日本語フィールド
著者：M.R. Derbel, J. Makhlouf and N. Mishima題名：A basic analysis on urban landscape continuity in a lowland urban heritage using deep learning-based method発表情報：Lowland Technology International 2020, 22(2), pp.192- 199, International Association of Lowland Technology (IALT): ISSN 1344-9656 巻: 22 号: 2 ページ: 192-199キーワード：概要：Architectural intervention in urban heritage area is subject to numerous parameters making it a time-consuming process. Urban façade analyses are also one of the required long-term tasks held by the architect, especially in urban heritage area where pressure concerning the neighborhood harmony is often faced.
To address this issue, A computer vision method for an automatic evaluation of the urban façade is used to compare a set of façade’s pictures. The target area is Hizenhamashuku, in a “preservation area of traditional buildings” located in Kashima city, which is a typical lowland city in Saga prefecture. This project aims to explore possibilities to boost the performance of urban facades study using a deep learning method. The used algorithm is able analyze pictures of
buildings from different historic eras with different historic styles, regarding any selected feature.
First, an objective feature, such as the orientation of the building which, having a unique parameter, prevent from bias and thus
its results can be used as reference. Next in order, a more subjective parameter such as the quality of insertion is tested, results are quantified and compared in order to evaluate the algorithm performance and enhance it in further research.抄録：Architectural intervention in urban heritage area is subject to numerous parameters making it a time-consuming process. Urban façade analyses are also one of the required long-term tasks held by the architect, especially in urban heritage area where pressure concerning the neighborhood harmony is often faced.
To address this issue, A computer vision method for an automatic evaluation of the urban façade is used to compare a set of façade’s pictures. The target area is Hizenhamashuku, in a “preservation area of traditional buildings” located in Kashima city, which is a typical lowland city in Saga prefecture. This project aims to explore possibilities to boost the performance of urban facades study using a deep learning method. The used algorithm is able analyze pictures of
buildings from different historic eras with different historic styles, regarding any selected feature.
First, an objective feature, such as the orientation of the building which, having a unique parameter, prevent from bias and thus
its results can be used as reference. Next in order, a more subjective parameter such as the quality of insertion is tested, results are quantified and compared in order to evaluate the algorithm performance and enhance it in further research.英語フィールド
Author：M.R. Derbel, J. Makhlouf and N. MishimaTitle：A basic analysis on urban landscape continuity in a lowland urban heritage using deep learning-based methodAnnouncement information:Lowland Technology International 2020, 22(2), pp.192- 199, International Association of Lowland Technology (IALT): ISSN 1344-9656 Vol: 22 Issue: 2 Page: 192-199An abstract：Architectural intervention in urban heritage area is subject to numerous parameters making it a time-consuming process. Urban façade analyses are also one of the required long-term tasks held by the architect, especially in urban heritage area where pressure concerning the neighborhood harmony is often faced.
To address this issue, A computer vision method for an automatic evaluation of the urban façade is used to compare a set of façade’s pictures. The target area is Hizenhamashuku, in a “preservation area of traditional buildings” located in Kashima city, which is a typical lowland city in Saga prefecture. This project aims to explore possibilities to boost the performance of urban facades study using a deep learning method. The used algorithm is able analyze pictures of
buildings from different historic eras with different historic styles, regarding any selected feature.
First, an objective feature, such as the orientation of the building which, having a unique parameter, prevent from bias and thus
its results can be used as reference. Next in order, a more subjective parameter such as the quality of insertion is tested, results are quantified and compared in order to evaluate the algorithm performance and enhance it in further research.An abstract：Architectural intervention in urban heritage area is subject to numerous parameters making it a time-consuming process. Urban façade analyses are also one of the required long-term tasks held by the architect, especially in urban heritage area where pressure concerning the neighborhood harmony is often faced.
To address this issue, A computer vision method for an automatic evaluation of the urban façade is used to compare a set of façade’s pictures. The target area is Hizenhamashuku, in a “preservation area of traditional buildings” located in Kashima city, which is a typical lowland city in Saga prefecture. This project aims to explore possibilities to boost the performance of urban facades study using a deep learning method. The used algorithm is able analyze pictures of
buildings from different historic eras with different historic styles, regarding any selected feature.
First, an objective feature, such as the orientation of the building which, having a unique parameter, prevent from bias and thus
its results can be used as reference. Next in order, a more subjective parameter such as the quality of insertion is tested, results are quantified and compared in order to evaluate the algorithm performance and enhance it in further research.