專業營建管理涵蓋工期、成本、安全和品質四大準則。在工程生命週期中，施工階段是實際進行工程建設的階段，需要處理各種安全風險、變更要求和資源限制等問題，工期管控是其中的核心，需要制定工期計劃，監測進度並進行調整和優化，工時在工程管理中用於評估進度、計算成本、安排資源和管理時間表。過去的工時記錄方式通常是手動紀錄，需要投入額外的人力，易出現誤差，且缺乏統整和分析，隨著人工智慧技術的成熟，許多產業開始應用人工智慧在產品和作業中，例如在醫療診斷中，深度學習模型可以自動分析圖像，幫助醫生進行準確診斷，同時也被應用於金融領域的風險評估和投資管理，以及晶片品質監測等領域，而於土木產業中，人工智慧技術可以應用於結構設計優化，提高結構效能和安全性，並降低成本。
然而，過去針對工時問題的相關研究多著重於數學模型的建構，缺乏考慮缺工和人事成本上漲等現實因素。此外，工時記錄通常是人工的工作，存在記錄誤差和缺乏統整分析的問題，因此，本研究旨在應用深度學習的人工智慧技術，建立一個物件偵測系統，主要用於辨識施工階段的機具、工人和物料，透過將辨識結果與資訊化系統結合，進行統整和分析，並記錄機具和工人的作業時間。這將有助於解決工時記錄的人力成本和誤差問題，並提供準確的工時資料，進而改進工時控制。
應用深度學習技術中的物件偵測算法模型YOLOv7，結合Microsoft的Excel軟體，以自動化和系統化的方式記錄土木工程施工階段的工時，透過模型辨識施工現場中的機具和人員，將辨識結果及相關資訊統整，以減少人力成本和時間，並進行自動化的整理和分析。研究目標主要包括建立土木領域的物件標註資料集，實現施工階段機具和人工時的自動記錄，以及將深度學習物件偵測技術應用於土木工程中，透過本研究，期望能有效提高施工管理的效率，減少人力成本，並提升工時記錄的準確性和精確性。

Construction management in civil engineering encompasses four major criteria: project duration, cost, safety, and quality. The construction phase is where actual construction activities take place, involving safety risks, change requests, and resource constraints. Effective schedule control is crucial, requiring the development of a project schedule, progress monitoring, and adjustments. Working hours are used to assess progress, calculate costs, allocate resources, and manage timelines. Traditional manual recording methods are prone to errors and lack consolidation and analysis capabilities.

With the maturity of AI technology, industries have started applying AI in various domains. In civil engineering, AI can optimize structural design, improve safety, and reduce costs. This study aims to use deep learning's object detection, specifically the YOLOv7 algorithm, and integrate it with Microsoft Excel to automate and systematize working hour recording in construction phases.

By identifying machinery and personnel, the system will consolidate and analyze data, reducing labor costs and enabling accurate recording. The objectives include creating an annotated dataset, automating working hour recording, and applying deep learning in civil engineering. The research aims to improve efficiency, reduce costs, and enhance the accuracy of working hour recording.

