交通運輸系統安全性的增進得到相當多關注。為了達成這個目標，研究者們發展了於交通道路偵測與分析車輛或行人的方法，但是腳踏車也是道路安全的一個顯著因子，相關研究卻相對較不完備。腳踏車影像是由兩個橢圓形式輪子與兩個三角形形式車架所組成，本論文基於上述觀察，提出一個側面腳踏車影像偵測演算法。經由提出的側面腳踏車影像偵測演算法、腳踏車數學模型、三角形與橢圓形之間的幾何關係條件，根據示範實作與資料量的評估結果得知，計算是快速的。此外，我們提出的演算法不須訓練過程，而且只須單張影像作為輸入資料。實驗結果亦顯示本文提出的腳踏車模型與偵測演算法的可行性與性能。

Improving the safety of transportation systems attract lots of attention. Researchers introduced their methods to detect and analyze the vehicle and the pedestrian on the road to accomplish this goal. However, the bicycle is also a significant factor of the safety on a road but has not been well-studied relatively. In this dissertation, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form of two triangles. Through the proposed triangle detection algorithm, the bicycle model and the geometric constraints on the relationship between the triangles and ellipses, the computation is fast according to the sample implementation and the evaluation of the reduced data amount. Besides, the training process is unnecessary and only single image is required for our algorithm. The experimental results are also given in this paper to show the practicability and the performance of the proposed bicycle model and bicycle detection algorithm.

[1] Joon-Ki Kim, Sungyop Kim, Gudmundur F. Ulfarsson, and Luis A. Porrello. Bicyclist injury severities in bicycle - motor vehicle accidents. Accident Analysis & Prevention, 39(2):238 – 251, 2007.
[2] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005., volume 1, pages 886–893 vol. 1, June 2005.
[3] Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9):1627–1645, Sept 2010.
[4] Ross Brook Girshick. From Rigid Templates to Grammars: Object Detection with Structured Models. University of Chicago, Division of the Physical Sciences, Department of Computer Science, 2012.
[5] Scott Rogers and Nikolaos P. Papanikolopoulos. Counting bicycles using computer vision. In Intelligent Transportation Systems, 2000. Proceedings. 2000 IEEE, pages 33–38, 2000.
[6] Jun Zhang, Zhi-Qiang Zhu, Ping Liu, and Wei-Han Zhang. Detection of contours of wheels based on improved codebook. In 2013 International Conference on Machine Learning and Cybernetics (ICMLC), volume 02, pages 510–515, July 2013.
[7] Yong Kui Liu and Borut Žalik. An efficient chain code with huffman coding. Pattern Recognition, 38(4):553 – 557, 2005.
[8] Zhijun Qui, Danya Yao, Yi Zhang, Daosong Ma, and Xinyu Liu. The study of the detection of pedestrian and bicycle using image processing. In Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems, volume 1, pages 340–345 vol.1, Oct 2003.
[9] Yuuki Fujimoto and Jun ichiro Hayashi. A method for bicycle detection using ellipse approximation. In Proceedings of the 19th Korea-Japan Joint Workshop on Frontiers of Computer Vision, (FCV), 2013, pages 254–257, Jan 2013.
[10] Kazuyuki Takahashi, Yasutaka Kuriya, and Takashi Morie. Bicycle detection using pedaling movement by spatiotemporal gabor filtering. In TENCON 2010 - 2010 IEEE Region 10 Conference, pages 918–922, Nov 2010.
[11] Yeunghak Lee, Taesun Kim, Sanghoon Lee, and Jaechang Shim. Spatial regions periodicity based detection of two-wheelers using histogram of oriented gradients. International Journal of Multimedia and Ubiquitous Engineering, 10(4):325–336, 2015.
[12] Heewook Jung, Yusuke Ehara, Joo Kooi Tan, Hyeongseop Kim, and Seiji Ishikawa. Detection of a bicycle in video images using msc-hog feature. International Journal of Innovative Computing, Information and Control, 10(2):521–533, 2014.
[13] Robert E. Schapire and Yoram Singer. Improved boosting algorithms using confidencerated predictions. Machine Learning, 37(3):297–336, 1999.
[14] Mehmet Kemal Kocamaz, Jian Gong, and Bernardo R. Pires. Vision-based counting of pedestrians and cyclists. In Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1–8, March 2016.
[15] Berthold K.P. Horn and Brian G. Schunck. Determining optical flow. Artificial Intelligence, 17(1):185 – 203, 1981.
[16] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool. Speeded-up robust features (surf). Computer Vision and Image Understanding, 110(3):346 – 359, 2008. Similarity Matching in Computer Vision and Multimedia.
[17] Guruprasad Somasundaram, Vassilios Morellas, and Nikolaos Papanikolopoulos. Counting pedestrians and bicycles in traffic scenes. In 2009 12th International IEEE Conference on Intelligent Transportation Systems, pages 1–6, Oct 2009.
