Johnny Kwok-Wai Wong, Fateme Bameri, Alireza Ahmadian Fard Fini, M. Maghrebi
{"title":"基于深度学习的现场监控视频分析跟踪室内施工进度","authors":"Johnny Kwok-Wai Wong, Fateme Bameri, Alireza Ahmadian Fard Fini, M. Maghrebi","doi":"10.1108/ci-10-2022-0275","DOIUrl":null,"url":null,"abstract":"\nPurpose\nAccurate and rapid tracking and counting of building materials are crucial in managing on-site construction processes and evaluating their progress. Such processes are typically conducted by visual inspection, making them time-consuming and error prone. This paper aims to propose a video-based deep-learning approach to the automated detection and counting of building materials.\n\n\nDesign/methodology/approach\nA framework for accurately counting building materials at indoor construction sites with low light levels was developed using state-of-the-art deep learning methods. An existing object-detection model, the You Only Look Once version 4 (YOLO v4) algorithm, was adapted to achieve rapid convergence and accurate detection of materials and site operatives. Then, DenseNet was deployed to recognise these objects. Finally, a material-counting module based on morphology operations and the Hough transform was applied to automatically count stacks of building materials.\n\n\nFindings\nThe proposed approach was tested by counting site operatives and stacks of elevated floor tiles in video footage from a real indoor construction site. The proposed YOLO v4 object-detection system provided higher average accuracy within a shorter time than the traditional YOLO v4 approach.\n\n\nOriginality/value\nThe proposed framework makes it feasible to separately monitor stockpiled, installed and waste materials in low-light construction environments. The improved YOLO v4 detection method is superior to the current YOLO v4 approach and advances the existing object detection algorithm. This framework can potentially reduce the time required to track construction progress and count materials, thereby increasing the efficiency of work-in-progress evaluation. It also exhibits great potential for developing a more reliable system for monitoring construction materials and activities.\n","PeriodicalId":45580,"journal":{"name":"Construction Innovation-England","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Tracking indoor construction progress by deep-learning-based analysis of site surveillance video\",\"authors\":\"Johnny Kwok-Wai Wong, Fateme Bameri, Alireza Ahmadian Fard Fini, M. Maghrebi\",\"doi\":\"10.1108/ci-10-2022-0275\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\nPurpose\\nAccurate and rapid tracking and counting of building materials are crucial in managing on-site construction processes and evaluating their progress. Such processes are typically conducted by visual inspection, making them time-consuming and error prone. This paper aims to propose a video-based deep-learning approach to the automated detection and counting of building materials.\\n\\n\\nDesign/methodology/approach\\nA framework for accurately counting building materials at indoor construction sites with low light levels was developed using state-of-the-art deep learning methods. An existing object-detection model, the You Only Look Once version 4 (YOLO v4) algorithm, was adapted to achieve rapid convergence and accurate detection of materials and site operatives. Then, DenseNet was deployed to recognise these objects. Finally, a material-counting module based on morphology operations and the Hough transform was applied to automatically count stacks of building materials.\\n\\n\\nFindings\\nThe proposed approach was tested by counting site operatives and stacks of elevated floor tiles in video footage from a real indoor construction site. The proposed YOLO v4 object-detection system provided higher average accuracy within a shorter time than the traditional YOLO v4 approach.\\n\\n\\nOriginality/value\\nThe proposed framework makes it feasible to separately monitor stockpiled, installed and waste materials in low-light construction environments. The improved YOLO v4 detection method is superior to the current YOLO v4 approach and advances the existing object detection algorithm. This framework can potentially reduce the time required to track construction progress and count materials, thereby increasing the efficiency of work-in-progress evaluation. It also exhibits great potential for developing a more reliable system for monitoring construction materials and activities.\\n\",\"PeriodicalId\":45580,\"journal\":{\"name\":\"Construction Innovation-England\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Construction Innovation-England\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1108/ci-10-2022-0275\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CONSTRUCTION & BUILDING TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Construction Innovation-England","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/ci-10-2022-0275","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
目的准确、快速地跟踪和统计建筑材料对于管理现场施工过程和评估其进度至关重要。此类过程通常通过目视检查进行,因此耗时且容易出错。本文旨在提出一种基于视频的深度学习方法,用于建筑材料的自动检测和计数。设计/方法/方法使用最先进的深度学习方法开发了一个在低光照条件下准确计算室内建筑工地建筑材料的框架。现有的物体检测模型,即You Only Look Once version 4(YOLO v4)算法,适用于实现材料和现场操作人员的快速收敛和准确检测。然后,DenseNet被部署来识别这些物体。最后,将基于形态学运算和霍夫变换的材料计数模块应用于建筑材料堆垛的自动计数。发现在一个真实的室内建筑工地的视频片段中,通过计算现场作业人员和成堆的高架地砖来测试所提出的方法。与传统的YOLO v4方法相比,所提出的YOLO v4对象检测系统在更短的时间内提供了更高的平均精度。独创性/价值拟议的框架使在低光建筑环境中单独监测储存、安装和废弃材料变得可行。改进的YOLO v4检测方法优于现有的YOLO v4方法,并改进了现有的目标检测算法。该框架可以潜在地减少跟踪施工进度和清点材料所需的时间,从而提高在建工程评估的效率。它还显示出开发更可靠的建筑材料和活动监测系统的巨大潜力。
Tracking indoor construction progress by deep-learning-based analysis of site surveillance video
Purpose
Accurate and rapid tracking and counting of building materials are crucial in managing on-site construction processes and evaluating their progress. Such processes are typically conducted by visual inspection, making them time-consuming and error prone. This paper aims to propose a video-based deep-learning approach to the automated detection and counting of building materials.
Design/methodology/approach
A framework for accurately counting building materials at indoor construction sites with low light levels was developed using state-of-the-art deep learning methods. An existing object-detection model, the You Only Look Once version 4 (YOLO v4) algorithm, was adapted to achieve rapid convergence and accurate detection of materials and site operatives. Then, DenseNet was deployed to recognise these objects. Finally, a material-counting module based on morphology operations and the Hough transform was applied to automatically count stacks of building materials.
Findings
The proposed approach was tested by counting site operatives and stacks of elevated floor tiles in video footage from a real indoor construction site. The proposed YOLO v4 object-detection system provided higher average accuracy within a shorter time than the traditional YOLO v4 approach.
Originality/value
The proposed framework makes it feasible to separately monitor stockpiled, installed and waste materials in low-light construction environments. The improved YOLO v4 detection method is superior to the current YOLO v4 approach and advances the existing object detection algorithm. This framework can potentially reduce the time required to track construction progress and count materials, thereby increasing the efficiency of work-in-progress evaluation. It also exhibits great potential for developing a more reliable system for monitoring construction materials and activities.