Object detection has been widely applied for construction safety management,
especially personal protective equipment (PPE) detection. Though the existing
PPE detection models trained on conventional datasets have achieved excellent
results, their performance dramatically declines in extreme construction
conditions. A robust detection model NST-YOLOv5 is developed by combining the
neural style transfer (NST) and YOLOv5 technologies. Five extreme conditions
are considered and simulated via the NST module to endow the detection model
with excellent robustness, including low light, intense light, sand dust, fog,
and rain. Experiments show that the NST has great potential as a tool for
extreme data synthesis since it is better at simulating extreme conditions than
other traditional image processing algorithms and helps the NST-YOLOv5 achieve
0.141 and 0.083 mAP_(05:95) improvements in synthesized and real-world extreme
data. This study provides a new feasible way to obtain a more robust detection
model for extreme construction conditions.

通过结合神经风格迁移（NST）和 YOLOv5 技术，开发了一种稳健的检测模型 NST-YOLOv5，用于在极端建筑条件下进行个人防护装备（PPE）检测，并通过模拟灯光不足、强光、沙尘、雾和雨等五种极端条件赋予该模型极佳的鲁棒性。实验结果表明 NST 在合成极端数据方面具有较高潜力，优于其他传统图像处理算法，并帮助 NST-YOLOv5 在合成和真实极端数据上分别提升了 0.141 和 0.083 mAP_(05:95)，为在极端建筑条件下获取更加稳健的检测模型提供了新的可行方式。

极端施工条件下的个人防护装备检测

Personal Protective Equipment Detection in Extreme Construction  Conditions

Accident of struck-by machines is one of the leading causes of casualties on
construction sites. Monitoring workers' proximities to avoid human-machine
collisions has aroused great concern in construction safety management.
Existing methods are either too laborious and costly to apply extensively, or
lacking spatial perception for accurate monitoring. Therefore, this study
proposes a novel framework for proximity monitoring using only an ordinary 2D
camera to realize real-time human-machine collision warning, which is designed
to integrate a monocular 3D object detection model to perceive spatial
information from 2D images and a post-processing classification module to
identify the proximity as four predefined categories: Dangerous, Potentially
Dangerous, Concerned, and Safe. A virtual dataset containing 22000 images with
3D annotations is constructed and publicly released to facilitate the system
development and evaluation. Experimental results show that the trained 3D
object detection model achieves 75% loose AP within 20 meters. Besides, the
implemented system is real-time and camera carrier-independent, achieving an F1
of roughly 0.8 within 50 meters under specified settings for machines of
different sizes. This study preliminarily reveals the potential and feasibility
of proximity monitoring using only a 2D camera, providing a new promising and
economical way for early warning of human-machine collisions.

本文提出了一种使用普通 2D 相机来实现实时人机碰撞预警的新框架，该框架设计了一个单目 3D 目标检测模型和后处理分类模块，用于识别危险、潜在危险、关注和安全等四个预定义的接近程度，精度达到了 75％，可用于监测建筑工地的人机接近度以避免碰撞。