在資訊研究的領域當中，辨識車輛並且即使給予駕駛預警能夠改善許多在交通上的安全性問題，也能夠有效的保護行人或是其他的駕駛者的安全。但汽車大部分都是在遠程的交通路途上使用，在較小的交通範圍之間，例如在學校、工廠、社區、小鎮當中，建築物之間的距離都不遠，除了使用車輛之外代步之外，可能會選擇更加輕便的交通工具，例如腳踏車。在這些情況當中，針對腳踏車的辨識方式將顯得重要。分類辨識的領域當中，如果能在受測圖片中有效的辨識出不同種類的交通工具，將有效地增加監控系統的辨識能力。對於工業自動化與車輛管理等都將有所貢獻。在本篇論文當中，將提出一項從側面偵測鑽石型車體自行車的方法，這方法是以鑽石型自行車車體的外型條件作為判斷的基礎，並以幾何條件的判別來辨識腳踏車。一般的鑽石型骨架腳踏車包含了兩個輪子和三角形的腳踏車骨架，這些都可以歸類於某些幾何圖形，例如輪胎屬於橢圓形的形式，腳踏車的骨架大部分屬於三角形的形式，兩形狀的偵測結果可經由文章提及的腳踏車演算法在既定條件之下辨識出腳踏車。經由幾何條件判斷三角形和橢圓形間的關係並進一步偵測鑽石型車架腳踏車的方法，比起由特徵為基礎的方式來說計算的速度可以更快速且直接，因為可以排除訓練的過程，也可在單張圖片上進行計算屏除資料庫的學習步驟。實驗結果將顯出本篇文章所提及的腳踏車模型與辨識演算法的實用性和效能。

In the field of research of computer vision, researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers in real time that improving the safety of transportation systems. Vehicle are always driven for long distance. The commuter chooses the bicycle as transportation for short-distance under certain circumstances, e.g., school, factory. Classify variety of different vehicles that will improving monitor capability which is important issue for traffic safety and vehicle management. That is why bicycle detection algorithm is getting more important. In this paper, a bicycle of diamond frame 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 design of geometric constraints on the relationship between the triangles and ellipses, the computation is fast comparing to the feature-based classifiers. 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]. 謝勝任, “The Analysis of Fatihue and Design Optimization for Bicycle Structure of Diamond Shape”, 大葉大學自動化工程學系碩士論文, 2004
[2]. Auken Richard L Van, “Bicycle frame”, U. S. Patent No. 4047731, 1997
[3]. P. Felzenszwalb, R. Girshick, D. McAllester and D. Ramanan, “Object Detection with Discriminatively Trained Part Based Models”, IEEE Transactions on pattern analysis and machine intelligence., 2010, pp.1627-1645
[4]. S. Rogers, N. Papanikolopoulos, “Counting bicycles using computer vision”, Intelligent Transportation Systems, 2000, pp. 33-38.
[5]. J. Zhang, Z.-Q. Zhu, P. Liu, W.-H. Zhang, “Detection of contours of wheels based on improved codebook”, Machine Learning and Cybernetics (ICMLC), 2013, pp. 510-515
[6]. S. Messelodi, C. M. Modena, G. Cattoni, “Vision-based bicycle/motorcycle classication”, Pattern Recognition Letters, 2007, pp. 1719-1726
[7]. X. Wang, T. X. Han, S. Yan, “An HOG-LBP Human Detector with Partial Occlusion Handling”, IEEE 2009 Computer Vision 12th International Conference, 2009, pp. 32-39
[8]. Somasundaram, G., Morellas, V., Papanikolopoulos, N. Papanikolopoulos and L. Austin, “Counting pedestrians and bicycles in traffic scenes”, IEEE Conference on Intelligent Transportation Systems, 2009, pp. 1-6
[9]. D. Maio and D. Maltoni, “Real-Time Face Location on Gray-Scale Static Images”, Pattern Recognition, vol. 33, no.9, 2000, pp. 1525-1539
[10]. C. Basca, M. Talos, R. Brad, “Randomized Hough transform for ellipse detection with result clustering”, The International Conference on Computer as a Tool, 2005
[11]. S.C. Zhang, Z.Q. Liu, “A robust, real-time ellipse detector”, Pattern Recognition 38 (2), 2005, pp.273–287
[12]. Libuda, L., Grothues, I., Kraiss, K.F, ”Ellipse detection in digital image data using geometric features”, Proc. Int. Conf. VISAPP and GRAPP, 2006, pp. 229-239
[13]. M. Fornaciari, A. Prati, R. Cucchiara, “A fast and effective ellipse detector for embedded vision applications”, Pattern Recognition, 2014, pp.3693-3708
[14]. Liu, H.M., Wang, Z.H., “PLDD: Point-lines Distance Distribution for Detection of Arbitrary Triangles, Regular Polygons and Circles”, J. Vis. Commun. Image R, 2014, pp.273-28
[15]. G. Griffin, A. Holub, and P. Perona, “Caltech-256 object category dataset”, Technical Report 7694, Caltech, 2007
[16]. M. Everingham, S. M. A. Eslami, L. Gool, C. K. I. Williams, J. Winn, A. Zisserman, “The pascal visual object classes challenge: A retrospective”, International Journal of Computer Vision, 2014, pp.98-136
[17]. P.F. Felzenszwalb, R.B. Girshick, D. McAllester and D. Ramanan, “Object Detection with Discriminatively Trained Part Based Models”, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008
[18]. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection”, arXiv preprint arXiv:1506.02640, 2015
[19]. I. Laptev, “Improving object detection with boosted histograms”, Image and Vision Computing, vol. 27, 2009, pp.535-544
[20]. L. Huang, Y. Yang, Y. Deng, and Y. Yu, “Densebox: Unifying landmark localization with end to end object detection”, arXiv preprint arXiv:1509.04874, 2015
[21]. S. Ren, K. He, R. Girshick, X. Zhang, and J. Sun. “Object detection networks on convolutional feature maps”, arXiv preprint arXiv:1504.06066, 2015
[22]. J. Dong, Q. Chen, S. Yan, and A. Yuille. “Towards unified object detection and semantic segmentation”, European Conference on Computer Vision (ECCV), 2014
[23]. K. E. A. van de Sande, C. G. M. Snoek, and A. W. M. Smeulders, “Fisher and vlad with flair”, IEEE Conference on Computer Vision and Pattern Recognition, 2014