The deep learning method applied to the detection and mapping of stone deterioration in open-air sanctuaries of the Hittite period in Anatolia

The detection of deterioration in archeological heritage sites is a very time-consuming task that requires expertise. Furthermore, vision-based approaches can cause errors, considering the complex types of de-terioration that develop in different scales and forms in monuments. This problem can be solved effec-tively owing to computer vision algorithms, commonly used in different areas nowadays. This study aims to develop a model that automatically detects and maps deteriorations (biological colonization, contour scaling, crack, higher plant, impact damage, microkarst, missing part) and restoration interventions using the Mask R-CNN algorithm, which has recently come to the fore with its feature of recognizing small and large-sized objects. To this end, a total of 2460 images of Yazilikaya monuments in the Hattusa archeo-logical site, which is on the UNESCO heritage list, were gathered. In the training phase of the proposed method, it was trained in model 1 to distinguish deposit deterioration commonly observed on the surface of monuments from other anomalies. Other anomalies trained were model 2. In this phase of the models, the average precision values with high accuracy rates ranging from 89.624% to 100% were obtained for the deterioration classes. The developed algorithms were tested on 4 different rock reliefs in Yazilikaya, which were not used in the training phase. In addition, an image of the Eflatunpinar water monument, which is on the UNESCO tentative list, was used to test the model's universality. According to the test results, it was determined that the models could be successfully applied to obtain maps of deterioration and restoration interventions in monuments in different regions. (c) 2021 Elsevier Masson SAS. All rights reserved.