簡易檢索 / 詳目顯示

回結果列表
研究生： 羅嘉鈞
Luo, Chia-Chun
論文名稱： 道路交通號誌之形狀偵測與神經網絡辨識
Shape-based Detection and Neural Network-based Recognition of Road Traffic Signs
指導教授： 楊家輝
Yang, Jar-Ferr
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2018
畢業學年度： 106
語文別： 英文
論文頁數： 55
中文關鍵詞： 先進輔助駕駛系統 、交通號誌偵測 、交通號誌辨識 、卷積式神經網路
外文關鍵詞： Advanced Driver Assistance System (ADAS), Traffic Sign Detection, Traffic Sign Recognition, Convolutional Neural Network (CNN)
相關次數： 點閱：49  下載：1 
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

    • 先進駕駛輔助系統的核心目標是利用智慧技術以提高駕駛的安全性，由於主動式安全配備的需求提升，先進駕駛輔助系統近年來有長足的發展。台灣的道路駕駛來說，先進駕駛輔助系統應該能分辨道路的圓形禁止標誌與三角警示標誌以協助提供駕駛員完整的交通訊息。在本論文中，我們提出了一套智慧交通標誌識別警告系統。我們首先提出三角與圓形號誌檢測方法以快速偵測交通標誌區塊。初期，我們先利用傳統的方向梯度直方圖(Histogram of Oriented Gradient)及支持向量機(Support Vector Machine)來分類。最後，我們採用捲積式神經網絡(Convolutional Neural Network)，以提高的辨識準確率，我們建議的神經網絡架構乃結合LeNet-5框架配合Google初端(Inception)模組以提高效能。在德國交通標誌識別基準（GTSRB）測試數據集中，我們的神經網絡比單純的 LeNet提升幾乎5％的準確率。為提高實用性，我們亦建立了一個台灣交通標誌數據庫來訓練我們的捲積式神經網絡。包含收集所錄製影片，實驗測試結果顯示，我們提出的智慧交通標誌識別系統能有效用於ADAS的情境中，系統成功達到的97%以上的正確偵測效能。

    Improving driver’s safety is the main goal of the advanced driver assistance system (ADAS). The ADAS has been widely developed in recent years because of the increased demand for proactive security. For road driving in Taiwan, the ADAS should recognize the circular prohibition and triangular warning traffic signs to help drivers with complete traffic conditions. In this thesis, we proposed a driver assistance system for traffic sign recognition. First, we proposed shaped-based detection algorithms to detect circle and triangular traffic signs. For classification, we originally used traditional features in histograms of oriented gradients (HOG) followed by classification with support vector machine (SVM). In order to pursue high recognition accuracy, we then apply state-of-the-art convolutional neural network (CNN), in which we combine LeNet-5 structure and Google’s inception modules to achieve about 5% improvement of top 1 accuracy compared with LeNet model in German Traffic Sign Recognition Benchmarks (GTSRB) testing dataset. For practical applications, we also establish a Taiwanese traffic sign database to train the proposed neural network. The simulation results on self-collect driving videos demonstrate that the proposed traffic sign recognition system achieved above 97% recognition rate can be effectively adopted in ADAS applications.

