© 2021, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.In recent years, the increasing pace of urbanization is expected to increase the temperatures in urban contexts and amplify the Urban Heat Island effect. This phenomenon has a negative impact on the urbanites` thermal comfort in outdoor spaces. Modeling and simulation-based approaches can precisely calculate outdoor thermal comfort; however, they are labor-intensive and high in computational cost. This difficulty might discourage decision-makers to consider outdoor thermal comfort conditions, which can affect their strategies at the beginning stage of design. This paper aims to propose a statistical model that can predict outdoor comfort using semantic segmentation of 2D street view images. Firstly, 78 panoramic street images of selected three streets in Istanbul are used to calculate the specific object classes that have an influence on outdoor temperature using semantic segmentation. Following, the streets' outdoor thermal comfort is calculated in Ladybug/Grasshopper. Lastly, two multi-variate regression models are built using the percentages of these object classes in each image and outdoor thermal comfort in given locations on the streets. Initial results show that the proposed regression models can predict UTCI with R2=0.78 and R2=0.80, indicating the semantic segmentation can support the calculation of outdoor comfort.