Takuya Oki

Inclusive and socially resilient cities depend on streetscapes that work for diverse residents, yet mainstream planning still optimizes for an ”average” user, implicitly treating perception as demographically uniform. The open problem, however, is not whether perceptual divergences exist, but that they have lacked a comparable, city-scale measure to locate and prioritize them. To address this, we construct a Heterogeneity Index that quantifies demographic perceptual divergence across 22 streetscape attributes, using Contrastive Language–Image Pretraining (CLIP)-derived representations within a supervised preference model. Trained on 400,000 pairwise evaluations from 38,525 Japanese participants stratified by gender and age, the proposed approach estimates these attributes. The models are applied to a large-scale case study of 241,912 geo-tagged street-view images from Tokyo’s Setagaya Ward, while inter-group differences are evaluated using the Heterogeneity Index based on correlation, absolute deviation, and data distribution. Divergence coordinate scatter plots visualize patterns of consensus and divergence. The models achieved a mean accuracy of 0.8983. Evaluated by the index and validated against a model-free human baseline (Spearman ρ = 0.761), results indicate that perceptions of ”open” and ”greenery” are consistent across groups, while ”desirable for living,” ”friendly,” and ”interesting” diverge considerably. Regression analysis indicates these gaps concentrate in commercial and quasi-residential contexts. By quantifying these divergences, we present a tiered framework to distinguish streetscape qualities suitable for universal standards from those requiring targeted interventions. By making these divergences measurable, this approach provides an empirical basis for identifying where average-user assumptions fail, informing inclusive urban design and social resilience.

This study investigates the relationship between walkability and evacuation safety in Japan from the perspective of street impressions. Using Google Street View images and large-scale web surveys, we collected impression evaluations under both normal and evacuation scenarios such as earthquakes, tsunamis, fires, and heavy rainfall. Deep learning models were trained to estimate impression values, achieving an average accuracy of 76.9%. Lasso regression revealed that the spatial determinants of impressions differ by situation. Furthermore, a route selection model incorporating impression values quantitatively demonstrated their significant influence on route choice, underscoring the importance of integrating perceptual factors into urban design for livability and disaster resilience.

Promoting walking is crucial for sustainable development and fosters individual health and well-being. Therefore, comprehensive investigations of factors that make walking attractive are vital. Previous research has linked streetscapes at eye-level to walking preferences, which usually focuses on simple linear relationships, neglecting the complex non-linear dynamics. Additionally, the varied effects of streetscape factors across street segments and intersections and different street structures remain largely unexplored. To address these gaps, this study explores how eye-level streetscapes influence walking preferences in various street segments and intersections in Setagaya Ward, Tokyo. Using street view data, an image survey, and computer vision algorithms, we measured eye-level streetscape factors and walking preferences. The Extreme Gradient Boosting (XGBoost) model was then applied to analyze their non-linear relationships. This study identified key streetscape factors influencing walking preferences and uncovered non-linear trends within various factors, showcasing a variety of patterns, including upward, downward, and threshold effects. Moreover, our findings highlight the heterogeneity of the structural characteristics of street segments and intersections, which also impact the relationship between eye-level streetscapes and walking preferences. These insights can significantly inform decision-making in urban streetscape design, enhancing pedestrian perceptions.

People flow trend estimation is crucial to traffic and urban safety planning and management. However, owing to privacy concerns, the collection of individual location data for people flow statistical analysis is difficult; thus, an alternative approach is urgently needed. Furthermore, the trend in people flow is reflected in streetscape factors, yet the relationship between them remains unclear in the existing literature. To address this, we propose an end-to-end deep-learning approach that combines street view images and human subjective score of each street view. For a more detailed people flow study, estimation and analysis were implemented using different time and movement patterns. Consequently, we achieved a 78% accuracy on the test set. We also implemented the gradient-weighted class activation mapping deep learning visualization and L1 based statistical methods and proposed a quantitative analysis approach to understand the land scape elements and subjective feeling of street view and to identify the effective elements for the people flow estimation based on a gradient impact method. In summary, this study provides a novel end-to-end people flow trend estimation approach and sheds light on the relationship between streetscape, human subjective feeling, and people flow trend, thereby making an important contribution to the evaluation of existing urban development.

The built year and structure of individual buildings are crucial factors for estimating and assessing potential earthquake and tsunami damage. Recent advances in sensing and analysis technologies allow the acquisition of high-resolution street view images (SVIs) that present new possibilities for research and development. In this study, we developed a model to estimate the built year and structure of a building using omnidirectional SVIs captured using an onboard camera. We used geographic information system (GIS) building data and SVIs to generate an annotated built year and structure dataset by developing a method to automatically combine the GIS data with images of individual buildings cropped through object detection. Furthermore, we trained a deep learning model to classify the built year and structure of buildings using the annotated image dataset based on a deep convolutional neural network (DCNN) and a vision transformer (ViT). The results showed that SVI accurately predicts the built year and structure of individual buildings using ViT (overall accuracies for structure = 0.94 [3 classes] and 0.96 [2 classes] and for age = 0.68 [6 classes] and 0.90 [3 classes]). Compared with DCNN-based networks, the proposed Swin transformer based on ViT architectures effectively improves prediction accuracy. The results indicate that multiple high-resolution images can be obtained for individual buildings using SVI, and the proposed method is an effective approach for classifying structures and determining building age. The automatic, accurate, and large-scale mapping of the built year and structure of individual buildings can help develop specific disaster prevention measures.

The availability of vast amounts of location-based data from social media platforms such as Twitter has enabled us to look deeply into the dynamics of human movement. The aim of this paper is to leverage a large collection of geo-tagged tweets and the street networks of two major metropolitan areas—London and Tokyo—to explore the underlying mechanism that determines the heterogeneity of human mobility patterns. For the two target cities, hundreds of thousands of tweet locations and road segments were processed to generate city hotspots and natural streets. User movement trajectories and city hotspots were then used to build a hotspot network capable of quantitatively characterizing the heterogeneous movement patterns of people within the cities. To emulate observed movement patterns, the study conducts a two-level agent-based simulation that includes random walks through the hotspot networks and movements in the street networks using each of three distance types—metric, angular and combined. Comparisons of the simulated and observed movement flows at the segment and street levels show that the heterogeneity of human urban movements at the collective level is mainly shaped by the scaling structure of the urban space.