    摘 要 I ABSTRACT II 誌 謝 III CONTENTS IV LIST OF TABLES VI LIST OF FIGURES VII CHAPTER 1: INTRODUCTION 1 1.1 Research Background 1 1.2 Motivations 2 1.3 Literature Reviews 3 1.4 Organization of Thesis 5 CHAPTER 2: RELATED WORK 7 2.1 Histograms of Oriented Gradients for Feature Extraction 7 2.2 Support Vector Machine 9 2.3 Convolutional Neural Network 11 2.3.1 CNN Basics 11 2.3.2 Inception of GoogLeNet 14 CHAPTER 3: THE PROPOSED TSR SYSTEM 16 3.1 Overview of the Proposed TSR System 16 3.2 Traffic Sign Detection 17 3.2.1 Pre-processing 19 3.2.2 Circular Detection 20 3.2.3 Triangular Detection 22 3.2.4 Relative Color Transform 24 3.3 Traffic Sign Recognition 25 CHAPTER 4: EXPERIMENTAL RESULTS 31 4.1 Experimental Environments 31 4.2 Detection of Traffic Sign 32 4.3 Classification of CNN 36 4.3.1 Test on GTSRB 36 4.3.2 Test on Taiwanese Traffic Sign Database 39 4.3.3 Transfer Learning from GTSRB 43 4.4 Fusion Version 46 CHAPTER 5: CONCLUSIONS 49 CHAPTER 6: FUTURE WORKS 50 REFERENCES 51

