Scholarlink

<p>Heritage buildings are vital to China’s cultural heritage, and rapid identification of efflorescent areas on their walls is crucial for restoration research. Traditional methods struggle with challenges like complex backgrounds, tiny region extraction, and image noise. Advances in artificial intelligence, particularly deep learning and Convolutional Neural Networks (CNN), offer new solutions. This study employs the YoloV10 model for efflorescent detection on building walls. Experimental results demonstrate its effectiveness in capturing efflorescent disease information, aiding in the analysis of wall efflorescence causes and the impact of meteorological parameters in regions with extreme climates. This research provides essential data and technology for the prevention and treatment of cultural relic diseases.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Brick wall efflorescence detection technology using target detection illustrated by Wuhan Gao’s Hospital

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月8日

查看全文
  • Xinrui Luo,
  • Hechi Wang,
  • Yuchen Qian,
  • Wendi Huang,
  • Zhaoyi Yan,
  • Gang Xie

摘要

Heritage buildings are vital to China’s cultural heritage, and rapid identification of efflorescent areas on their walls is crucial for restoration research. Traditional methods struggle with challenges like complex backgrounds, tiny region extraction, and image noise. Advances in artificial intelligence, particularly deep learning and Convolutional Neural Networks (CNN), offer new solutions. This study employs the YoloV10 model for efflorescent detection on building walls. Experimental results demonstrate its effectiveness in capturing efflorescent disease information, aiding in the analysis of wall efflorescence causes and the impact of meteorological parameters in regions with extreme climates. This research provides essential data and technology for the prevention and treatment of cultural relic diseases.