首页|基于单目三维尺度恢复的人机碰撞识别与预警

基于单目三维尺度恢复的人机碰撞识别与预警

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
高效的施工安全管理对建筑业健康与高质量发展至关重要,其中预防人机碰撞事故是保障安全施工的核心.为了提升人机作业危险识别的精度,以施工挖掘机为例,提出一种基于双尺度单目相机自标定的人机碰撞危险识别与安全预警方法.该方法基于施工场景几何特性分析与目标检测特征提取来恢复单目视觉的三维尺度,以高效测算人机三维空间距离.此外,基于工程机械的运动学特性设计了人机碰撞预警及可视化模拟方法,依据人机距离阈值触发多级碰撞预警.以上海某房建工程项目为测试实例,实现了高精度人机目标检测(平均精度为91.2％)、空间距离测算(精度大于98％)与高效的碰撞事件评估,且算法帧率满足实时监测要求.
Automated collision recognition and warning for human-machine interaction based on 3D scale recovery of monocular vision
Efficient construction safety managements facilitate healthy and high-quality development of the construction industry.To ensure safe construction,it is crucial to prevent human-machine collision accidents.To accurately recognize the safety risks of human-machine operation,an automated method for human-machine collision risk recognition and warning was proposed based on self-calibration of dual-scale monocular cameras.This method recovered the three-dimensional scale of monocular vision based on the geometric characteristics analysis of the construction site and the extraction of target features,leading to precise measurement of the spatial distance between humans and machines.Furthermore,an approach for human-machine collision warning and visual simulation was proposed based on the kinematic characteristics of construction machinery.This method can trigger multi-level collision warnings based on a human-machine distance threshold.A construction project in Shanghai was selected as a test case and achieved accurate object detections(with average accuracy of 91.2％),spatial distance measurements(with accuracy above 98％)and collision event assessments,with the algorithm frame rate meeting real-time monitoring requirements.

construction monocular visionthree-dimensional scale recoveryhuman-machine collisionconstruction safety supervisionhazard warning

卢昱杰、王瑞、魏伟、张雁杰、霍骏

展开 >

同济大学土木工程学院,上海 200092

同济大学工程结构性能演化与控制教育部重点实验室,上海 200092

同济大学上海智能科学与技术研究院,上海 200092

施工单目视觉 三维尺度恢复 人机碰撞 施工安全监管 危险预警

国家重点研发计划土水工程Ⅰ类高峰学科建设项目(2022)国家自然科学基金项目同济大学-浦发人保城市建设与管理人工智能联合研究中心资助

2022YFC380170052078374

2024

10.14006/j.jzjgxb.2023.0673

建筑结构学报
中国建筑学会

建筑结构学报

CSTPCD北大核心
影响因子：1.546
ISSN：1000-6869
年,卷(期)：2024.45(7)
  • 30