Central Courtyard Feature Extraction in Remote Sensing Aerial Images Using Deep Learning: A Case-Study of Iran

Abstract

Central courtyards are primary components of vernacular architecture in Iran. The directions, dimensions, ratios, and other characteristics of central courtyards are critical for studying historical passive cooling and heating solutions. Several studies on central courtyards have compared their features in different cities and climatic zones in Iran. In this study, deep learning methods for object detection and image segmentation are applied to aerial images, to extract the features of central courtyards. The case study explores aerial images of nine historical cities in Bsk, Bsh, Bwk, and Bwh Köppen climate zones. Furthermore, these features were gathered in an extensive dataset, with 26,437 samples and 76 geometric and climactic features. Additionally, the data analysis methods reveal significant correlations between various features, such as the length and width of courtyards. In all cities, the correlation coefficient between these two characteristics is approximately +0.88. Numerous mathematical equations are generated for each city and climate zone by fitting the linear regression model to these data in different cities and climate zones. These equations can be used as proposed design models to assist designers and researchers in predicting and locating the best courtyard houses in Iran’s historical regions.

A Data-Driven Method for Constructing the Spatial Database of Traditional Villages—A Case Study of Courtyard Residential Typologies in Yunnan, China

“…(2) Problem-solving technology: Rural planning involves the utilization of a TVD to examine traditional settlement patterns, provide guidance for spatial buildings via machine learning methodologies [62], and integrate traditional design ideas into modern urban development analysis. Scholars could examine the progression of architectural styles, construction methods, and cultural impacts within various periods and geographical areas.…”

The Methods of Deep Learning and Big Data Analysis in Promoting Sustainable Architecture

“…Furthermore, the training dataset should include variations with distinct characteristics of the observed elements, such as elements from different geographic locations, to enhance recognition capabilities. We describe the training details in [17] where the object detection is done with the COCO-train2017 pre-trained model and further trained on FasterRCNN-ResNet-50 Backbone. This process is explained in [21].…”

“…The investigators have conducted a systematic review in which they are contrasting several aspects of inner courts and residences, such as their alignment and proportion [3], [24]- [27]. On the basis of the most recent research [17] a situation is described in which the authors used machine learning algorithms to analyze aerial VHR photography using data gathered from inner courts. This…”

“…The proposed process is based on our previous research [17] and can be divided into five stages and four processes.…”

The Effect of Improper Interfering in The Historical Architecture on Energy Wasting (Case Study: Bibi-Roqayyeh House, Yazd, Iran)

“…The central courtyard creates homogeneity in the spatial hierarchy of traditional buildings in Iran's central area. The central courtyard has played a fundamental and structural role across all scales in the cities in the center of Iran (i.e., Isfahan, Shiraz, and Yazd) [5][6][7]. Houses with central courtyards have been used by most ancient civilizations in central Iran, and many other dry parts of the Middle East.…”