研究生: |
吳振豪 Wu, Chen-Hao |
---|---|
論文名稱: |
輕量化且高效能的多角度車牌辨識模型 A Lightweight, High-Performance Multi-Angle License Plate Recognition Model |
指導教授: |
林政宏
Lin, Cheng-Hung |
學位類別: |
碩士 Master |
系所名稱: |
電機工程學系 Department of Electrical Engineering |
論文出版年: | 2019 |
畢業學年度: | 107 |
語文別: | 中文 |
論文頁數: | 42 |
中文關鍵詞: | 車牌辨識系統 、深度學習模型 、輕量化 、多角度 |
英文關鍵詞: | license plate recognition system, deep learning model, lightweight, multi-angle |
DOI URL: | http://doi.org/10.6345/NTNU201900730 |
論文種類: | 學術論文 |
相關次數: | 點閱:171 下載:2 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來在台灣的街道上,經常會看到許多路邊收費員一手騎著機車,一手拿著行動裝置對在路邊停放的汽機車開立繳費通知單。然而路邊收費員的工作內容與危險息息相關,除了要先將機車停靠在要收費的汽機車旁,還得用雙眼確認車牌號碼,將車牌號碼輸入至行動裝置中,再將繳費單貼在汽機車上。因此本研究意圖將自動車牌辨識系統實現在路邊收費員的行動裝置中,提升路邊收費員的工作效率以降低他們在道路上工作的時間。
自動車牌辨識系統目前已經廣泛的運用於日常生活中,例如:收費系統、進出管理系統、交通安全系統等。然而現有之自動車牌辨識系統必須在許多約束條件下才能達到良好的辨識率,例如固定的角度與固定光源。此外,由於一般的行動裝置之運算資源不足,應用在車牌辨識上無法在複雜的環境或是歪斜的角度下擁有良好的辨識率。
因此本論文提出了一種輕量化且高效能的多角度車牌字元辨識模型,降低了傳統車牌辨識的複雜度與運算量,也針對路邊收費員的工作環境,使用不同環境、角度與大小的車牌去做資料的收集。
最後,我們訓練了一個針對車牌字元結構優化過的深度學習模型來辨識車牌上的字元。實驗結果顯示此模型能夠辨識100公分內傾斜0~60度之車牌,且recall rate達89.6%。與Tiny-YOLOv2在同樣的範圍下相比,所提出的模型的運算量減少61%,處理時間減少30%,可是recall rate略為下降。
On the streets of Taiwan, many roadside tollers are often seen riding motorcycles in one hand, and the other hand holding mobile devices to issue payment notices for cars and motorcycles parked on the roadsides. The work of roadside tollers is very dangerous. First, they must first park their motorcycles next to the roadside cars and motorcycles. Then they use their eyes to confirm the license plate number, enter the license plate number into the mobile device, and finally place the bill on the car's windows or attach the bill to the motorcycles. Our idea is to implement an automated license plate recognition system in mobile devices to increase the efficiency of roadside tollers and reduce their work time on the road.
Recently, license plate recognition systems have been widely used in various aspects of life, such as parking lot toll systems, access management systems, and traffic management systems. However, existing license plate recognition systems must have good recognition rates under a number of constraints, such as fixed angles and fixed light sources. Moreover, due to the insufficient computing resources of the general mobile device, the application cannot have a good recognition rate in the complex environment or skewed angle in the license plate recognition. Therefore, this paper proposes a lightweight and high-performance multi-angle license plate character recognition model, which reduces the complexity and computational complexity of traditional license plate recognition. This paper also collects a large number of license plate images from different environments, angles and sizes as training data. Finally, we propose an optimized deep learning model to identify the characters on license plates. The experimental results show that the proposed model can recognize the license plate with a tilt of 0~60 degrees, and the overall recall rate is 84.5%. Compared with Tiny-YOLOv2, the proposed model has a 61% reduction in computational complexity and a 30% reduction in processing time, but the recall rate is slightly reduced.
