研究生: |
邱俊瑋 Chun-Wei Chiu |
---|---|
論文名稱: |
機車車牌即時追蹤演算法之效能探討 A Comparison Study on Tracking of Motorcycle License Plates |
指導教授: |
徐繼聖
Gee-Sern Hsu |
口試委員: |
賴尚宏
Shang-Hong Lai 王鈺強 Yu-Chiang Wang 郭景明 Jing-Ming Guo 亞魯 ArulMurugan Ambikapathi |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2016 |
畢業學年度: | 104 |
語文別: | 中文 |
論文頁數: | 72 |
中文關鍵詞: | 物件追蹤 、稀疏表示 、車牌辨識 |
外文關鍵詞: | Object Tracking, Sparse Representation, License Plate Recognition |
相關次數: | 點閱:310 下載:10 |
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 |
機車是台灣與大多的亞洲國家常見的交通工具,也是交通及治安相關的案件所用的主要交通工具,但是極少的研究在探討機車車牌追蹤,而追蹤是動態影像車牌辨識非常重要的一環。然而,目前車牌追蹤技術仍以比較傳統的Optical Flow與Kalman Filter為基礎,並未參考近年發展快速的Tracking-by-Detection的方法。Tracking-by-Detection方法大多探討在不同場景下(光線、速度、遮蔽…等)人或一般物體追蹤應用,並未著重特殊物件所需注意之處。本論文首次將車牌追蹤與即時追蹤演算法作連結,將Tracking-by-Detection方法應用在車牌上,本研究詳盡探討state-of-the-art追蹤演算法包含Minimum Output Sum of Squared Error (MOSSE),Discriminative Scale Space Tracker (DSST),Fast Compressive Tracking (FCT),Circulant Structure with Kernels (CSK),Kernelized Correlation Filters (KCF) and Spatio-Temporal Context Tracker(STC). 本研究的貢獻可歸納為以下三點:1) 評估近幾年的追蹤演算法應用在機車車牌上;2) 探討各追蹤演算法最佳參數設定以用來追蹤特定的目標。3) 明確定義追蹤評估法則與資料庫屬性。
This paper presents a comprehensive comparison of state-of-the-art tracking algorithms, including Minimum Output Sum of Squared Error (MOSSE), Discriminative Scale Space Tracker (DSST), Fast Compressive Tracking (FCT), Circulant Structure with Kernels (CSK), Kernelized Correlation Filters (KCF) and Spatio-Temporal Context Tracker(STC). While many consider generic tracking problems in which targets, mostly cars and humans, are moving in various settings, we consider motorcycles in this study, or more precisely the license plates on motorcycles. Motorcycles are one the most popular transportation means in metropolitan areas, especially in Asia, However, very limited research has been done on the tracking of motorcycle license plates, which is a crucial step for license plate recognition. This study has three contributions: 1) Comparison of latest tracking algorithms for handling motorcycle license plates; 2) Determination of appropriate settings of the selected algorithms to highlight what needs to be considered when applying these algorithms to track specific objects; 3) A benchmark database with videos collected under various conditions is offered to the community for performance evaluation and technical advancement.
[1]Zhang, K., Zhang, L., & Yang, M. H. (2014). Fast compressive tracking.Pattern Analysis and Machine Intelligence, IEEE Transactions on, 36(10), 2002-2015.
[2]Zhang, K., Zhang, L., & Yang, M. H. (2012). Real-time compressive tracking. In Computer Vision–ECCV 2012 (pp. 864-877). Springer Berlin Heidelberg.
[3]Jordan, A. (2002). On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. Advances in neural information processing systems, 14, 841.
[4]Bolme, D. S., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010, June). Visual object tracking using adaptive correlation filters. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on (pp. 2544-2550). IEEE.
[5]Danelljan, M., Häger, G., Khan, F., & Felsberg, M. (2014). Accurate scale estimation for robust visual tracking. In British Machine Vision Conference, Nottingham, September 1-5, 2014. BMVA Press.
[6]Dalal, N., & Triggs, B. (2005, June). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Vol. 1, pp. 886-893). IEEE.
