請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74964
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 謝尚賢(Shang-Hsien Hsieh) | |
dc.contributor.author | Rong-Chun Chien | en |
dc.contributor.author | 簡榮均 | zh_TW |
dc.date.accessioned | 2021-06-17T09:11:25Z | - |
dc.date.available | 2020-09-03 | |
dc.date.copyright | 2019-09-03 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-27 | |
dc.identifier.citation | 陳韋成, 丁肇隆, 張瑞益(2016)。營建工地安全系統之工地安全帽及背心偵測。資訊、科技與社會學報,頁 65-77。
勞動部職業安全衛生署(民107)。中華民國 106 年勞動檢查年報。 新北市:勞動部職業安全衛生署。 Abramovich, F., & Pensky, M. (2015). Classification with many classes: challenges and pluses. eprint arXiv:1506.01567, arXiv:1506.01567. Barro-Torres, S., Fernández-Caramés, T. M., Pérez-Iglesias, H. J., & Escudero, C. J. (2012). Real-time personal protective equipment monitoring system. Computer Communications, 36(1), 42-50. doi: 10.1016/j.comcom.2012.01.005 Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. eprint arXiv:1602.00763, arXiv:1602.00763. Ding, L., Fang, W., Luo, H., Love, P. E. D., Zhong, B., & 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. doi: 10.1016/j.autcon.2017.11.002 Dong, S., He, Q., Li, H., & Yin, Q. (2015). Automated PPE misuse identification and assessment for safety performance enhancement. Paper presented at the Iccrem 2015, Luleå, Sweden. Fang, Q., Li, H., Luo, X., Ding, L., Luo, H., & Li, C. (2018). Computer vision aided inspection on falling prevention measures for steeplejacks in an aerial environment. Automation in Construction, 93, 148-164. doi: 10.1016/j.autcon.2018.05.022 Fang, Q., Li, H., Luo, X., Ding, L., Luo, H., Rose, T. M., & An, W. (2018). Detecting non-hardhat-use by a deep learning method from far-field surveillance videos. Automation in Construction, 85, 1-9. doi: 10.1016/j.autcon.2017.09.018 Fang, Q., Li, H., Luo, X., Ding, L., Rose, T. M., An, W., & Yu, Y. (2018). A deep learning-based method for detecting non-certified work on construction sites. Advanced Engineering Informatics, 35, 56-68. doi: 10.1016/j.aei.2018.01.001 Fang, W., Ding, L., Luo, H., & Love, P. E. D. (2018). Falls from heights: A computer vision-based approach for safety harness detection. Automation in Construction, 91, 53-61. doi: 10.1016/j.autcon.2018.02.018 Fang, W., Ding, L., Zhong, B., Love, P. E. D., & Luo, H. (2018). Automated detection of workers and heavy equipment on construction sites: A convolutional neural network approach. Advanced Engineering Informatics, 37, 139-149. doi: 10.1016/j.aei.2018.05.003 Fang, W., Zhong, B., Zhao, N., Love, P. E. D., Luo, H., Xue, J., & Xu, S. (2019). A deep learning-based approach for mitigating falls from height with computer vision: Convolutional neural network. Advanced Engineering Informatics, 39, 170-177. doi: 10.1016/j.aei.2018.12.005 Girshick, R. (2015). Fast R-CNN. eprint arXiv:1504.08083, arXiv:1504.08083. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2013). Rich feature hierarchies for accurate object detection and semantic segmentation. eprint arXiv:1311.2524, arXiv:1311.2524. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep residual learning for image recognition. eprint arXiv:1512.03385, arXiv:1512.03385. Hu, G. X., Yang, Z., Hu, L., Huang, L., & Han, J. M. (2018). Small object detection with multiscale features. International Journal of Digital Multimedia Broadcasting, 2018, 1-10. doi: 10.1155/2018/4546896 Huang, X., & Hinze, J. (2003). Analysis of construction worker fall accidents. Journal of Construction Engineering and Management, 129(3), 262-271. doi: 10.1061/(asce)0733-9364(2003)129:3(262) Kelm, A., Laußat, L., Meins-Becker, A., Platz, D., Khazaee, M. J., Costin, A. M., Helmus, M., Teizer, J. (2013). Mobile passive Radio Frequency Identification (RFID) portal for automated and rapid control of Personal Protective Equipment (PPE) on construction sites. Automation in Construction, 36, 38-52. doi: 10.1016/j.autcon.2013.08.009 Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Paper presented at the Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Lake Tahoe, Nevada. Li, K., Zhao, X., Bian, J., & Tan, M. (2018). Automatic safety helmet wearing detection. eprint arXiv:1802.00264, arXiv:1802.00264. