Scholarlink

<p>Building strength is essential for ensuring the longevity and safety of structures used for living and working. The age of construction materials, such as cement, soil, and water, can be estimated using post-classifier methods. To improve accuracy, a drone-based network system is proposed for classifying pre- and post-construction buildings. This system integrates LiDAR data to enhance the precision of building age estimation. Building footprints are calculated using the Normalized Perimeter Index and centroid analysis. The system can identify houses, trees, and roads to determine the age of building footprints. Image classifiers segment and classify structures and boundary data within the digital surface model, allowing measurement of building morphology and topography. In the first stage, the training model is evaluated, and extracted image data of city or village buildings are processed. In the next stage, the system predicts age factors for individual buildings, including material degradation, structural changes, and environmental impact. This study proposes a novel framework integrating UAV-based high-resolution imaging, multispectral indices, and AI-driven modeling to predict building age and durability. A dataset of over 10,000 building images covering village, city, and industrial structures was analyzed. Key indices, including NDVI, NDMI, RDI, SDI, CDI, and NPI, were extracted to quantify material degradation, shape irregularity, and environmental exposure. These indices were combined using the Building Age Factor algorithm to estimate structural strength, construction age, and remaining lifespan. The method achieved prediction accuracy of 85–88%, with remaining life estimates ranging from 2 to 8 years across building types. Compared to existing approaches, this framework provides quantitative, large-scale, and actionable assessments, enabling proactive maintenance and risk mitigation. The results highlight the influence of material quality, construction techniques, and environmental conditions on building aging, demonstrating the novelty and practical utility of this integrated approach for infrastructure management. Overall, the proposed system provides an automated, AI-driven approach for assessing building condition and predicting lifespan, supporting maintenance and planning in both urban and rural areas.</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

Research measurement of building construction age and life time using drone mapping image indices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月7日

查看全文
  • S. Meivel,
  • S. Raveendran,
  • K. Indira Devi,
  • S. Tamilarasi,
  • S. Uma Maheswari

摘要

Building strength is essential for ensuring the longevity and safety of structures used for living and working. The age of construction materials, such as cement, soil, and water, can be estimated using post-classifier methods. To improve accuracy, a drone-based network system is proposed for classifying pre- and post-construction buildings. This system integrates LiDAR data to enhance the precision of building age estimation. Building footprints are calculated using the Normalized Perimeter Index and centroid analysis. The system can identify houses, trees, and roads to determine the age of building footprints. Image classifiers segment and classify structures and boundary data within the digital surface model, allowing measurement of building morphology and topography. In the first stage, the training model is evaluated, and extracted image data of city or village buildings are processed. In the next stage, the system predicts age factors for individual buildings, including material degradation, structural changes, and environmental impact. This study proposes a novel framework integrating UAV-based high-resolution imaging, multispectral indices, and AI-driven modeling to predict building age and durability. A dataset of over 10,000 building images covering village, city, and industrial structures was analyzed. Key indices, including NDVI, NDMI, RDI, SDI, CDI, and NPI, were extracted to quantify material degradation, shape irregularity, and environmental exposure. These indices were combined using the Building Age Factor algorithm to estimate structural strength, construction age, and remaining lifespan. The method achieved prediction accuracy of 85–88%, with remaining life estimates ranging from 2 to 8 years across building types. Compared to existing approaches, this framework provides quantitative, large-scale, and actionable assessments, enabling proactive maintenance and risk mitigation. The results highlight the influence of material quality, construction techniques, and environmental conditions on building aging, demonstrating the novelty and practical utility of this integrated approach for infrastructure management. Overall, the proposed system provides an automated, AI-driven approach for assessing building condition and predicting lifespan, supporting maintenance and planning in both urban and rural areas.