[7]Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2012). Exploiting the circulant structure of tracking-by-detection with kernels. In Computer Vision–ECCV 2012 (pp. 702-715). Springer Berlin Heidelberg.
[8]Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015). High-speed tracking with kernelized correlation filters. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 37(3), 583-596.
[9]Wu, Y., Lim, J., & Yang, M. H. (2013). Online object tracking: A benchmark. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 2411-2418).
[10]Scholkopf, B., & Smola, A. J. (2001). Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press.
[11]Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2), 303-338.
[12]Li, H., Shen, C., & Shi, Q. (2011, June). Real-time visual tracking using compressive sensing. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on (pp. 1305-1312). IEEE.
[13]Anagnostopoulos, C. N. E., Anagnostopoulos, I. E., Psoroulas, I. D., Loumos, V., & Kayafas, E. (2008). License plate recognition from still images and video sequences: A survey. Intelligent Transportation Systems, IEEE Transactions on, 9(3), 377-391.
[14]Hsu, G. S., Chen, J. C., & Chung, Y. Z. (2013). Application-oriented license plate recognition. Vehicular Technology, IEEE Transactions on, 62(2), 552-561.
[15]Hsu, G. S., Zeng, S. D., Chiu, C. W., & Chung, S. L. (2015, June). A comparison study on motorcycle license plate detection. In Multimedia & Expo Workshops (ICMEW), 2015 IEEE International Conference on (pp. 1-6). IEEE.
[16]Sarfraz, M. S., Shahzad, A., Elahi, M. A., Fraz, M., Zafar, I., & Edirisinghe, E. A. (2013). Real-time automatic license plate recognition for CCTV forensic applications. Journal of real-time image processing, 8(3), 285-295.
[17]Arth, C., Limberger, F., & Bischof, H. (2007, June). Real-time license plate recognition on an embedded DSP-platform. In Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on (pp. 1-8). IEEE.
[18]Thome, N., Vacavant, A., Robinault, L., & Miguet, S. (2011). A cognitive and video-based approach for multinational license plate recognition. Machine Vision and Applications, 22(2), 389-407.
[19]Zhang, K., Zhang, L., Liu, Q., Zhang, D., & Yang, M. H. (2014). Fast visual tracking via dense spatio-temporal context learning. In Computer Vision–ECCV 2014 (pp. 127-141).
[20]Lucas, B. D., & Kanade, T. (1981, August). An iterative image registration technique with an application to stereo vision. In IJCAI (Vol. 81, pp. 674-679).
[21]Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of basic Engineering, 82(1), 35-45.
[22]Horn, B. K., & Schunck, B. G. (1981, November). Determining optical flow. In 1981 Technical symposium east (pp. 319-331). International Society for Optics and Photonics.
[23]Bouguet, J. Y. (2001). Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corporation, 5(1-10), 4.
[24]Avidan, S. (2004). Support vector tracking. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(8), 1064-1072.
[25]Babenko, B., Yang, M. H., & Belongie, S. (2011). Robust object tracking with online multiple instance learning. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 33(8), 1619-1632.
[26]Zhang, K., Zhang, L., & Yang, M. H. (2013). Real-time object tracking via online discriminative feature selection. Image Processing, IEEE Transactions on,22(12), 4664-4677.
[27]曾喜得,"動態與靜態影像之車牌辨識," 台灣科技大學碩士學位論文, 2015.
[28]鍾育儒,"含自動學習機制之動態影像車牌辨識," 台灣科技大學碩士學位論文, 2014.
[29]Mukhtar, A., Xia, L., & Tang, T. B. (2015). Vehicle detection techniques for collision avoidance systems: A review. Intelligent Transportation Systems, IEEE Transactions on, 16(5), 2318-2338.
[30]Tian, B., Li, Y., Li, B., & Wen, D. (2014). Rear-view vehicle detection and tracking by combining multiple parts for complex urban surveillance. Intelligent Transportation Systems, IEEE Transactions on,15(2), 597-606.
[31]Phatanasrirat, W., & Phiphobmongkol, S. (2009, January). Motorcycle and license plate detection using fixed-size vertical projection and multi-part mean analysis. In Computer Engineering and Technology, 2009. ICCET'09. International Conference on (Vol. 2, pp. 43-47). IEEE.