[1] S. Du, M. Ibrahim, M. Shehata and W. Badawy, “Automatic License Plate Recognition (ALPR): A State-of-the-Art Review,” in IEEE Transactions on Circuits and Systems for Video Technology, vol. 23, no. 2, pp. 311-325, Feb. 2013.
[2] L. Connie, C. Kim On and A. Patricia Patricia, “A Review of Automatic License Plate Recognition System in Mobile-based Platform,” Journal of Telecommunication, Electronic and Computer Engineering (JTEC), Vol 10, No 3-2, pp. 77-82, 2018.
[3] N. N. Kyaw, G. R. Sinha and K. L. Mon, “License Plate Recognition of Myanmar Vehicle Number Plates A Critical Review,” IEEE 7th Global Conference on Consumer Electronics (GCCE), Nara, 2018, pp. 771-774..
[4] S. Tang and W. Li, “Number and letter character recognition of vehicle license plate based on edge Hausdorff distance,” in Proc. Int. Conf. Parallel Distributed Comput. Applicat. Tech. , 2005, pp. 850–852.
[5] V. Shapiro and G. Gluhchev, “Multinational license plate recognition system: Segmentation and classification,” in Proc. Int. Conf. Pattern Recognit. , 2004, vol. 4., pp. 352–355.
[6] Yo-Ping Huang, Shi-Yong Lai and Wei-Po Chuang, “A template-based model for license plate recognition,” IEEE International Conference on Networking, Sensing and Control, 2004, Taipei, Taiwan, 2004, Vol.2, pp. 737-742.
[7] Mi-Ae Ko and Young-Mo Kim, “License plate surveillance system using weighted template matching,” 32nd Applied Imagery Pattern Recognition Workshop, Washington, DC, USA, 2003, pp. 269-274.
[8] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A Large-Scale Hierarchical Image Database,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2009, pp. 248–255.
[9] A. Mutholib, T. S. Gunawan, and M. Kartiwi, “Design and implementation of automatic number plate recognition on android platform,” 2012 International Conference on Computer and Communication Engineering (ICCCE), Kuala Lumpur, 2012, pp. 540-543.
[10] R.K. Romadhon, M. Ilham, N.I. Munawar, S. Tan, and R. Hedwig, “Android-based license plate recognition using pre-trained neural network,” in Internet Working Indonesia Journal, pp. 15-18, 2012.
[11] J. Chen, “Chinese license plate identification based on Android platform,” 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT), Ghaziabad, 2017, pp. 1-5.
[12] Q. Wang, “License plate recognition via convolutional neural networks,” 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, 2017, pp. 926-929.
[13] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proc. of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'14) , 2014, pp.580-587.
[14] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9):1627–1645, 2010.
[15] M. Everingham, L. Gool, C. K. Williams, J. Winn, and A. Zisserman, “The Pascal Visual Object Classes Challenge: A Retrospective,” Int. J. Comput. Vision 111, 1, 2015.
[16] J. Uijlings, K. van de Sande, T. Gevers, and A. Smeulders, “Selective search for object recognition,” IJCV, 2013.
[17] P.F. Felzenszwalb, D.P. Huttenlocher, “Efficient Graph-Based Image Segmentation”, Int'l J. Computer Vision, vol. 59, pp. 167-181, 2004.
[18] R. Girshick, “Fast R-CNN,” in ICCV, 2015.
[19] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” in NIPS, 2015.
[20] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 779-788.
[21] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 6517-6525.
[22] Tzutalin. LabelImg. Git code (2015). https://github.com/tzutalin/labelImg
[23] G. Hsu, J. Chen and Y. Chung, “Application-Oriented License Plate Recognition,” in IEEE Transactions on Vehicular Technology, vol. 62, no. 2, pp. 552-561, Feb. 2013.
[24] R. Huang, J. Pedoeem and C. Chen, “YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers,” 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 2018, pp. 2503-2510.
[25] 中華民國交通部公路總局https://www.thb.gov.tw/page?node=92d4a6e2-9afb-464d-a2eb-2be8d26d8d89
[26] FFmpeg Developers. (2016). ffmpeg tool (Version be1d324) [Software].Available from http://ffmpeg.org/