基於影像辨識距離計算之工地即時人員定位方法研究

AN IMAGE RECOGNITION BASED REAL-TIME WORKER LOCATING METHOD

10.6652/JoCICHE.202311_35(7).0008

余文德(Wen-Der Yu)；蕭文達(Wen-Ta Hsiao)；張憲寬(Hsien-Kuan Chang)；謝堉程(Yu-Cheng Xie)

營建安全 ； 電腦視覺 ； 三角立體視覺 ； 即時定位 ； construction safety ； computer vision ； triangulation ； RTLS

中國土木水利工程學刊

35卷7期（2023 / 11 / 01）

705 - 719

繁體中文;英文

營建工地具有開放與動態性，充滿危害與風險，許多工地意外常發生於一瞬之間。因此，掌握勞工之即時定位資訊，是辨識危害情境，預防意外災害發生的重要手段。過去雖有即時定位系統（Real-time Locating System, RTLS）技術之研發與應用，然而不是因為成本過於昂貴就是精度不足，難以達到產業實務應用之目標。本研究旨在應用電腦視覺影像辨識與幾何距離推估技術，配合目前工地常見之攝影機，發展一種既能滿足勞安管理需求且又經濟實用之工地即時人員定位方法。經過驗證，本研究所提出之方法，以工地一般CCTV攝影機取像，在8 m之實驗場域測試時，其平均水平距離誤差為3.23 cm（2.58%）、垂直距離誤差為2.68 cm（0.42%）；而在15 m範圍之工地實測結果，平均水平距離誤差為7.89 cm（9.09%）、垂直距離誤差為7.73 cm（0.65%）。若能提高攝影機之解析度，其監控範圍與精確度可再提高。本方法之精度優於大多數現有之RTLS技術水平，且幾乎不需增加成本，因此具有極高之產業實用性，值得營建產業推廣應用。

Construction sites are inherently hazardous due to their open, dynamic nature, and many accidents occur spontaneously. To mitigate these risks, it is essential to determine workers' real-time location, which aids in identifying hazards and preventing accidents on the site. Although real-time locating system (RTLS) technology has been developed, its widespread adoption has been hindered by its high cost or low accuracy, making it impractical. This research aims to develop an economical and practical real-time locating method for construction workers that meets construction safety management requirements. This method combines computer vision image recognition and geometric distance estimating technique with the common Closed Circuit Television (CCTV) cameras on construction sites. The proposed I-RTLM was tested in the laboratory and field within an 8 m and 15 m range, respectively. The results show that I-RTLM has a mean error (MAE) of 3.23 cm (MAPE = 2.58%) for X-coordinate, and 2.68 cm (MAPE = 0.42%) for Y-coordinate in the lab testing. In the field testing, it achieves an MAE of 7.89 cm (MAPE = 9.09%) for X-coordinate, and 7.73 cm (MAPE = 0.65%) for Y-coordinate, which is superior than most existing RTLS technologies. By increasing the camera's resolution, the monitoring range can be expanded and the locating accuracy can be further improved. Furthermore, this method has strong industrial applicability, requires almost no additional cost, and is worthy of practical construction applications.

