Quantifying the Visuo-Perceptual Segregation Between Ortabayır and Levent District in Istanbul through Semantic Segmentation

Urban segregation has always been a critical problem affecting citizens’ socio-cultural equality. Although the issue has been widely investigated, recent methodological perspectives based on machine learning techniques can provide alternative viewpoints while contributing to precise findings. This study highlights the urban segregation problem in the context of Levent and Ortabayir districts in Istanbul while reviewing the existing literature on the relevant issue of segregation. The study aims to elaborate on the visual and perceptual segregation between Levent and Ortabayir while providing quantitative evidence. This study applies semantic segmentation of street view images and scene ratings to quantify visuo-perceptual segregation. The dataset for semantic segmentation contains 150 street view images for both Levent and Ortabayır regions. Seven semantic label criteria are decided, such as nature, pavement, road, sky, buildings, people, and cars, to outline the basic visual qualities of the urban environment. The street view scenes are evaluated on a 7-Likert scale by fifty raters who are asked to focus on the scenes’ safety and beauty perceptual qualities. We applied comparison analysis to detect the statistical similarities and variations and correlation analyses to investigate the associative trends between virtual and perceptual variables. This study distinguishes itself from the existing literature by adopting the machine learning method to asses the segregation problem between Levent and Ortabayir through semantic labels. Our approach contributes to the literature with its methodology and the quantitative, precise segregation findings. This study confirms the segregation between Levent and Ortabayir with their visual and perceptual qualities and illustrates the discrete visuo-perceptual features of both regions. This study shows that segregation appears in the selected regions on both inter-regional and intra-regional scales.