[18] Anna Bosch, Andrew Zisserman, and Xavier Munoz. Representing shape with a spatial pyramid kernel. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR ’07, pages 401–408, New York, NY, USA, 2007.
[19] David G. Lowe. Object recognition from local scale-invariant features. In Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999., volume 2, pages 1150–1157 vol.2, 1999.
[20] Hongyu Hu, Pengfei Tao, Zhenhai Gao, Qingnian Wang, Zhihui Li, and Zhaowei Qu. Vision-based bicycle detection using multiscale block local binary pattern. Mathematical Problems in Engineering, 2014, 2014.
[21] Kai Yang, Chao Liu, Jiang Yu Zheng, Lauren Christopher, and Yaobin Chen. Bicyclist detection in large scale naturalistic driving video. In 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 1638–1643, Oct 2014.
[22] Farideh Foroozandeh Shahraki, Ali Pour Yazdanpanah, Emma E. Regentova, and Venkatesan Muthukumar. Advances in Visual Computing: 11th International Symposium, ISVC 2015, Las Vegas, NV, USA, December 14-16, 2015, Proceedings, Part II, chapter Bicycle Detection Using HOG, HSC and MLBP, pages 554–562. Springer International Publishing, Cham, 2015.
[23] Wei Tian and Martin Lauer. Fast cyclist detection by cascaded detector and geometric constraint. In Proceedings of the 2015 IEEE 18th International Conference on Intelligent Transportation Systems, pages 1286–1291, Sept 2015.
[24] Wei Tian and Martin Lauer. Fast and robust cyclist detection for monocular camera systems. 2014.
[25] Tomoki Watanabe, Satoshi Ito, and Kentaro Yokoi. Co-occurrence histograms of oriented gradients for pedestrian detection. In The 3rd Pacific-Rim Symposium on Image and Video Technology, page 37–47, January 2009.
[26] Gu Yanlei and Shunsuke Kamijo. Bicyclist recognition and orientation estimation from on-board vision system. International Journal of Automotive Engineering, 6(2):67–73, 2015.
[27] Ivan Laptev. Improving object detection with boosted histograms. Image Vision Comput., 27(5):535–544, April 2009.
[28] Xiaolong Wang, Liang Lin, Lichao Huang, and Shuicheng Yan. Incorporating structural alternatives and sharing into hierarchy for multiclass object recognition and detection. n Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2013.
[29] Hyunggi Cho, Paul E. Rybski, and Wende Zhang. Vision-based bicycle detection and tracking using a deformable part model and an ekf algorithm. In Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2010, pages 1875–1880, Sept 2010.
[30] Hyunggi Cho, Paul E. Rybski, and Wende Zhang. Vision-based bicyclist detection and tracking for intelligent vehicles. In Intelligent Vehicles Symposium (IV), 2010 IEEE, pages 454–461, June 2010.
[31] Han-Hsuan Chen, Chun-Cheng Lin, Wei-Yu Wu, Yi-Ming Chan, Li-Chen Fu, and Pei-Yung Hsiao. Integrating appearance and edge features for on-road bicycle and motorcycle detection in the nighttime. In Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 354–359, Oct 2014.
[32] Bin-Feng Lin, Yi-Ming Chan, Li-Chen Fu, Pei-Yung Hsiao, Li-An Chuang, Shin-Shinh Huang, and Min-Fang Lo. Integrating appearance and edge features for sedan vehicle detection in the blind-spot area. IEEE Transactions on Intelligent Transportation Systems, 13(2):737–747, June 2012.
[33] Jinfeng Yan, Qiang Ling, Yicheng ZHANG, Feng Li, and Feng Zhao. An adaptive bicycle detection algorithm based on multi-gaussian models. Journal of Computational Information Systems, 9:10075–10083, 2013.
[34] Stefano Messelodi, Carla Maria Modena, and Gianni Cattoni. Vision-based bicycle/motorcycle classification. Pattern Recognition Letters, 28(13):1719 – 1726, 2007.
[35] Håkan Ardö, Mikael Nilsson, Aliaksei Laureshyn, and Anna Persson. Reduced search space for rapid bicycle detection. In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM 2013), 2013.
[36] Alessandro Moro, Enzo Mumolo, Massimiliano Nolich, and Kazunori Umeda. Realtime gpu implementation of an improved cars, pedestrians and bicycles detection and classification system. In Proceedings of the 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 1343–1348, Oct 2011.
[37] J.H. Dukesherer and C.E. Smith. A hybrid hough-hausdorff method for recognizing bicycles in natural scenes. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2001, volume 4, pages 2493–2498 vol.4, 2001.
[38] Mun K. Leung and Thomas S. Huang. Detecting wheels of vehicle in stereo images. In 10th International Conference on Pattern Recognition, 1990., volume i, pages 263–267 vol.1, Jun 1990.
[39] Tohid Ardeshiri, Fredrik Larsson, Fredrik Gustafsson, Thomas B. Schön, and Michael Felsberg. Bicycle tracking using ellipse extraction. In 14th International Conference on Information Fusion (FUSION), 2011, pages 1–8, July 2011.