1. 余文德,張憲寬,鄭紹材(2017)。整合即時定位系統與建築資訊模型技術於施工人員墜落風險即時防護模式之研究。中國土木水利工程學刊，29(4)，205-217。
   連結：
2. 林楨中,鄭慶武,楊啟男(2013)。中小型營造業施工安全重大職災初探。勞工安全衛生研究季刊，21(3)，277-303。
   連結：
3. Brilakisa, I.,Park, M. W.,Jog, G.(2011).Automated vision tracking of project related entities.Advanced Engineering Informatics,25(4),713-724.
4. Chang, H. K.,Yu, W. D.,Hsiao, W. T.,Bulgakov, A.(2021).A big data based safety risk classification model of construction workers for construction site safety management.Proceedings of the 3rd International Conference on Architecture, Construction, Environment, and Hydraulics (ICACEH 2021),Miaoli, Taiwan:
5. Ding, L.,Fang, W.,Luo, H.,Love, P. E. D.,Ouyang, X.(2018).A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory.Automation in Construction,86,118-124.
6. Fang, Q.,Li, H.,Luo, X.,Ding, L.,An, W.(2018).Detecting non-hardhat-use by a deep learning method from far-field surveillance videos.Automation in Construction,85,1-9.
7. Fang, W. L.,Ding, L. Y.,Luo, H. B.,Love, P. E. D.(2018).Falls from heights: A computer vision-based approach for safety harness detection.Automation in Construction,91,53-61.
8. Gopalakrishnan, K.,Khaitan, S. K.,Choudhary, A.,Agrawal, A.(2017).Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection.Construction and Building Materials,157,322-330.
9. Gu, Y.,Lo, A.,Niemegeers, I.(2009).A survey of indoor positioning systems for wireless personal networks.IEEE Communications Surveys & Tutorials,11(1),13-32.
10. Heinrich HW., Industrial Accident Prevention, McGraw-Hill, New York (1931).
11. Jiang, H.,Learned-Miller, E.(2017).Face Detection with the Faster R-CNN.2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
12. Kim, H.,Lee, Y.,Yim, B.,Park, E.,Kim, H.(2016).On-road object detection using deep neural network.Consumer Electronics-Asia (ICCE-Asia), IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)
13. Krizhevsky, A.,Sutskever, I.,Hinton, G. E.(2012).Imagenet classification with deep convolutional neural networks.Advances in Neural Information Processing Systems
14. Krutikovaa, O.,Sisojevsa, A.,Kovalovsa, M.(2017).Creation of a depth map from stereo images of faces for 3D model reconstruction.Procedia Computer Science,104,452-459.
15. Lee, H. S.,Lee, K. P.,Park, M.,Baek, Y.,Lee, S.(2012).RFID-based real-time locating system for construction safety management.Journal of Computing in Civil Engineering,26(3),366-377.
16. Li, H.,Chan, G.,Wong, J. K. W.,Skitmore, M.(2016).Real-time locating systems applications in construction.Automation in Construction,63,37-47.
17. Li, N.,Calis, G.,Becerik-Gerber, B.(2012).Measuring and monitoring occupancy with an RFID based system for demand-driven HVAC operations.Automation in Construction,24,89-99.
18. Lu, D. M.,Chang, C. F.,Hwang, W.M.(1995).Cross ratio in sphere geometry and its application to mechanism design.Journal of the Franklin Institute,332(2),219-226.
19. Maalek, R.,Sadeghpour, F.(2013).Accuracy assessment of ultra-wide band technology in tracking static resources in indoor construction scenarios.Automation in Construction,30,170-183.
20. Park, J.,Won, D.,Park, K.,Baeg, S.,Baeg, M.(2006).Development of a real time locating system using psd under indoor environments.2006 SICE-ICASE International Joint Conference
21. Park, M. W.,Brilakis, I.(2012).Construction worker detection in video frames for initializing vision trackers.Automation in Construction,28,15-25.
22. Park, M. W.,Koch, C.,Brilakis, I.(2011).Three-dimensional tracking of construction resources using an on-site camera system.Journal of Computing in Civil Engineering,26(4),541-549.
23. Pradhananga, N.,Teizer, J.(2013).Automatic spatiotemporal analysis of construction site equipment operations using GPS data.Automation in Construction,29,107-122.
