Pro-active warning system for the crossroads at construction sites based on computer vision

Abstract

Purpose To improve insufficient management by artificial management, especially for traffic accidents that occur at crossroads, the purpose of this paper is to develop a pro-active warning system for crossroads at construction sites. Although prior studies have made efforts to develop warning systems for construction sites, most of them paid attention to the construction process, while the accidents that occur at crossroads were probably overlooked. Design/methodology/approach By summarizing the main reasons resulting for those accidents occurring at crossroads, a pro-active warning system that could provide six functions for countermeasures was designed. Several approaches relating to computer vision and a prediction algorithm were applied and proposed to realize the setting functions. Findings One 12-hour video that films a crossroad at a construction site was selected as the original data. The test results show that all designed functions could operate normally, several predicted dangerous situations could be detected and corresponding proper warnings could be given. To validate the applicability of this system, another 36-hour video data were chosen for a performance test, and the findings indicate that all applied algorithms show a significant fitness of the data. Originality/value Computer vision algorithms have been widely used in previous studies to address video data or monitoring information; however, few of them have demonstrated the high applicability of identification and classification of the different participants at construction sites. In addition, none of these studies attempted to use a dynamic prediction algorithm to predict risky events, which could provide significant information for relevant active warnings.

A systematic review of construction safety research: quantitative and qualitative content analysis approach

“…This is a rapidly growing research trend due to the industry's technological advancement and changing mindset from reactive to a proactive approach. This trend has enabled automatic hazard recognition, proactive warning systems (Zhu et al , 2020) and equipment path and poses predictions to prevent incidents on construction projects. Also, studies have captured causality patterns for near-miss incidents and stakeholders' personal protective equipment (PPE) non-compliance using computer vision with machine learning and deep learning algorithms.…”

Pose estimation method for construction machine based on improved AlphaPose model

“…Hyojoo et al (2019) presented a vision-based collision warning system based on the automated 3D position estimation of each worker with monocular vision, intending to protect equipment workers from potentially dangerous situations, such as collisions between the equipment and workers in a certain proximity. Zhu et al (2020) analyzed the potential risks and the dangerous factors for the safety of crossroads at construction sites and used computer vision technology to build an early warning systems (EWS), which contributed to the safety management of the crossroads at construction sites. Xu and Wang (2020) provided a safety prewarning mechanism, which can automatically extract safety information from surveillance cameras based on computer vision, assess risks based on the embedded comprehensive risk assessment model, categorize risks into five levels and provide timely suggestions.…”

“…(2019) presented a vision-based collision warning system based on the automated 3D position estimation of each worker with monocular vision, intending to protect equipment workers from potentially dangerous situations, such as collisions between the equipment and workers in a certain proximity. Zhu et al. (2020) analyzed the potential risks and the dangerous factors for the safety of crossroads at construction sites and used computer vision technology to build an early warning systems (EWS), which contributed to the safety management of the crossroads at construction sites.…”

Experiment study on pedestrian abnormal behavior detection and crowd stability analysis in cross passages

“…To detect and track the pedestrians, we can use the feasible target detection algorithms, e.g., YOLO and SSD [9]. In this study, we use HOG and SVM to classify the recognized behaviors into normal and abnormal behaviors [10].…”