請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71288
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 傅立成(Li-Chen Fu) | |
dc.contributor.author | Xing-Yu Ye | en |
dc.contributor.author | 葉興宇 | zh_TW |
dc.date.accessioned | 2021-06-17T05:03:02Z | - |
dc.date.available | 2021-07-26 | |
dc.date.copyright | 2018-07-26 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-07-24 | |
dc.identifier.citation | [1] S. Ren, K. He, R. Girshick, and J. Sun, 'Faster r-cnn: Towards real-time object detection with region proposal networks,' in Advances in neural information processing systems, 2015, pp. 91-99.
[2] M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, 'The pascal visual object classes (voc) challenge,' International journal of computer vision, vol. 88, no. 2, pp. 303-338, 2010. [3] W. Liu et al., 'Ssd: Single shot multibox detector,' in Preceedings of the European conference on computer vision, 2016, pp. 21-37: Springer. [4] Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. arXiv preprint. [5] T. Wu and A. Ranganathan, 'A practical system for road marking detection and recognition,' in Preceedings of the IEEE Intelligent Vehicles Symposium (IV), 2012, pp. 25-30. [6] H. Chen, F.-Y. Wang, and D. Zeng, 'Intelligence and security informatics for homeland security: information, communication, and transportation,' IEEE Transactions on Intelligent Transportation Systems, vol. 5, no. 4, pp. 329-341, 2004. [7] S. Vacek, C. Schimmel, and R. Dillmann, 'Road-marking Analysis for Autonomous Vehicle Guidance,' in Preceedings of the European Conference on Mobile Robots (EMCR), 2007. [8] J. K. Suhr and H. G. Jung, 'Fast symbolic road marking and stop-line detection for vehicle localization,' Preceedings of the IEEE Intelligent Vehicles Symposium (IV), 2015, pp. 186-191. [9] N. Dalal and B. Triggs, 'Histograms of oriented gradients for human detection,' Preceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, vol. 1, pp. 886-893. [10] K.-A. Toh and H.-L. Eng, 'Between classification-error approximation and weighted least-squares learning,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 4, pp. 658-669, 2008. [11] W. Liu, J. Lv, B. Yu, W. Shang, and H. Yuan, 'Multi-type road marking recognition using adaboost detection and extreme learning machine classification,' in Preceedings of the IEEE Intelligent Vehicles Symposium (IV), 2015, pp. 41-46. [12] Z.-L. Sun, H. Wang, W.-S. Lau, G. Seet, and D. Wang, 'Application of BW-ELM model on traffic sign recognition,' Neurocomputing, vol. 128, pp. 153-159, 2014. [13] G.-B. Huang, D. H. Wang, and Y. Lan, 'Extreme learning machines: a survey,' International journal of machine learning and cybernetics, vol. 2, no. 2, pp. 107-122, 2011. [14] Y. Ouerhani, A. Alfalou, and C. Brosseau, 'Road mark recognition using HOG-SVM and correlation,' in Optics and Photonics for Information Processing XI, 2017, vol. 10395, p. 103950Q: International Society for Optics and Photonics. [15] J. A. Suykens and J. Vandewalle, 'Least squares support vector machine classifiers,' Neural processing letters, vol. 9, no. 3, pp. 293-300, 1999. [16] O. Bailo, S. Lee, F. Rameau, J. S. Yoon, and I. S. Kweon, 'Robust road marking detection and recognition using density-based grouping and machine learning techniques,' in Preceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2017, pp. 760-768. [17] K. Zuiderveld, 'Contrast limited adaptive histogram equalization,' Graphics gems, pp. 474-485, 1994. [18] J. Matas, O. Chum, M. Urban, and T. Pajdla, 'Robust wide-baseline stereo from maximally stable extremal regions,' Image and vision computing, vol. 22, no. 10, pp. 761-767, 2004. [19] T.-H. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, and Y. Ma, 'PCANet: A simple deep learning baseline for image classification?,' in Preceedings of the IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5017-5032, 2015. [20] S. Lee et al., 'VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition,' in Preceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1965-1973. [21] T. Chen, Z. Chen, Q. Shi, and X. Huang, 'Road marking detection and classification using machine learning algorithms,' in Preceedings of the IEEE Intelligent Vehicles Symposium (IV), 2015, pp. 617-621. [22] M.-M. Cheng, Z. Zhang, W.-Y. Lin, and P. Torr, 'BING: Binarized normed gradients for objectness estimation at 300fps,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 3286-3293. [23] V. Nair and G. E. Hinton, 'Rectified linear units improve restricted boltzmann machines,' in Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp. 807-814. [24] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, 'Dropout: A simple way to prevent neural networks from overfitting,' The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014. [25] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Proceedings of the Advances in neural information processing systems, 2012, pp. 1097-1105. [26] O. Russakovsky et al., 'Imagenet large scale visual recognition challenge,' International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, 2015. [27] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' arXiv preprint arXiv:1409.1556, 2014. [28] SZEGEDY, Christian, et al. 'Going deeper with convolutions', in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 1-9. [29] R. Girshick, J. Donahue, T. Darrell, and J. Malik, 'Rich feature hierarchies for accurate object detection and semantic segmentation,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580-587. [30] Girshick, R. