Citation

Chen H, Hou L, Zhang GK, Wu S. Safety Sci. 2023; 158: e105958.

Copyright

(Copyright © 2023, Elsevier Publishing)

DOI

10.1016/j.ssci.2022.105958

PMID

unavailable

Abstract

Automated recognition of image patterns in surveillance cameras is beneficial for safety monitoring. A representative application is visual proximity detection for accident prevention. However, existing deep learning (DL)-based proximity detection methods are likely to be inaccurate due to congestion, background clutter, and occlusion in construction sites. Another problem is that most of these methods cannot suffice computing capability, network training efficiency, and performance accuracy at the same time. This study first presents a novel context-guided data augmentation method that addresses the performance loss issue due to object occlusion. This method places new instances on images based on contextual image information rather than randomly erasing images to simulate occlusion circumstances. Next, a light-weight and less-costly DL model named YOLOv4-EFNB0 is formulated for multi-class construction resource detection in real-time. Moreover, this study presents a proactive proximity detection application by integrating YOLOv4-EFNB0 with homography transformation. Based on the experiment, YOLOv4-EFNB0 demonstrates a better object detection outcome when trained on the augmented dataset over the Moving Objects in Construction Sites (MOCS) baseline dataset. This study also conducts a feasibility test for the visual proximity detection application. The results indicate the application has a high accuracy rate and a fast speed, namely, 96.76% in 25 Frames Per Second (FPS), which can facilitate the automation of safety monitoring and inspection.

Language: en

Keywords

Computer Vision; Construction Resource Detection; Data Augmentation; Deep Learning; Proximity Detection