Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran
This research paper reports the process and results of a project to automatically classify historical and non-historical buildings using airborne and satellite imagery. The case study area is the center of Yazd, the most important historical site in Iran. New computational scientific methods and acc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Heritage |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9408/5/4/159 |
| _version_ | 1797457417963831296 |
|---|---|
| author | Hadi Yazdi Shina Sad Berenji Ferdinand Ludwig Sajad Moazen |
| author_facet | Hadi Yazdi Shina Sad Berenji Ferdinand Ludwig Sajad Moazen |
| author_sort | Hadi Yazdi |
| collection | DOAJ |
| description | This research paper reports the process and results of a project to automatically classify historical and non-historical buildings using airborne and satellite imagery. The case study area is the center of Yazd, the most important historical site in Iran. New computational scientific methods and accessibility to satellite images have created more opportunities to work on automated historical architecture feature recognition. Building on this, a convolutional neural network (CNN) is the main method for the classification task of the project. The most distinctive features of the historical houses in Iran are central courtyards. Based on this characteristic, the objective of the research is recognizing and labeling the houses as historical buildings by a CNN model. As a result, the trained model is tested by a validation dataset and has an accuracy rate of around 98%. In Sum, the reported project is one of the first works on deep learning methods in historical Iranian architecture study and one of the first efforts to use automated remote sensing techniques for recognizing historical courtyard houses in aerial images. |
| first_indexed | 2024-03-09T16:21:53Z |
| format | Article |
| id | doaj.art-9ccca6f98b2b445fb51c42238e65b7b8 |
| institution | Directory Open Access Journal |
| issn | 2571-9408 |
| language | English |
| last_indexed | 2024-03-09T16:21:53Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Heritage |
| spelling | doaj.art-9ccca6f98b2b445fb51c42238e65b7b82023-11-24T15:13:20ZengMDPI AGHeritage2571-94082022-10-01543066308010.3390/heritage5040159Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, IranHadi Yazdi0Shina Sad Berenji1Ferdinand Ludwig2Sajad Moazen3Department of Architecture, School of Engineering and Design, Technical University of Munich, 80333 Munich, GermanyDepartment of landscape Architecture, Tarbiat Modares University, Tehran 119-14115, IranDepartment of Architecture, School of Engineering and Design, Technical University of Munich, 80333 Munich, GermanySchool of Architecture and environmental design, Iran University of Science and Technology, Tehran 13114-16846, IranThis research paper reports the process and results of a project to automatically classify historical and non-historical buildings using airborne and satellite imagery. The case study area is the center of Yazd, the most important historical site in Iran. New computational scientific methods and accessibility to satellite images have created more opportunities to work on automated historical architecture feature recognition. Building on this, a convolutional neural network (CNN) is the main method for the classification task of the project. The most distinctive features of the historical houses in Iran are central courtyards. Based on this characteristic, the objective of the research is recognizing and labeling the houses as historical buildings by a CNN model. As a result, the trained model is tested by a validation dataset and has an accuracy rate of around 98%. In Sum, the reported project is one of the first works on deep learning methods in historical Iranian architecture study and one of the first efforts to use automated remote sensing techniques for recognizing historical courtyard houses in aerial images.https://www.mdpi.com/2571-9408/5/4/159historical architectureremote sensingdeep learningconvolutional neural network (CNNs)image processingYazd |
| spellingShingle | Hadi Yazdi Shina Sad Berenji Ferdinand Ludwig Sajad Moazen Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran Heritage historical architecture remote sensing deep learning convolutional neural network (CNNs) image processing Yazd |
| title | Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran |
| title_full | Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran |
| title_fullStr | Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran |
| title_full_unstemmed | Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran |
| title_short | Deep Learning in Historical Architecture Remote Sensing: Automated Historical Courtyard House Recognition in Yazd, Iran |
| title_sort | deep learning in historical architecture remote sensing automated historical courtyard house recognition in yazd iran |
| topic | historical architecture remote sensing deep learning convolutional neural network (CNNs) image processing Yazd |
| url | https://www.mdpi.com/2571-9408/5/4/159 |
| work_keys_str_mv | AT hadiyazdi deeplearninginhistoricalarchitectureremotesensingautomatedhistoricalcourtyardhouserecognitioninyazdiran AT shinasadberenji deeplearninginhistoricalarchitectureremotesensingautomatedhistoricalcourtyardhouserecognitioninyazdiran AT ferdinandludwig deeplearninginhistoricalarchitectureremotesensingautomatedhistoricalcourtyardhouserecognitioninyazdiran AT sajadmoazen deeplearninginhistoricalarchitectureremotesensingautomatedhistoricalcourtyardhouserecognitioninyazdiran |