REAL-TIME OBJECT DETECTION FOR AUTOMATED CONSTRUCTION MATERIAL MANAGEMENT

Abstract

Object detection in construction sites is now replacing traditional methods of quality control and material management. Artificial Intelligence (AI)-driven systems are now being used to detect objects, classify them, and evaluate construction materials using deep learning algorithms. These algorithms enhance the material quality assurance of operational activities. Conventional methods for construction materials are time-consuming, labor-intensive, and prone to error. While the AI-driven approaches are flexible, scalable, and reduce the cost of achieving high accuracy. This study shows the innovative role of object detection in the construction materials industry, emphasizing its benefits, applications, challenges, and future potential. This study proposes the use of a Deep learning -based model, Yolov11, which enhances the capability of real-time object detection by offering a high overall accuracy of 94.3 % precision of 96.3%, thereby enhancing the automated construction site monitoring and construction material management.