Development of Image Classification Model for Urban Park User Activity Using Deep Learning of Social Media Photo Posts†

This study aims to create a basic model for classifying the activity photos that urban park users shared on social media using Deep Learning through Artificial Intelligence. Regarding data, related parks were collected Naver search, collected, and used classification model. Based indicators of Naturalness, Potential Attraction, Activity, which can be evaluate characteristics parks, 21 categories created. Urban by category, annotated datasets A custom CNN transfer learning utilizing pre-trained photo designed subsequently analyzed. As result study, Xception model, demonstrated best performance, was selected as user image evaluated several evaluation indicators. is meaningful in it has built AI an index user-shared media. The mitigates limitations manual classification, efficiently classify large amounts photos. So, said useful method monitoring management city future.