    [1]J. N. Chourasia and P. Bajaj, "Centroid based detection algorithm for hybrid traffic sign recognition system," in Emerging Trends in Engineering and Technology (ICETET), 2010 3rd International Conference on, 2010, pp. 96-100: IEEE.
    [2]C. Kiran, L. V. Prabhu, and K. Rajeev, "Traffic sign detection and pattern recognition using support vector machine," in Advances in Pattern Recognition, 2009. ICAPR'09. Seventh International Conference on, 2009, pp. 87-90: IEEE.
    [3]H. Fleyeh, "Color detection and segmentation for road and traffic signs," in Cybernetics and Intelligent Systems, 2004 IEEE Conference on, 2004, vol. 2, pp. 809-814: IEEE.
    [4]C. Bahlmann, Y. Zhu, V. Ramesh, M. Pellkofer, and T. Koehler, "A system for traffic sign detection, tracking, and recognition using color, shape, and motion information," in Intelligent Vehicles Symposium, 2005. Proceedings. IEEE, 2005, pp. 255-260: IEEE.
    [5]S. Maldonado-Bascón, S. Lafuente-Arroyo, P. Gil-Jimenez, H. Gómez-Moreno, and F. López-Ferreras, "Road-sign detection and recognition based on support vector machines," IEEE transactions on intelligent transportation systems, vol. 8, no. 2, pp. 264-278, 2007.
    [6]R. Malik, J. Khurshid, and S. N. Ahmad, "Road sign detection and recognition using colour segmentation, shape analysis and template matching," in Machine Learning and Cybernetics, 2007 International Conference on, 2007, vol. 6, pp. 3556-3560: IEEE.
    [7]H. Huang, C. Chen, Y. Jia, and S. Tang, “Automatic detection and recognition of road sign,” in Proc. ICMESA, 2008, pp. 626–630.
    [8]P. Wanitchai and S. Phiphobmongkol, "Traffic warning signs detection and recognition based on fuzzy logic and chain code analysis," in Intelligent Information Technology Application, 2008. IITA'08. Second International Symposium on, 2008, vol. 3, pp. 508-512: IEEE.
    [9]W. Shadeed, D. I. Abu-Al-Nadi, and M. J. Mismar, "Road traffic sign detection in color images," in Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003 10th IEEE International Conference on, 2003, vol. 2, pp. 890-893: IEEE.
    [10]G. Loy and N. Barnes, "Fast shape-based road sign detection for a driver assistance system," in Intelligent Robots and Systems, 2004.(IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on, 2004, vol. 1, pp. 70-75: IEEE.
    [11]N. Barnes, A. Zelinsky, and L. S. Fletcher, "Real-time speed sign detection using the radial symmetry detector," IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 2, pp. 322-332, 2008.
    [12]S. Kim, S. Kim, Y. Uh, and H. Byun, "Color and shape feature-based detection of speed sign in real-time," in Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on, 2012, pp. 663-666: IEEE.
    [13]A. Adam and C. Ioannidis, "Automatic road sign detecion and classification based on support vector machines and HOG descriptos," ISPRS annals of the photogrammetry, remote sensing and spatial information sciences, vol. 2, no. 5, p. 1, 2014.
    [14]G. Overett and L. Petersson, "Large scale sign detection using HOG feature variants," in Intelligent Vehicles Symposium (IV), 2011 IEEE, 2011, pp. 326-331: IEEE.
    [15]Z. Xiao, Z. Yang, L. Geng, and F. Zhang, "Traffic sign detection based on histograms of oriented gradients and boolean convolutional neural networks," in Machine Vision and Information Technology (CMVIT), International Conference on, 2017, pp. 111-115: IEEE.
    [16]J. Greenhalgh and M. Mirmehdi, "Real-time detection and recognition of road traffic signs," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 4, pp. 1498-1506, 2012.
    [17]F. Zaklouta and B. Stanciulescu, "Real-time traffic-sign recognition using tree classifiers," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 4, pp. 1507-1514, 2012.
    [18]A. Z. Kouzani, "Road-sign identification using ensemble learning," in Intelligent Vehicles Symposium, 2007 IEEE, 2007, pp. 438-443: IEEE.
    [19]Y. Yang, H. Luo, H. Xu, and F. Wu, "Towards real-time traffic sign detection and classification," IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 7, pp. 2022-2031, 2016.
    [20]W. Hu, Q. Zhuo, C. Zhang, and J. Li, "Fast Branch Convolutional Neural Network for Traffic Sign Recognition," IEEE Intelligent Transportation Systems Magazine, vol. 9, no. 3, pp. 114-126, 2017.
    [21]R. Qian, Y. Yue, F. Coenen, and B. Zhang, "Traffic sign recognition with convolutional neural network based on max pooling positions," in Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2016 12th International Conference on, 2016, pp. 578-582: IEEE.
    [22]J. Jin, K. Fu, and C. Zhang, "Traffic sign recognition with hinge loss trained convolutional neural networks," IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 5, pp. 1991-2000, 2014.
    [23]J. Greenhalgh and M. Mirmehdi, "Traffic sign recognition using MSER and random forests," in Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European, 2012, pp. 1935-1939: IEEE.
    [24]Y. Xu, Q. Wang, Z. Wei, and S. Ma, "Traffic sign recognition based on weighted ELM and AdaBoost," Electronics Letters, vol. 52, no. 24, pp. 1988-1990, 2016.
    [25]Z. Abedin, P. Dhar, M. K. Hossenand, and K. Deb, "Traffic sign detection and recognition using fuzzy segmentation approach and artificial neural network classifier respectively," in Electrical, Computer and Communication Engineering (ECCE), International Conference on, 2017, pp. 518-523: IEEE.
    [26]J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, "The German traffic sign recognition benchmark: a multi-class classification competition," in Neural Networks (IJCNN), The 2011 International Joint Conference on, 2011, pp. 1453-1460: IEEE.
    [27]Z. Zhu, D. Liang, S. Zhang, X. Huang, B. Li, and S. Hu, "Traffic-sign detection and classification in the wild," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2110-2118.
    [28]N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, vol. 1, pp. 886-893: IEEE.
    [29]Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
    [30]C. Szegedy et al., "Going deeper with convolutions," 2015: Cvpr.
    [31]J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, "Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition," Neural networks, vol. 32, pp. 323-332, 2012.
    [32]P. Sermanet and Y. LeCun, "Traffic sign recognition with multi-scale convolutional networks," in Neural Networks (IJCNN), The 2011 International Joint Conference on, 2011, pp. 2809-2813: IEEE.
    [33]F. Zaklouta, B. Stanciulescu, and O. Hamdoun, "Traffic sign classification using kd trees and random forests," in Neural Networks (IJCNN), The 2011 International Joint Conference on, 2011, pp. 2151-2155: IEEE.
    [34]D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
    [35]J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.s

    下載圖示 校內：2023-07-19公開
    校外：2023-07-19公開
    QR CODE