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2016). Feature pyramid networks for object detection. eprint arXiv:1612.03144, arXiv:1612.03144. Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. eprint arXiv:1708.02002, arXiv:1708.02002. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2015). SSD: Single Shot MultiBox Detector. eprint arXiv:1512.02325, arXiv:1512.02325. doi: 10.1007/978-3-319-46448-0_2 Lombardi, D. A., Verma, S., Brennan, M. J., & Perry, M. J. (2009). Factors influencing worker use of personal protective eyewear. Accident; analysis and prevention, 41(4), 755-762. Mneymneh, B. E., Abbas, M., & Khoury, H. (2017). Automated hardhat detection for construction safety applications. Procedia Engineering, 196, 895-902. doi: 10.1016/j.proeng.2017.08.022 Mneymneh, B. E., Abbas, M., & Khoury, H. (2019). Vision-based framework for intelligent monitoring of hardhat wearing on construction sites. Journal of Computing in Civil Engineering, 33(2), 04018066. doi: 10.1061/(asce)cp.1943-5487.0000813 Park, M.-W., Elsafty, N., & Zhu, Z. (2015). Hardhat-wearing detection for enhancing on-site safety of construction workers. Journal of Construction Engineering and Management, 141(9), 04015024. doi: 10.1061/(asce)co.1943-7862.0000974 Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2015). You only look once: unified, real-time object detection. eprint arXiv:1506.02640, arXiv:1506.02640. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. eprint arXiv:1506.01497, arXiv:1506.01497. Roberts, D., Bretl, T., & Golparvar-Fard, M. (2017). Detecting and classifying cranes using camera-equipped UAVs for monitoring crane-related safety hazards. Computing in Civil Engineering 2017, 442-449. doi: doi:10.1061/9780784480847.055 Rubaiyat, A. H. M., Toma, T. T., Kalantari-Khandani, M., Rahman, S. A., Chen, L., Ye, Y., & Pan, C. S. (2016, 13-16 Oct. 2016). Automatic detection of helmet uses for construction safety. Paper presented at the 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW). Seo, J., Han, S., Lee, S., & Kim, H. (2015). Computer vision techniques for construction safety and health monitoring. Advanced Engineering Informatics, 29(2), 239-251. doi: 10.1016/j.aei.2015.02.001 Seong, H., Choi, H., Cho, H., Lee, S., Son, H., & Kim, C. (2017). Vision-based safety vest detection in a construction scene. Paper presented at the Proceedings of the 34th International Symposium on Automation and Robotics in Construction (ISARC), Taipei, Taiwan. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. eprint arXiv:1409.1556, arXiv:1409.1556. doi: 10.1.1.740.6937 Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of data in deep learning era. eprint arXiv:1707.02968, arXiv:1707.02968. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2016). Inception-v4, Inception-ResNet and the impact of residual connections on learning. eprint arXiv:1602.07261, arXiv:1602.07261. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. (2014). Going deeper with convolutions. eprint arXiv:1409.4842, eprint arXiv:1409.4842. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2015). Rethinking the inception architecture for computer vision. eprint arXiv:1512.00567, arXiv:1512.00567. Wu, H., & Zhao, J. (2018). An intelligent vision-based approach for helmet identification for work safety. Computers in Industry, 100, 267-277. doi: 10.1016/j.compind.2018.03.037 Wu, J., Geyer, C., & Rehg, J. M. (2011, 9-13 May 2011). Real-time human detection using contour cues. Paper presented at the 2011 IEEE International Conference on Robotics and Automation. Zalewski, E. (2004). Enforcing PPE use. Occupational health & safety, 73 2, 66, 89. Zhang, H., Yan, X., Li, H., Jin, R., & Fu, H. (2019). Real-time alarming, monitoring, and locating for non-hard-hat use in construction. Journal of Construction Engineering and Management, 145(3), 04019006. doi: 10.1061/(asce)co.1943-7862.0001629 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74964 | - |
