Visual Environmental Correlates of AI-Predicted Emotional Perception in Campus Indoor Pedestrian Corridors: A Quantitative Study Based on Deep Learning Methods

In the campus planning of severe cold regions, indoor pedestrian corridors have emerged as an important strategy for mitigating harsh weather and maintaining pedestrian network continuity. These enclosed systems provide thermal comfort and physical convenience for faculty and students. However, reduced visual contact with outdoor natural environments may be associated with less favorable affective experiences. Existing research primarily emphasizes functional connectivity and spatial efficiency, with limited quantitative evidence on the visual characteristics of indoor corridors and their relationship with emotional perception. Drawing upon environmental psychology, this study examines the associations between corridor visual characteristics and five AI-predicted affective perception dimensions. Using deep-learning-based computer vision, semantic segmentation, and statistical analysis, environmental features and predicted perception scores were analyzed. A local human validation showed moderate overall agreement between human consensus ratings and AI-predicted scores, supporting their use as exploratory perception proxies. The findings indicate that indoor-corridor-related visual features were negatively associated with predicted beauty scores and positively associated with predicted depression scores, while predicted boringness was positively associated with wall enclosure. Predicted safety and liveliness showed weaker associations with individual visual features. These results provide exploratory evidence for balancing thermal protection, circulation efficiency, and psychological comfort in future campus corridor design.