24. Rangesh, A.,Ohn-Bar, E.,Trivedi, M. M.(2016).Driver hand localization and grasp analysis: A vision-based real-time approach.Intelligent Transportation Systems (ITSC), IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)
25. Rasmussen, J.,Pejtersen, A. M.,Goodstein, L. P.(1994).Cognitive System Engineering.New York:John Wiley & Sons, Inc..
26. Raza, M.,Chen, Z.,Rehman, S. U.,Wang, P.,Wang, J.(2018).Framework for estimating distance and dimension attributes of pedestrians in real-time environments using monocular camera.Neurocomputing,275,533-545.
27. Rubaiyat, A. H. M.,Toma, T. T.,Kalantari-Khandani, M.,Rahman, S. A.,Chen, L. W.,Ye, Y. F.,Pan, C. S.(2016).Automatic detection of helmet uses for construction safety.Proceedings of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops
28. Skibniewski, M. J.,Jang, W. S.(2009).Simulation of accuracy performance for wireless sensor-based construction asset tracking.Computer-Aided Civil and Infrastructure Engineering,24(5),335-345.
29. Taneja, S.,Akcamete, A.,Akinci, B.,Garrett, J. H., Jr.,Soibelman, L.,East, E. W.(2012).Analysis of three indoor localization technologies for supporting operations and maintenance field tasks.Journal of Computing in Civil Engineering,26(6),708-719.
30. Teizer, J.,Caldas, C. H.,Haas, C. T.(2007).Real-time three-dimensional occupancy grid modeling for the detection and tracking of construction resources.Journal of Construction Engineering and Management,133(11),880-888.
31. Teo, A.,Ofori, G.,Tjandra, I.,Kim, H.(2016).Construction Economics and Building,16(4),1-18.
32. Widner, J.T.(1973).Selected Readings in Safety.Macom, Ga:Academy Press.
33. Yang, J.,Shi, Z. K.,Wu, Z. Y.(2016).Vision-based action recognition of construction workers using dense trajectories.Advanced Engineering Informatics,30,327-336.
34. Yeh, C. H.,Lin, C. H.,Kang, L. W.,Huang, C. H.,Lin, M. H.,Chang, C. Y.,Wang, C. C.(2021).Lightweight deep neural network for joint learning of underwater object detection and color conversion.IEEE Transactions on Neural Networks and Learning Systems,33(11)
35. Yu, W. D.,Chang, H. K.,Hsiao, W. T.,Chiang, H. S.,Bulgakov, A.(2022).A model combining computer vision and drone for proactive construction site safety monitoring.Proceedings of the 12th International Conference on Engineering, Project, and Production Management (EPPM 2022),Athens, Greece:
36. Yu, W. D.,Chang, H. K.,Hsie, Y. C.,Bulgakov, A.(2021).An image recognition-based distance measurement technique for real-time locating of construction workers.Proceedings of the 3rd IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability 2021 (ECBIOS 2021),Tainan, Taiwan:
37. Yu, W. D.,Liao, H. C.,Hsiao, W. D.,Chang, H. K.,Tsai, C. K.,Lin, C. C.(2020).Automatic safety monitoring of construction hazard working zone-A semantic segmentation based deep learning approach.Proceedings of the 2020 International Conference on Automation and Logistics (ICAL 2020),Beijing, China:
38. Yu, W. D.,Liao, H. C.,Hsiao, W. T.,Chang, H. K.,Wu, T. Y.,Lin, C. C.(2022).Real-time identification of worker’s personal safety equipment with hybrid machine learning techniques.International Journal of Machine Learning and Computing,12(3),79-84.
39. Zhang, J.,Hu, H.,Chen, S.,Huang, Y.,Guan, Q.(2016).Cancer cells detection in phase-contrast microscopy images based on faster R-CNN.9th International Symposium on Computational Intelligence and Design (ISCID), Vol. 1
40. Zhang, L.,Lin, L.,Liang, X.,He, K.(2016).Is faster R-CNN doing well for pedestrian detection?.European Conference on Computer Vision
41. 張書誠(2015)。台北，國立臺灣師範大學資訊工程研究所。
42. 勞動部職業安全衛生署，勞動檢查法第二十八條所定勞工有立即發生危險之虞認定標準—第 3 條，全國法規資料庫系統： https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=N0070016 ， 2005/6/10 修正，2022/6/26 查詢。
43. 勞動部職業安全衛生署，起重升降機具安全規則—第21 條，全國法規資料庫系統： https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=N0060013，2020/8/20 修正，2022/6/26 查詢。
44. 黃子銘(2019)。臺中，朝陽科技大學。