dc.description.abstract | 在工地,確實的配戴個人防護裝備(Personal Protective Equipment)是有效避免意外發生的方法之一。然而工地人員為了作業方便、舒適度等原因,常有未依規定穿著適當裝備的情況發生。因此,如何確保個人防護裝備的配戴一直都是工地安全的重點項目之一。
近年來隨著顯示卡的性能提升及深度學習的崛起,影像辨識領域有著相當大的進展。若以工地監視器的畫面進行影像辨識,比起傳統上以感測器為主的監控方式,能以更低的成本達成即時的個人防護裝備偵測。 本研究提出一個新的二階段偵測方法用以偵測未戴安全帽、未穿反光背心和赤裸上身三項PPE違規。首先,基於RetinaNet的物件偵測模型會先辨識出畫面中人員的位置,再利用基於InceptionNet的分類模型對人物影像進行裝備違規的辨識。相較於直接使用物件偵測方法偵測PPE,二階段的辨識方法可以避免在進行物件偵測時PPE因為縮圖而導致特徵遺失的問題。 本研究搜集了3015張工地影像,利用遷移學習完成模型的訓練,並測試其在不同人物解析度下的表現。結果顯示本研究的方法能在10 fps的運算速度下,有效地偵測出工地的PPE違規,在人物解析度為120像素以上時,Precision和Recall都能在0.9以上,而在人物解析度為60像素時也能有0.8的Precision。 | zh_TW |
dc.description.abstract | Being well-equipped with Personal Protective Equipment (PPE) plays an essential role in construction sites to protect individuals from accidents. However, due to inconvenience and discomfort, it is common to see workers not wearing them on site. Therefore, ensuring the wearing of PPE remains important subject to facilitate construction sites safety.
In recent years, because of the increasing performance of graphic cards and the rise of deep learning, Convolutional neural network (CNN) based computer vision techniques is receiving increased attention. Monitoring PPE use via computer vision method has been considered to be effective rather than sensor-based method. In this paper, a two-stage method is proposed to automatically detect 3 kinds of PPE violations, including non-hardhat-use, un-equipped with safety vest and bare to the waist. Combining object detection model and classification model, our two-stage method can avoid feature loss of small-scale PPE to achieve better accuracy. First, the object detection model based on RetinaNet is adopted to detect the presence of worker in the image. Then, by using InceptionNet as classification model, these worker images are input to identify the violations of PPE use. This study collected 3015 site images to preform transfer learning. The results show that our method can effectively detect PPE violations at the frame rate of 10 fps. When the image resolution of the worker is 120 pixels or more, both precision and recall can be above 0.9; while the resolution is only 60 pixels, it could also achieve the precision of 0.8. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T09:11:25Z (GMT). No. of bitstreams: 1 ntu-108-R05521609-1.pdf: 2738794 bytes, checksum: 196f2c485585f302ebc8390b22a9d780 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 口試委員會審定書 i
誌謝 ii 摘要 iii Abstract iv 目錄 v 圖目錄 vii 表目錄 ix 第一章 緒論 1 1.1研究背景 1 1.2研究目的 2 1.3研究架構 2 第二章 文獻回顧 4 2.1傳統PPE偵測方法 4 2.2卷積神經網路 6 2.3物件偵測演算法 8 2.4基於深度學習的PPE偵測方法 12 第三章 研究方法 14 3.1即時裝備違規辨識架構 14 3.2人員偵測 15 3.3裝備違規辨識 16 第四章 模型訓練與實作 17 4.1資料蒐集與標籤 17 4.2準確度定義 19 4.3物件偵測模型訓練與結果 19 4.4分類模型訓練與結果 25 4.5即時辨識系統實作 28 第五章 驗證與討論 30 5.1混淆矩陣 30 5.2驗證方式 31 5.3驗證結果 33 5.4討論 38 第六章 結論與建議 40 6.1研究貢獻 40 6.2未來建議 40 參考文獻 41 | |
dc.language.iso | zh-TW | |
dc.title | 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 | zh_TW |
dc.title | Deep Learning Based Computer Vision Techniques for Real-time Identification of Construction Site Personal Equipment Violations | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳柏華(Albert Y. Chen),韓仁毓(Jen-Yu Han) | |
dc.subject.keyword | 工地安全,個人防護裝備,電腦視覺,深度學習,卷積神經網路, | zh_TW |
dc.subject.keyword | Construction sites safety,PPE,Computer vision,Deep learning,CNN, | en |
dc.relation.page | 43 | |
dc.identifier.doi | 10.6342/NTU201900514 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-27 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 2.67 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。