A Human Detection Approach for Intrusion in Hazardous Areas Using 4D-BIM-Based Spatial-Temporal Analysis and Computer Vision

Abstract

Detecting intrusion in hazardous areas is one of the priorities and duties of safety enhancement. With the emergence of vision intelligence technology, hazardous-area-detection algorithms can support safety managers in predicting potential hazards and making decisions. However, because of the dynamic and complex nature of the jobsite, high-risk zones have a different geometry and can be changed following the schedule and workspace of activity. This leads to hazardous areas being annotated manually. Thus, this study proposes a computer vision and a 4D BIM-based approach for intrusion detection in hazardous areas, called IDC4D. IDC4D comprises three modules: (1) the 4D BIM-based safety planning (4BSP) module, which analyzes the hazardous area; (2) the hazardous area registration (HAR) module, which delivers the hazardous area from the BIM model to the camera’s first frame image; and (3) the hazardous-area-intrusion-detection module (HAID), which applies the computer vision algorithm to identify the correlation between workers and hazardous areas. The efficiency of the IDC4D approach is validated by testing a maintenance project on the construction site. IDC4D supports the planner in choosing the plan and detecting the event of workers entering hazardous areas while working. It showed an average precision of 93% and 94% in phase 1 and phase 2, respectively. These findings provide insight into how varying geometries of diverse hazard areas can be handled for enhancing intrusion detection.

Integrating BIM and computer vision for preventing Hazards at construction sites

“…The start-up company Newmetrix.com has implemented its capacity to distinguish 50 unique safety-related objects (such as rebar caps, hardhats, and ladders) from photographs and videos recorded at over 1 ,000 construction sites (Newmetrix, n.d.). To prevent hazardous area entry, Tran et al (2023) developed an IDC4D approach to extract hazardous area objects from the BIM model and then determine the correlation between workers and hazardous area objects. These technological breakthroughs allow the rapid detection of possible threats and the implementation of proactive risk management strategies.…”

“…Visual information-based construction safety monitoring has many advantages over traditional methods, such as manual inspection or paper-based documentation, such as higher accuracy, efficiency, reliability, and scalability. For instance, various types of dangerous situations have been investigated in-depth, including not wearing Personal Protective Equipment (PPE) (Khan, Khalid, Anjum, Tran, & Park, 2022), accessing a hazardous location (Tran et al, 2023), and failing to follow safety protocols (Zhang, Shi, & Yang, 2020). However, in a study of research publications published over the previous decade, Love, Matthews, Fang, and Luo (2023) pointed out that previous research concentrated on testing the accuracy of object detectors.…”