2019/01/30 by Idris Jeelani, Khashayar Asadi, Jeelani, Idris +7 · 1 citation
Engineering · Health Professions · Psychology · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human-Automation Interaction and Safety #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Occupational Health and Safety Research #Safety Warnings and Signage #Traffic and Road Safety
paper · pdf · doi:10.48550/arxiv.1901.11078
openalex publication_date 2019/01/30 · openalex created_date 2022/07/30 · openalex updated_date 2026/07/28
Research studies have shown that a large proportion of hazards remain\nunrecognized, which expose construction workers to unanticipated safety risks.\nRecent studies have also found that a strong correlation exists between viewing\npatterns of workers, captured using eye-tracking devices, and their hazard\nrecognition performance. Therefore, it is important to analyze the viewing\npatterns of workers to gain a better understanding of their hazard recognition\nperformance. This paper proposes a method that can automatically map the gaze\nfixations collected using a wearable eye-tracker to the predefined areas of\ninterests. The proposed method detects these areas or objects (i.e., hazards)\nof interests through a computer vision-based segmentation technique and\ntransfer learning. The mapped fixation data is then used to analyze the viewing\nbehaviors of workers and compute their attention distribution. The proposed\nmethod is implemented on an under construction road as a case study to evaluate\nthe performance of the proposed method.\n