arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03083cs.CVcs.RO
收藏

施工现场安全监测与挖掘机作业分析系统

Construction Site Safety Monitoring and Excavator Activity Analysis System

Baidu Research(百度研究院);Baidu USA(百度美国)

Sibo Zhang, Liangjun Zhang

摘要:

随着深度学习和计算机视觉的最新进展,自动挖掘机等人工智能驱动的工程机械取得了重大进展。安全是现代建筑中最重要的部分,建筑机械越来越自动化。在本文中,我们提出了一个基于视觉的挖掘机感知,活动分析和安全监测系统。我们的感知系统可以实时检测多类建筑机械和人类,同时估计挖掘机的姿势和动作。然后,我们提出了一种新的安全监测和挖掘机活动分析系统的感知结果的基础上。为了评估我们的方法的性能,我们收集了一个数据集,使用自主挖掘机系统(AES),包括多类对象在不同的照明条件下与人类注释。我们还评估了我们的方法的基准建设数据集。结果显示,与Faster R-CNN/ YOLO v3模型相比,我们的YOLO v5多类对象检测模型将推理速度提高了8倍(YOLO v5 x-large)到34倍(YOLO v5 small)。此外,YOLO v5模型的准确性提高了2.7%(YOLO v5 x-large),而模型大小减少了63.9%(YOLO v5 x-large)至93.9%(YOLO v5 small)。实验结果表明,所提出的动作识别方法优于国家的最先进的方法的top-1的准确率约5.18%。本文提出的实时安全监控系统不仅适用于固体废弃物场景中的自主挖掘机系统(AES),也可以应用于一般的施工场景。

英文摘要:

With the recent advancements in deep learning and computer vision, the AI-powered construction machine such as autonomous excavator has made significant progress. Safety is the most important section in modern construction, where construction machines are more and more automated. In this paper, we propose a vision-based excavator perception, activity analysis, and safety monitoring system. Our perception system could detect multi-class construction machines and humans in real-time while estimating the poses and actions of the excavator. Then, we present a novel safety monitoring and excavator activity analysis system based on the perception result. To evaluate the performance of our method, we collect a dataset using the Autonomous Excavator System (AES) including multi-class of objects in different lighting conditions with human annotations. We also evaluate our method on a benchmark construction dataset. The results showed our YOLO v5 multi-class objects detection model improved inference speed by 8 times (YOLO v5 x-large) to 34 times (YOLO v5 small) compared with Faster R-CNN/ YOLO v3 model. Furthermore, the accuracy of YOLO v5 models is improved by 2.7% (YOLO v5 x-large) while model size is reduced by 63.9% (YOLO v5 x-large) to 93.9% (YOLO v5 small). The experimental results show that the proposed action recognition approach outperforms the state-of-the-art approaches on top-1 accuracy by about 5.18%. The proposed real-time safety monitoring system is not only designed for our Autonomous Excavator System (AES) in solid waste scenes, it can also be applied to general construction scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