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 1440-1448, 2015. [31] J. R. Uijlings, K. E. Van De Sande, T. Gevers, and A. W. Smeulders, 'Selective search for object recognition,' International journal of computer vision, vol. 104, no. 2, pp. 154-171, 2013. [32] M. D. Zeiler and R. Fergus, 'Visualizing and understanding convolutional networks,' in European conference on computer vision, 2014, pp. 818-833: Springer. [33] 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. [34] J. Redmon, 'Darknet: Open source neural networks in c,' Pjreddie. com.[Online]. Available: https://pjreddie. com/darknet/.[Accessed: 21-Jun-2017], 2016. [35] M. Jaderberg, K. Simonyan, and A. Zisserman, 'Spatial transformer networks,' in Proceedings of the Advances in neural information processing systems, 2015, pp. 2017-2025. [36] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510-4520), 2018 [37] T. Ahmad, D. Ilstrup, E. Emami, and G. Bebis, 'Symbolic road marking recognition using convolutional neural networks,' in Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 2017, pp. 1428-1433. [38] Y. LeCun, 'LeNet-5, convolutional neural networks,' URL: http://yann.lecun.com/exdb/lenet, p. 20, 2015. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71288 | - |
dc.description.abstract | 近年來,自動駕駛技術以及先進駕駛輔助系統變的越來越流行,其性能也越來越可靠。對於上述系統來説,最重要的就是對道路環境的偵測和理解。路面標記對於駕駛員以及行車輔助設備起到了非常重要的引導作用。但是路面標記會受到不同天氣、光照及視角的影響導致難以偵測。傳統的路面標記偵測方法通常使用固定的門檻值參數,因此無法應對現實狀況中各種各樣的情況。爲瞭解決這個難題,基於深度學習的即時物件偵測框架例如Single Shot Detector (SSD) 和You Only Look Once (YOLO)比較適合處理這個問題。但這些基於深度學習的方法都需要大量的資料來進行訓練,而目前網路上並沒有合適的路面標記資料庫可以訓練這些偵測系統。此外,這些偵測系統容易將高度扭曲的路面標記辨識成錯誤的類別。如何平衡準確率以及召回率對這些偵測系統來説也是一個難題。
本論文提出了一種包含兩個階段的深度學習系統來解決現有偵測架構中難以辨識高度扭曲的路面標記以及難以平衡召回率以及準確率的問題,本系統可在各種環境下即時準確的偵測地面標記。本論文還建立了一個新的路面標記偵測與分類的基準,收集的資料庫包含11800張高解析度影像。這些影像是在不同的時間和天氣狀況下拍攝於臺北的道路,並且手工標記出13種列別的候選框。實驗證明本論文提出的架構在路面標記偵測的任務中超過其他物件偵測架構。 | zh_TW |
dc.description.abstract | In recent years, Autonomous Driving Systems (ADS) and Advanced Driver Assistance Systems (ADAS) become more and more popular and reliable. It is important for the above systems to understand the road environments. Road markings are important for drivers and driver assistance systems to better understand the road environment. But the detection of road markings will be influenced by various illumination, weather conditions and angles of view. Most traditional road marking detection methods use fixed threshold to detect the road marking, which is not robust enough to handle various situations in the real world. To solve this problem, deep learning-based real-time detection framework such as Single Shot Detector (SSD) and You Only Look Once (YOLO) is suitable for this task. However, these deep learning-based methods are data-driven but there is no suitable public road marking dataset for us to train the network. Besides, these detection frameworks usually struggle with classifying highly distorted road markings. Balancing the precision and recall is also a challenging task for these detection frameworks.
In this thesis, we propose a two-stage deep learning-based system to tackle highly distorted road marking detection and to balance precision and recall of the detection framework. Our system can perform real-time road marking detection under diverse circumstances. We also create a new benchmark for road marking detection and classification tasks. The dataset consists of 11800 high resolution images captured at different times under various weather conditions in Taipei. The images are manually labeled with object bounding boxes and 13 classes. The experimental result shows that the proposed system outperforms other real-time detection framework and Faster R-CNN in road marking detection task. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T05:03:02Z (GMT). No. of bitstreams: 1 ntu-107-R05922146-1.pdf: 4274824 bytes, checksum: 355f8410965ef2095741b495b14f796d (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 口試委員審定書 i
中文摘要 ii ABSTRACT iii CONTENTS v LIST OF FIGURES vii LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Related Work 4 1.3 Contributions 7 1.4 Thesis Organization 8 Chapter 2 Preliminaries 10 2.1 Convolutional Neural Networks 10 2.1.1 Convolutional Layer 11 2.1.2 Pooling Layer 13 2.1.3 Activation Function 15 2.1.4 Fully Connected Layer 16 2.1.5 AlexNet 17 2.1.6 ResNet 18 2.2 Detection Frameworks 19 2.2.1 Faster-RCNN 19 2.2.2 You Only Look Once (YOLO) 21 Chapter 3 Methodology 23 3.1 System Overview 23 3.2 Road Marking Detection Stage 25 3.3 Road Marking Classification Stage 32 3.4 Implementation of Our System 39 Chapter 4 Experiments 41 4.1 Proposed Road Marking Dataset 41 4.2 Environments 46 4.3 Evaluation Metrics 47 4.4 Experimental Result of RM-Net 48 4.5 Experimental Result of the Proposed Detection System 51 4.6 Inference Time 58 Chapter 5 Conclusion 59 REFERENCE 61 | |
dc.language.iso | en | |
dc.title | 基於深度學習之強健性即時道路標記偵測系統 | zh_TW |
dc.title | Deep Learning-based Robust Real-time Road Marking Detection System | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 蕭培墉(Pei-Yung Hsiao) | |
dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),黃世勳(Shih-Shinh Huang),方瓊瑤(Chiung-Yao Fang) | |
dc.subject.keyword | 深度學習,道路標記,即時物件偵測,物件分類, | zh_TW |
dc.subject.keyword | Deep Learning,Road Marking,Real-time Object Detection,Object Classification, | en |
dc.relation.page | 65 | |
dc.identifier.doi | 10.6342/NTU201801616 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-07-24 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-1.pdf 目前未授權公開取用 | 4.17 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。