This study aims to propose a three-dimensional convolutional neural network (3D CNN)-based one-stage model for real-time action detection in video of construction equipment (ADVICE). The 3D CNN-based single-stream feature extraction network and detection network are designed with the implementation of the 3D attention module and feature pyramid network developed in this study to improve performance. For model evaluation, 130 videos were collected from YouTube including videos of four types of construction equipment at various construction sites. Trained on 520 clips and tested on 260 clips, ADVICE achieved precision and recall of 82.1% and 83.1%, respectively, with an inference speed of 36.6 frames per second. The evaluation results indicate that the proposed method can implement the 3D CNN-based one-stage model for real-time action detection of construction equipment in videos of diverse, variable, and complex construction sites. The proposed method paved the way to improving safety, productivity, and environmental management of construction projects.

中文翻译：

---

基于3D卷积神经网络的建筑设备视频实时动作检测一级模型

本研究旨在提出一种基于三维卷积神经网络 (3D CNN) 的单阶段模型，用于施工设备视频 (ADVICE) 中的实时动作检测。基于 3D CNN 的单流特征提取网络和检测网络的设计实现了本研究中开发的 3D 注意力模块和特征金字塔网络，以提高性能。对于模型评估，从 YouTube 上收集了 130 个视频，其中包括各种施工现场的四种施工设备的视频。在 520 个片段上训练并在 260 个片段上进行测试，ADVICE 的准确率和召回率分别达到 82.1% 和 83.1%，推理速度为每秒 36.6 帧。评估结果表明，所提出的方法可以实现基于 3D CNN 的单阶段模型，用于在多样化、可变和复杂的施工现场视频中实时检测施工设备的动作。所提出的方法为提高建设项目的安全性、生产力和环境管理铺平了道路。