arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.15097cs.CVcs.AI
收藏

面向施工进度监控的计算机视觉:一种实时目标检测方法

Computer Vision for Construction Progress Monitoring: A Real-Time Object Detection Approach

TU Dresden(德累斯顿工业大学);Fraunhofer-Institut für Integrierte Schaltungen IIS(弗劳恩霍夫集成电路研究所IIS);Implenia Hochbau GmbH(依必安派特建筑有限公司)

Jiesheng Yang, Andreas Wilde, Karsten Menzel, Md Zubair Sheikh, Boris Kuznetsov

AI总结:

本文提出基于YOLOv8的实时目标检测方法用于自动化施工进度监控,构建并标注建筑要素数据集,实验表明其在精确率、召回率和F1分数上显著优于现有方法。

摘要:

施工进度监控(CPM)对于有效的项目管理至关重要,可确保项目按时、按预算交付。传统的CPM方法通常依赖人工检查和报告,耗时且容易出错。本文提出了一种使用最先进目标检测算法实现自动化CPM的新方法。所提方法利用YOLOv8的实时能力和高精度,在现场图像和视频中识别和跟踪施工要素。研究创建了一个数据集,包含各种建筑要素,并标注了用于训练和验证的相关对象。使用精确率、召回率和F1分数等标准指标对所提方法的性能进行了评估,结果表明其相比现有方法有显著提升。将计算机视觉集成到CPM中,为利益相关者提供了可靠、高效且具有成本效益的项目进度监控手段,有助于及时决策,并最终促进建设项目的成功完成。

英文摘要:

Construction progress monitoring (CPM) is essential for effective project management, ensuring on-time and on-budget delivery. Traditional CPM methods often rely on manual inspection and reporting, which are time-consuming and prone to errors. This paper proposes a novel approach for automated CPM using state-of-the-art object detection algorithms. The proposed method leverages e.g. YOLOv8's real-time capabilities and high accuracy to identify and track construction elements within site images and videos. A dataset was created, consisting of various building elements and annotated with relevant objects for training and validation. The performance of the proposed approach was evaluated using standard metrics, such as precision, recall, and F1-score, demonstrating significant improvement over existing methods. The integration of Computer Vision into CPM provides stakeholders with reliable, efficient, and cost-effective means to monitor project progress, facilitating timely decision-making and ultimately contributing to the successful completion of construction projects.

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。

↑