Kinesiology-inspired assessment of intrusion risk based on human motion features

Intrusion behavior in hazardous areas is one of the major causes of construction safety accidents including falls from height and strikes by objects. Implementing automatic and preassessment of intrusions to enhance safety performance is of great importance in construction areas. Traditional behavioral safety management mainly relies on manual observation, which makes it difficult to accurately identify detailed changes in behavioral posture, while the results of risk analysis are susceptible to bias due to subjective factors. The emergence of artificial intelligence techniques and computer vision has provided new solutions for human behavior detection in recent years. Accurate vision-based skeleton extraction helps capture detailed behavioral information. Current studies generally focus on intrusion after the occurrence and rarely select metrics considering complex human motion features. It is difficult to accurately assess the potential intrusion risk, resulting in inefficient ex-ante safety management outcomes. This paper presents a novel intrusion assessment approach by integrating human kinematics to extract risk indicators and apply objective assessment methods for risk quantification. An indoor experiment with control groups was conducted by employing skeleton detection technology with safety knowledge to demonstrate its feasibility and effectiveness. The risk levels of the different activities were compared through a control group experimental analysis. The results show that a satisfying accuracy of intrusion assessment can be achieved for different workers. Appropriate warning and intervention methods can be implemented to mitigate the occurrence or reduce the severity of intrusions, thus reducing safety incidents on construction sites.