[40] Baochen Sun and Kate Saenko. From virtual to reality: Fast adaptation of virtual object detectors to real domains. In BMVC, volume 1, page 3, 2014.
[41] Paul L Rosin and Tim Ellis. Frame-based system for image interpretation. Image and Vision Computing, 9(6):353 – 361, 1991.
[42] Gareth Loy and Nick Bames. Fast shape-based road sign detection for a driver assistance system. In Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004. (IROS 2004), volume 1, pages 70–75 vol.1, Sept 2004.
[43] Jesmin F. Khan, Sharif M. A. Bhuiyan, and Reza R. Adhami. Image segmentation and shape analysis for road-sign detection. IEEE Transactions on Intelligent Transportation Systems, 12(1):83–96, March 2011.
[44] Gareth Loy and Alexander Zelinsky. Fast radial symmetry for detecting points of interest. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(8):959–973, Aug 2003.
[45] Ofer Achler and Mohan M. Trivedi. Vehicle wheel detector using 2d filter banks. In Intelligent Vehicles Symposium, 2004 IEEE, pages 25–30, June 2004.
[46] Vítězslav Beran, Adam Herout, and Ivo Řezníček. Video-based bicycle detection in underground scenarios. In Proceedings of the 17th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, pages 103–107, February 2009.
[47] Cosmin A. Basca, Mihai Talos, and Remus Brad. Randomized hough transform for ellipse detection with result clustering. In Proceedings of the International Conference on Computer as a Tool, 2005. EUROCON 2005., volume 2, pages 1397–1400, Nov 2005.
[48] Robert A. McLaughlin. Randomized hough transform: Improved ellipse detection with comparison1. Pattern Recognition Letters, 19(3 - 4):299 – 305, 1998.
[49] Si-Cheng Zhang and Zhi-Qiang Liu. A robust, real-time ellipse detector. Pattern Recognition, 38(2):273 – 287, 2005.
[50] Lars Libuda, Ingo Grothues, and Karl-Friedrich Kraiss. Ellipse detection in digital image data using geometric features. In Proceedings of the International Conferences VISAPP and GRAPP 2006,, pages 229–239, Berlin, Heidelberg, 2007. Springer Berlin Heidelberg.
[51] Dilip K. Prasad, Maylor K.H. Leung, and Siu-Yeung Cho. Edge curvature and convexity based ellipse detection method. Pattern Recognition, 45(9):3204 – 3221, 2012. Best Papers of Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA’2011).
[52] Jiang-Ping He and Yan Ma. Triangle detection based on windowed hough transform. In Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition, 2009. ICWAPR 2009., pages 95–100, July 2009.
[53] Hong-Min Liu and Zhi-Heng Wang. Detection of arbitrary triangle. In 4th International Congress on Image and Signal Processing (CISP), 2011, volume 2, pages 893–897, Oct 2011.
[54] Halil Demirezen and Mehmet Baran. Triangle detection with color information. In Proceedings of the 2010 International Conference on Applied Electronics (AE), pages 1–4, Sept 2010.
[55] Jie Zhu, Jian Yu, Chaomurilige Wang, and Fan-Zhang Li. Colour combination attention for object recognition. IET Image Processing, 8(9):539–547, September 2014.
[56] Jun Rui Lv and Xue Gang Luo. An approach for triangle traffic sign detection based on improved radon transform. In 2012 Fourth International Conference on Computational and Information Sciences (ICCIS), pages 176–178, Aug 2012.
[57] Michele Fornaciari, Andrea Prati, and Rita Cucchiara. A fast and effective ellipse detector for embedded vision applications. Pattern Recognition, 47(11):3693 – 3708, 2014.
[58] Paul L. Rosin. Measuring shape: Ellipticity, rectangularity, and triangularity. Mach. Vision Appl., 14(3):172–184, July 2003.
[59] Gary Bradski and Adrian Kaehler. Learning OpenCV: Computer vision with the OpenCV library. O’Reilly Media, Inc., 2008.
[60] Gregory Griffin, Alex Holub, and Pietro Perona. Caltech-256 object category dataset. http://www.vision.caltech.edu/Image_Datasets/Caltech256/. Accessed: 2016-02-21.
[61] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009., pages 248–255, June 2009.
[62] George A. Miller. Wordnet: A lexical database for english. Commun. ACM, 38(11):39–41, November 1995.
[63] Mark Everingham, S. M. Ali Eslami, Luc Van Gool, Christopher K. I. Williams, John Winn, and Andrew Zisserman. The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1):98–136, 2014.
[64] S. Bileschi. Cbcl streetscenes challenge framework (2007).
[65] Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. The cityscapes dataset for semantic urban scene understanding. CoRR, abs/1604.01685, 2016.
[66] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
[67] Shiming Xiang, Gaofeng Meng, Ying Wang, Chunhong Pan, and Changshui Zhang. Image deblurring with matrix regression and gradient evolution. Pattern Recognition, 45(6):2164 – 2179, 2012.