the purpose of knowledge transfer in cultural heritage.

show abstract

“…Of course, in the field of heritage documentation, conservation, and valorisation, there is a particular focus on developing these increasingly efficient solutions, as evidenced by numerous studies and research carried out in the last few years (Fiorucci et al, 2020;Felicetti, Paolanti, Zingaretti, Pierdicca & Malinverni, 2020). In fact, recently, deep-learning strategies have been often applied by researchers operating in the fieldwork of geomatics and heritage documentation, for example, to automatically recognise pre-established elements in digital images (Condorelli, Rinaudo, Salvadore, & Tagliaventi, 2020) or to perform classification of architectural heritage (Llamas, Lerones, Medina, Zalama, & Gómez-García-Bermejo, 2017).…”

Section: Deep Learning and Cultural Heritagementioning

confidence: 99%

Multiclass semantic segmentation for digitisation of movable heritage using deep learning techniques

Patrucco

Setragno²

2021

Virtual archaeol. rev.

View full text Add to dashboard Cite

Digitisation processes of movable heritage are becoming increasingly popular to document the artworks stored in our museums. A growing number of strategies for the three-dimensional (3D) acquisition and modelling of these invaluable assets have been developed in the last few years. Their objective is to efficiently respond to this documentation need and contribute to deepening the knowledge of the masterpieces investigated constantly by researchers operating in many fieldworks. Nowadays, one of the most effective solutions is represented by the development of image-based techniques, usually connected to a Structure-from-Motion (SfM) photogrammetric approach. However, while images acquisition is relatively rapid, the processes connected to data processing are very time-consuming and require the operator’s substantial manual involvement. Developing deep learning-based strategies can be an effective solution to enhance the automatism level. In this research, which has been carried out in the framework of the digitisation of a wooden maquettes collection stored in the ‘Museo Egizio di Torino’, using a photogrammetric approach, an automatic masking strategy using deep learning techniques is proposed, to increase the level of automatism and therefore, optimise the photogrammetric pipeline. Starting from a manually annotated dataset, a neural network was trained to automatically perform a semantic classification to isolate the maquettes from the background. The proposed methodology allowed the researchers to obtain automatically segmented masks with a high degree of accuracy. The workflow is described (as regards acquisition strategies, dataset processing, and neural network training). In addition, the accuracy of the results is evaluated and discussed. Finally, the researchers proposed the possibility of performing a multiclass segmentation on the digital images to recognise different object categories in the images, as well as to define a semantic hierarchy to perform automatic classification of different elements in the acquired images.Highlights:<ul><li>In the framework of movable heritage digitisation processes, many procedures are very time-consuming, and they still require the operator’s substantial manual involvement.</li><li>This research proposes using deep learning techniques to enhance the automatism level in the generation of exclusion masks, improving the optimisation of the photogrammetric procedures.</li><li>Following this strategy, the possibility of performing a multiclass semantic segmentation (on the 2D images and, consequently, on the 3D point cloud) is also discussed, considering the accuracy of the obtainable results.</li></ul>

show abstract

A Neural Networks Approach to Detecting Lost Heritage in Historical Video

Cited by 13 publications

References 20 publications

Evaluating Communication Patterns of Women Legislative Successors of Karawang in 2019 Election

Evaluating Communication Patterns of Women Legislative Successors of Karawang in 2019 Election

An automatic workflow for orientation of historical images with large radiometric and geometric differences

Multiclass semantic segmentation for digitisation of movable heritage using deep learning techniques

Contact Info

Product

Resources

About