請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84087完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅楸善 | zh_TW |
| dc.contributor.advisor | Chiou-Shann Fuh | en |
| dc.contributor.author | 孫譽 | zh_TW |
| dc.contributor.author | Yu Sun | en |
| dc.date.accessioned | 2023-03-19T22:04:37Z | - |
| dc.date.available | 2023-12-26 | - |
| dc.date.copyright | 2022-08-02 | - |
| dc.date.issued | 2022 | - |
| dc.date.submitted | 2002-01-01 | - |
| dc.identifier.citation | [Chiu 2020] Y. C. Chiu, C. Y. Tsai et al., "Mobilenet-SSDv2: An Improved Object Detection Model for Embedded Systems," Proceedings of International Conference on System Science and Engineering, Kagawa, Japan, pp. 1-5, 2020. [Hannun 2017] Hannun, "Sequence Modeling with CTC," Distill, https://distill.pub/2017/ctc/, 2017. [Howard 2017] A. G. Howard, M. L. Zhu et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” https://arxiv.org/pdf/1704.04861.pdf, 2017. [Huang 2021] X. Huang, X. Wang, W. Lv, et al., “PP-YOLOv2: A Practical Object Detector,” https://arxiv.org/pdf/2104.10419.pdf, 2021. [Iandola 2016] F. N. Iandola, S. Han, et al., “SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and <0.5MB Model Size,” https://arxiv.org/pdf/1602.07360.pdf, 2016. [Intel 2022] Intel, “Intel Distribution of OpenVINO Toolkit,” https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/overview.html, 2022. [Liu 2016] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, “SSD: Single Shot MultiBox Detector,” Proceedings of European Conference on Computer Vision, Amsterdam, Netherlands, LNCS, Vol. 9905, pp. 21-37, 2016. [Sandler 2018] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp. 4510-4520, 2018. [Silva 2017] S. M. Silva and C. R. Jung, “Real-Time Brazilian License Plate Detection and Recognition Using Deep Convolutional Neural Networks,” Proceedings of Conference on Graphics, Patterns, and Images, Niterói, Brazil, pp. 55–62, 2017. [Silva 2018] S. M. Silva and C. R. Jung, “License Plate Detection and Recognition in Unconstrained Scenarios,” Proceedings of European Conference on Computer Vision, Munich, Germany, LNCS, Vol. 11216, pp. 593-609, 2018. [Simonyan 2014] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” https://arxiv.org/pdf/1409.1556.pdf, 2014. [Szegedy 2016] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,” https://arxiv.org/pdf/1602.07261.pdf, 2016. [Wang 2021] Y. Wang and Z. P. Bian et al., “Rethinking and Designing a High-Performing Automatic License Plate Recognition Approach,” https://arxiv.org/pdf/2011.14936.pdf, 2021. [Zherzdev 2018] S. Zherzdev and A. Gruzdev, “LPRNet: License Plate Recognition via Deep Neural Networks,” https://arxiv.org/pdf/1806.10447.pdf, 2018. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84087 | - |
| dc.description.abstract | 本論文提出一個專用於機車上的車牌辨識(License Plate Recognition)系統解決方案。搭載工業電腦以及人工智慧(AI: Artificial Intelligence)加速卡，可在載具行進期間，同時進行實時的車牌辨識。本篇論文透過自行改良的深度學習網路架構，提高機車在行駛途中攝影機所拍下的影像辨識準確率。此外，本研究更提出整個系統安裝至機車時的配置以及設計參考。為了更好的使用者體驗，本篇研究將車牌辨識程式整合成一系列應用程式介面(API: Application Programming Interface)，實際開發出一套完整的「AI人工智能警用機車影像識別偵查系統」。配合應用程式介面的開發，此系統可以實時處理兩部攝影機的影像輸入，同時對前方車道以及右側路邊停車區域進行車牌辨識。 | zh_TW |
| dc.description.abstract | We propose SunLPR, a license plate recognition system solution dedicated to common scooter. Equipped with IPC (Industrial Personal Computer) and AI (Artificial Intelligence) acceleration card (Mustang V-100 Movidius Mx8). Our SunLPR can perform real-time license plate inference tasks when scooter is moving. A modified deep learning network also implicitly improves the accuracy of plate number recognition. And a brief design of the AI scooter was introduced, including cameras and battery. In this thesis, SunLPR was merged into an API (Application Programming Interface) for a better user experience. This AI system can deal with two camera’s video input in real-time and tracking the license plates in front and on the right. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:04:37Z (GMT). No. of bitstreams: 1 U0001-1307202219444500.pdf: 5326798 bytes, checksum: 8df66a50f93ea1cfc6cb3992ebe53f83 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES x Chapter 1 Introduction 1 1.1 Overview 1 1.2 License Plates in Natural Scene 4 1.3 Thesis Organization 8 Chapter 2 Related Works 9 Chapter 3 Background 11 3.1 MobileNet-SSD 11 3.2 LPRNet: License Plate Recognition via Deep Neural Networks 16 3.3 OpenVINO: Open Visual Inference and Neural Network Optimization 20 3.3.1 Overview 20 3.3.2 Deployment Workflow 22 Chapter 4 Methodology 23 4.1 Overview 23 4.2 System Components 24 4.3 GUI (Graphical User Interface) and API (Application Programming Interface) 37 4.4 License Plate Recognition 44 Chapter 5 Experimental Results 52 5.1 Overview 52 5.2 Datasets 53 5.2.1 Scene Dataset 53 5.2.2 License Plate Dataset 54 5.3 Experiment Method 55 5.4 Results 57 Chapter 6 Conclusion and Future Works 62 References 65 | - |
| dc.language.iso | en | - |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | 應用程式介面 | zh_TW |
| dc.subject | 人工智慧 | zh_TW |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 車牌辨識 | zh_TW |
| dc.subject | 車牌辨識 | zh_TW |
| dc.subject | 機車 | zh_TW |
| dc.subject | 應用程式介面 | zh_TW |
| dc.subject | 機車 | zh_TW |
| dc.subject | 人工智慧 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | Computer Vision | en |
| dc.subject | Scooter | en |
| dc.subject | Application Programming Interface | en |
| dc.subject | Artificial Intelligence | en |
| dc.subject | Computer Vision | en |
| dc.subject | Deep Learning | en |
| dc.subject | License Plate Recognition | en |
| dc.subject | Scooter | en |
| dc.subject | Application Programming Interface | en |
| dc.subject | License Plate Recognition | en |
| dc.subject | Deep Learning | en |
| dc.subject | Artificial Intelligence | en |
| dc.title | 孫車牌: 基於深度學習之車牌辨識系統 | zh_TW |
| dc.title | SunLPR: Vehicle License Plate Recognition System with Deep Learning | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 110-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 沈浴池;詹志康 | zh_TW |
| dc.contributor.oralexamcommittee | Yu-Chi Shen;Zhi-Kang Zhan | en |
| dc.subject.keyword | 車牌辨識,深度學習,電腦視覺,人工智慧,應用程式介面,機車, | zh_TW |
| dc.subject.keyword | License Plate Recognition,Deep Learning,Computer Vision,Artificial Intelligence,Application Programming Interface,Scooter, | en |
| dc.relation.page | 67 | - |
| dc.identifier.doi | 10.6342/NTU202201454 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2022-07-20 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | - |
| dc.date.embargo-lift | 2027-07-13 | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-110-2.pdf 未授權公開取用 | 5.2 MB | Adobe PDF | 檢視/開啟 |
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。