隨著科技的進步，人工智慧的影像辨識已發展相當成熟，也廣泛的應用於各項產業領域，在營建產業中更是有多方研究致力於將其結合與應用，加上營建管理的專案進度排程已成為工程中不可獲缺的重要任務，故本研究嘗試將本研究室既有的研究所訓練的偵測模型做為影像辨識之輔助工具，此偵測模型主要針對施工現場之不同工項進度影像進行分類以及偵測，並加入建築資訊模型（Building Information Model, BIM）做為建築資訊的傳遞媒介，提出一套整合AI影像辨識與BIM技術的自動化施工進度管控系統。然而，上述的偵測模型僅能針對單一的影像進行辨識，而單一影像可能無法涵蓋完整的施工區域，因此，本研究將著重於結合多視角的影像偵測結果，並將基於AI偵測結果的資訊透過BIM模型做為資訊傳遞之媒介，最後，將現場進度資訊與進度排程系統進行比對，並將比對結果依元件進度以不同的顏色在BIM模型上呈現，透過視覺化的方式，使管理人員能夠直觀地即時掌握施工進度。

With the advancement of technology, the image recognition capabilities of artificial intelligence have matured significantly and have been widely applied across various industries. In the construction industry, there have been numerous studies dedicated to integrating and utilizing these capabilities. Coupled with the fact that project scheduling within construction management has become an indispensable task, this research endeavors to leverage the detection models previously developed by our research team as auxiliary tools for image recognition. These detection models primarily focus on classifying and detecting different construction progress images from various tasks on construction sites. Additionally, the research incorporates Building Information Model (BIM) as a means of conveying architectural information. The goal is to propose an integrated system that combines AI image recognition and BIM technology for automated construction progress monitoring and control. However, the aforementioned detection models can only address individual images, and a single image might not encompass the entire construction area. Thus, this study places emphasis on amalgamating results from image detection using multiple perspectives. Furthermore, the information derived from AI detection outcomes is transmitted through the BIM model as a medium of information transfer. Ultimately, the research involves comparing on-site progress information with the scheduling system, and presenting the comparison results on the BIM model using distinct colors corresponding to different component progress levels. This visual approach allows management personnel to intuitively and promptly comprehend the construction progress.

[1] 陳宛榆, 應用深度學習技術於施工現場影像之工項進度自動化偵測. 2023, 國立台灣科技大學.
[2] Hany Omar , Lamine Mahdjoubi , Gamal Kheder, Towards an automated photogrammetry-based approach for monitoring and controlling construction site activities. 2017.
[3] Sepehr Alizadehsalehi, Ibrahim Yitmen, The Impact of Field Data Capturing Technologies on Automated Construction Project Progress Monitoring. 2016.
[4] McCarthy J., Minsky M. L., Rochester N., Shannon C.E., A proposal for the Dartmouth summer research project on artificial intelligence. AI Magazine, 2006. Volume 27(Issue 4): p. 12-14.
[5] P., Langley, Human and machine learning. Machine Learning, 1986: p. 243-248.
[6] Hinton G. E., Salakhutdinov R. R., Reducing the Dimensionality of Data with Neural Networks. Science, 28 Jul 2006. Volume 313(Issue 5786): p. 504-507.
[7] Krizhevsky A., Sutskever I., Hinton G. E., ImageNet classification with deep convolutional neural network. Advances in Neural Information Processing Systems. 2012. Volume 2: p. 1097-1105.
[8] Albawi S., Mohammed T., Al-Zawi S., Understanding of a convolutional neural network. International Conference on Engineering and Technology (ICET). 2017.
[9] Chen J., Kira Z., Cho Y.K., Deep Learning Approach to Point Cloud Scene Understanding for Automated Scan to 3D Reconstruction. Journal of Computing in Civil Engineering, 2019. Volume 33(Issue 4).
[10] Arabi S., Haghighat A., Sharma A, A deep-learning-based computer vision solution for construction vehicle detection. Computer-Aided Civil and Infrastructure Engineering, 2020. Volume 35(Issue 7): p. 753-767.
[11] 鄭群嚴, 工地安全之跌倒偵測－以深度學習為工具. 2020, 國立臺灣大學.
[12] Saudi M. M., Ma'arof A. H., Ahmad A.,Saudi A. S. M.,Ali M. H., Narzullaev A., Ghazali M. I. M., Image Detection Model for Construction Worker Safety Conditions using Faster R-CNN. IJACSA, 2020. Volume 11.
[13] Alipour M., Harris D. K., Increasing the robustness of material-specific deep learning models for crack detection across different materials. Engineering Structures, 2020. Volume 206.
[14] 吳勻棠, 應用影像辨識分析挖土機之行為模式及其產值, in 土木工程學研究所. 2021, 國立臺灣大學.
[15] 彭大倫, 基於鋼構廠生產線模擬生成資料之大數據分析研究, in 營建工程系. 2020, 國立臺灣科技大學.
[16] 楊雨蒨, 結合竣工時程網圖與BIM技術以利爭議釐清之研究, in 營建管理研究所. 2015, 國立中央大學: 桃園縣.
[17] 吳翌禎, 紀宛君, 謝尚賢, 4D營建管理系統應用於成本控制之初步探討. 技師月刊(48), 2008: p. 44-56.
[18] H.J Wang, J.P Zhan, K.W Chau, M Anson, 4D dynamic management for construction planning and resource utilization. 2004. 13(5): p. 575-589.
[19] Julian H. Kang, M.ASCE, Stuart D. Anderson, M.ASCE, Mark J. Clayton Empirical Study on the Merit of Web-Based 4D Visualization in Collaborative Construction Planning and Scheduling. 200. 133(6): p. 447-461.
[20] Mani Golparvar-Fard, MASc, MSc Application of D4AR – A 4-Dimensional augmented reality model for automating construction progress monitoring data collection, processing and communication. 2009. 14(13): p. 129-153.
[21] Unity, [online], https://unity.com/.
[22] Gang, Su-Myung, Hyeoung-Wook Choi, Do-Ryeong Kim, and Yun-Jae Choung, A Study on the Construction of the Unity 3D Engine Based on the WebGIS System for the Hydrological and Water Hazard Information Display. Procedia Engineering, 2016.
[23] Pour Rahimian, Farzad, Saleh Seyedzadeh, Stephen Oliver, Sergio Rodriguez, and Nashwan Dawood, On-demand monitoring of construction projects through a game-like hybrid application of BIM and machine learning. Automation in Construction, 2020.
[24] 謝政廷, 整合SLAM-based頭戴式MR與BIM之室內施工進度視覺化管理遠端協作系統. 2021, 國立台灣科技大學.