Abstract

With the advancement of modern urban planning, traditional landmark systems in Chinese cities have experienced spatial displacement, and their original organizational logic has been overlooked. To address this gap, the study uses historical gazetteer maps to develop a technical framework combining image tiling, deep learning, object detection, and a QGIS plugin for spatial feature recognition and analysis. Focusing on the Jiangnan region’s cities, the project extracts key elements such as gates, pagodas, bridges, buildings, etc, to analyze their spatial patterns and configurations. It further attempts to reconstruct the landmark network of Jiangnan cities through quantitative and digital methods, providing analytical tools for interpreting traditional spatial structures and cultural memory.

Speaker Bio

Xinyi YANG is a Harvard FAS CAMLab Visiting Student and Ph.D. candidate at Tongji University. Her research interests include Urban Morphology, Urban Planning Principles and Construction Strategies in Ancient China, and Spatial Configurations of Ancient Cities.

Event Information

• Free and open to the public
• June 20th (Friday)
• 12:00 – 13:30 PM ET
• This is an in-person event.

Please note

Advanced RSVP required.
The event will be conducted in Mandarin Chinese.