1. Barrie, D. S., & Paulson, B. C. (1992). Professional construction management: including CM, design-construct, and general contracting. (No Title).
2. Beymer, D., McLauchlan, P., Coifman, B., & Malik, J. (1997). A real-time computer vision system for measuring traffic parameters. Paper presented at the Proceedings of IEEE computer society conference on computer vision and pattern recognition.
3. Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
4. Cottrell, W. D. (1999). Simplified program evaluation and review technique (PERT). Journal of construction Engineering and Management, 125(1), 16-22.
5. Cui, L., Ma, R., Lv, P., Jiang, X., Gao, Z., Zhou, B., & Xu, M. (2018). MDSSD: multi-scale deconvolutional single shot detector for small objects. arXiv preprint arXiv:1805.07009.
6. Dumoulin, V., & Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
7. Elgendy, M. (2020). Deep learning for vision systems: Simon and Schuster.
8. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
9. He, J., Xiao, Y., Huang, L., Li, A., Chen, Y., Ma, Y., . . . Zhan, Y. (2022). Application of leakage pre-warning system for hazardous chemical storage tank based on YOLOv3-prePReLU algorithm. Journal of Loss Prevention in the Process Industries, 80, 104905. doi: https://doi.org/10.1016/j.jlp.2022.104905
10. Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., & Shi, J. (2020). Foveabox: Beyound anchor-based object detection. IEEE Transactions on Image Processing, 29, 7389-7398.
11. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
12. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
13. Lee, Y., Hwang, J.-w., Lee, S., Bae, Y., & Park, J. (2019). An energy and GPU-computation efficient backbone network for real-time object detection. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops.
14. Li, Y., Lu, Y., & Chen, J. (2021). A deep learning approach for real-time rebar counting on the construction site based on YOLOv3 detector. Automation in Construction, 124, 103602. doi: https://doi.org/10.1016/j.autcon.2021.103602
15. Li, Z., & Zhou, F. (2017). FSSD: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960.
16. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
17. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., . . . Zitnick, C. L. (2014). Microsoft coco: Common objects in context. Paper presented at the Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13.
18. Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
19. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. Paper presented at the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14.
20. Marr, D., & Poggio, T. (1979). A computational theory of human stereo vision. Proceedings of the Royal Society of London. Series B. Biological Sciences, 204(1156), 301-328.
21. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
22. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.
23. Rosebrock, A. (2016). Intersection over Union (IoU) for object detection. Diambil kembali dari PYImageSearch https//www. pyimagesearch. com/2016/11/07/intersection-over-union-iou-for-object-detection.
24. Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. Paper presented at the International conference on machine learning.
25. Terven, J., & Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. arXiv preprint arXiv:2304.00501.
26. Tian, Z., Shen, C., Chen, H., & He, T. (2019). Fcos: Fully convolutional one-stage object detection. Paper presented at the Proceedings of the IEEE/CVF international conference on computer vision.
27. Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2021). Scaled-yolov4: Scaling cross stage partial network. Paper presented at the Proceedings of the IEEE/cvf conference on computer vision and pattern recognition.
28. Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696.
29. Williams, D. P. (2019). Demystifying deep convolutional neural networks for sonar image classification.
30. Xing, Z., Zhang, Z., Yao, X., Qin, Y., & Jia, L. (2022). Rail wheel tread defect detection using improved YOLOv3. Measurement, 203, 111959. doi: https://doi.org/10.1016/j.measurement.2022.111959
31. Ye, G., Qu, J., Tao, J., Dai, W., Mao, Y., & Jin, Q. (2023). Autonomous surface crack identification of concrete structures based on the YOLOv7 algorithm. Journal of Building Engineering, 106688. doi: https://doi.org/10.1016/j.jobe.2023.106688
32. Yu, Z., Shen, Y., & Shen, C. (2021). A real-time detection approach for bridge cracks based on YOLOv4-FPM. Automation in Construction, 122, 103514. doi: https://doi.org/10.1016/j.autcon.2020.103514
33. Zeng, T., Wang, J., Cui, B., Wang, X., Wang, D., & Zhang, Y. (2021). The equipment detection and localization of large-scale construction jobsite by far-field construction surveillance video based on improving YOLOv3 and grey wolf optimizer improving extreme learning machine. Construction and Building Materials, 291, 123268. doi: https://doi.org/10.1016/j.conbuildmat.2021.123268
34. Zhang, D.-Y., Luo, H.-S., Cheng, T., Li, W.-F., Zhou, X.-G., Wei, G., . . . Diao, Z. (2023). Enhancing wheat Fusarium head blight detection using rotation Yolo wheat detection network and simple spatial attention network. Computers and Electronics in Agriculture, 211, 107968. doi: https://doi.org/10.1016/j.compag.2023.107968
35. Zhang, S., Chi, C., Yao, Y., Lei, Z., & Li, S. Z. (2020). Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
36. Zhang, Y., Huang, J., & Cai, F. (2020). On Bridge Surface Crack Detection Based on an Improved YOLO v3 Algorithm. IFAC-PapersOnLine, 53(2), 8205-8210. doi: https://doi.org/10.1016/j.ifacol.2020.12.1994
37. Zhu, C., He, Y., & Savvides, M. (2019). Feature selective anchor-free module for single-shot object detection. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.
38. 吳思穎. (2021). 以深度學習方法發展之電腦輔助瘜肉定位系統應用於大腸鏡切除手術教學.
39. 洪瑋宏（2020）。基於YOLOv4應用的軌道缺失扣件偵測。未出版之碩士論文，大同大學資訊工程學系(所)，台北市。
40. 范琝瀚（2021）。基於YOLOv4模型的時尚圖像物件分類辨識研究。未出版之碩士論文，國立臺北科技大學工業工程與管理系，台北市。
41. 劉子綸. (2004). 工率迴算模式建立營建工程單價分析之研究. (碩士), 國立中興大學, 台中市. Retrieved from https://hdl.handle.net/11296/7x4qhz
42. 蔡明儒, 陳正忠, 石豐銘, & 周文陽. (2007). 視訊監控技術於土木工程應用上之未來趨勢. 中興工程(97), 53-62.
43. 蕭瑋廷. (2018). 基於深度學習的大腸息肉即時自動偵測與分類. (碩士), 國立中正大學, 嘉義縣. Retrieved from https://hdl.handle.net/11296/2hwn36
44. 簡榮均. (2019). 基於深度學習的電腦視覺技術於即時工地人員裝備違規辨識. (碩士), 國立臺灣大學, 台北市. Retrieved from https://hdl.handle.net/11296/x7n995
45. 顏大立（2021）。基於YOLOv4之即時旗語辨識研究。未出版之碩士論文，中原大學電子工程研究所，桃園縣。
46. 黃一峰, 陳柏翰, & 陳思愷. (2021). 使用 U-net 全卷積神經網路實現橋梁塗層缺陷識別自動化. 中國土木水利工程學刊, 33(8), 605-617.