{"title":"应用物体检测算法有效识别文物建筑的损坏情况","authors":"Huadu Tang, Yalin Feng, Ding Wang, Ruiguang Zhu, Liwei Wang, Shengwang Hao, Shan Xu","doi":"10.1002/arp.1947","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Heritage buildings are crucial for any area's cultural and political aspects. Proper maintenance and monitoring are essential for the conservation of these buildings. However, manual inspections are time-consuming and expensive. We propose a deep learning–based detection framework to identify the damages on the ancient architectural wall. The algorithm applied in this study is YOLOv5. Comparing its five different versions, it was decided to use YOLOv5m as the most accurate detection algorithm with a mAP of 0.801. The damage types identified are physical weathering and visitors' scratches. High-resolution images were selected for the experiment and effectively identified image. In addition, the applied algorithm allows real-time detection and the identification of seasonal sources of disruption, which is proved by the video test in this study. The findings contribute to the development of an intelligent tool for health monitoring with the goal of fast and remote damage detection in the routine maintenance of heritage buildings.</p>\n </div>","PeriodicalId":55490,"journal":{"name":"Archaeological Prospection","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Application of Object Detection Algorithm for Efficient Damages Identification of the Conservation of Heritage Buildings\",\"authors\":\"Huadu Tang, Yalin Feng, Ding Wang, Ruiguang Zhu, Liwei Wang, Shengwang Hao, Shan Xu\",\"doi\":\"10.1002/arp.1947\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>Heritage buildings are crucial for any area's cultural and political aspects. Proper maintenance and monitoring are essential for the conservation of these buildings. However, manual inspections are time-consuming and expensive. We propose a deep learning–based detection framework to identify the damages on the ancient architectural wall. The algorithm applied in this study is YOLOv5. Comparing its five different versions, it was decided to use YOLOv5m as the most accurate detection algorithm with a mAP of 0.801. The damage types identified are physical weathering and visitors' scratches. High-resolution images were selected for the experiment and effectively identified image. In addition, the applied algorithm allows real-time detection and the identification of seasonal sources of disruption, which is proved by the video test in this study. The findings contribute to the development of an intelligent tool for health monitoring with the goal of fast and remote damage detection in the routine maintenance of heritage buildings.</p>\\n </div>\",\"PeriodicalId\":55490,\"journal\":{\"name\":\"Archaeological Prospection\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-06-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Archaeological Prospection\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/arp.1947\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"ARCHAEOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archaeological Prospection","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/arp.1947","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"ARCHAEOLOGY","Score":null,"Total":0}
Application of Object Detection Algorithm for Efficient Damages Identification of the Conservation of Heritage Buildings
Heritage buildings are crucial for any area's cultural and political aspects. Proper maintenance and monitoring are essential for the conservation of these buildings. However, manual inspections are time-consuming and expensive. We propose a deep learning–based detection framework to identify the damages on the ancient architectural wall. The algorithm applied in this study is YOLOv5. Comparing its five different versions, it was decided to use YOLOv5m as the most accurate detection algorithm with a mAP of 0.801. The damage types identified are physical weathering and visitors' scratches. High-resolution images were selected for the experiment and effectively identified image. In addition, the applied algorithm allows real-time detection and the identification of seasonal sources of disruption, which is proved by the video test in this study. The findings contribute to the development of an intelligent tool for health monitoring with the goal of fast and remote damage detection in the routine maintenance of heritage buildings.
期刊介绍:
The scope of the Journal will be international, covering urban, rural and marine environments and the full range of underlying geology.
The Journal will contain articles relating to the use of a wide range of propecting techniques, including remote sensing (airborne and satellite), geophysical (e.g. resistivity, magnetometry) and geochemical (e.g. organic markers, soil phosphate). Reports and field evaluations of new techniques will be welcomed.
Contributions will be encouraged on the application of relevant software, including G.I.S. analysis, to the data derived from prospection techniques and cartographic analysis of early maps.
Reports on integrated site evaluations and follow-up site investigations will be particularly encouraged.
The Journal will welcome contributions, in the form of short (field) reports, on the application of prospection techniques in support of comprehensive land-use studies.
The Journal will, as appropriate, contain book reviews, conference and meeting reviews, and software evaluation.
All papers will be subjected to peer review.