A Deep Learning-based Method of Investigating Rammed-earth Wall Damage on the Ming Great Wall Military Defense System

Abstract

The collection, detection, and statistical analysis of massive damage information from large cultural heritage sites is an important issue that affects the progress, depth, and quality of cultural heritage protection efforts. The Ming Great Wall of China, known for its vast size, poses a significant challenge to protection efforts. Conventional methods for collecting and recognizing damage information from the wall are nearly impossible due to its scale. The limitation has significantly hindered efforts to safeguard the vulnerable rammed-earth walls of the Ming Great Wall. To address this issue, we developed new technical schemes that combine the efficiency of unmanned aerial vehicles (UAV) for low-altitude surveying and mapping with the accuracy of artificial intelligence detection. This enables the efficient collection, detection, and statistical analysis of a massive amount of damage data from the Great Wall sites. The system achieved an average damage detection accuracy of 0.838, as measured by the average precision (AP). Additionally, the system's average effective detection range exceeded 91.5%, while reducing manual labor time by about 95%. These results provide accurate, efficient, and timely data and technical support for efforts such as status investigation, condition evaluation, protection and maintenance, and budgeting for the Great Wall sites. Furthermore, this research proposes a potential approach for gathering and analyzing data from other large-scale cultural heritage sites.