Most existing studies concentrating on human-induced loads on structures often rely on approximate formulas based on the loading from a single gait cycle, which inherently possess certain limitations. In this paper, a novel approach utilizing a multi-person 2D posture estimation model rooted in computer vision technology to real-time identify the posture of moving human bodies on construction sites is proposed. This approach works to deduce the reaction forces of moving bodies upon the floor by analyzing the motion characteristics of different body parts during their movement, ensuring an accurate estimation of structural loading. To validate the model’s accuracy, a series of tests were conducted, leveraging force measurement equipment to scrutinize the precision of load estimation during single-person motion. This examination seeks to ascertain the potential of the load prediction model in forecasting multi-person loads within actual project environments.