[JCR] Recognition of Damage Types of Gray-Brick Buildings

Recognition of Damage Types of Chinese Gray-Brick Ancient Buildings Based on Machine Learning—Taking the Macau World Heritage Buffer Zone as an Example

Abstract: This study proposes using the YOLOv4 machine learning model to automatically detect and classify five types of damage on historic gray-brick buildings, improving efficiency compared to manual assessment. The research focuses on gray- brick wall buildings in Macau’s global cultural heritage buffer zone. A total of 1355 on-site photographs were collected, identifying the five most common types of damage. From these images, a training set of 1000 labeled images was created for model training over 200 generations. The study concludes that gray-brick buildings in Macau sustain damage from the subtropical maritime climate, including missing paint, stains, and cracks. Machine learning aids in identifying damage types, assisting in management and protection. The proposed model accurately detects missing, cracking, erosion, yellowing, and pollution on gray-brick walls, enabling precise evaluation and protection strategies. [SCITIP]

DOI: https://doi.org/10.3390/atmos14020346

CITE: Yang, Xiaohong, Liang Zheng, Yile Chen, Jingzhao Feng, and Jianyi Zheng. 2023. “Recognition of Damage Types of Chinese Gray-Brick Ancient Buildings Based on Machine Learning—Taking the Macau World Heritage Buffer Zone as an Example” Atmosphere 14, no. 2: 346. https://doi.org/10.3390/atmos14020346

1. 心得分享

今日分享之论文，是本年度我们第一篇 SCIE+EI 期刊论文。这个小研究算是从去年 10 月开始，采集数据，做到后面发现能力有限，开始招兵买马，又组建了新的小组分工完成，后面投稿又返修，等了几天，终于上线与大家见面了！！！！等待还是值得的。认真努力还是会有回报的💪

[JCR] Recognition of Damage Types of Gray-Brick Buildings

线上阅读地址：https://www.mdpi.com/2073-4433/14/2/346

2. 简单讲讲

在我们岭南广府地区，有很多当时清朝华人建筑的青砖历史建筑，例如澳门世界遗产内的郑家大屋、卢家大屋。但是，在世遗缓冲区，也有不少，例如叫 xx 围或者 xx 里。因此，我们采集的地点有幻觉围、凤仙围、六屋围、永福围……还有一些路过的零散的还剩下半堵墙的地方……青砖损坏的类型有很多，我们通过 1000 张照片分类打标签，分出 5 种不同的青砖损坏类型，通过机器学习的方法，建立训练集，达到图像识别分析辅助后期建筑遗产修复的目的。青砖损坏的类型不同，它对应的后期修复成本也是有差异的，计算机视觉技术只是辅助我们提高工作效率，得到应用。那为什么是做这样的研究？这个期刊是关于大气科学的，征稿栏目当时有一个主题是建筑遗产与微气候。青砖的损坏类型，在澳门，其实也有不少属于微气候导致的。

于是，当时投了一个摘要，后面通过了，还挂出来了征稿的页面：

当时英语水平确实有限啊，青砖的翻译都没统一。在投稿了，返修阶段，返修了两次，可能是遇到自然科学的专家审稿人，他们背景是倾向做实验实打实那种，一开始还是比较质疑的，想知道机器识别与人工识别之间有什么区别，准确率如何。后面，二轮返修的时候，几乎是利用周末时间在通宵 OT 找专业建筑师人工校对分类，得到机器识别的准确率，补充了一节在人工检验的部分。本文的同行评议是公开的，详情可以查阅。

论文标题框架：

1.1. Research Background

1.2. Literature Review

1.3. Problem Statement and Objectives

2. Gray-Brick Walls and Climate Influence Factors

2.1. Material Characterization in the Gray-Brick Ancient Buildings

2.2. Analysis of Damage Types and Climatic Factors of Gray bricks

2.3. Sample Processing

3. Methods

3.1. Operational Process of Image Recognition Technology

3.2. Model Training

4. Discussion: Image Recognition and Analysis of Damaged Gray Bricks