本論文主要目的為偵測處理枕木紋行人穿越道，分別針對靜態與動態模式進行影像處理，進而幫助盲人或行動不便者，代替他們雙眼以偵測出枕木紋行人穿越道，並輔助其能安全地穿越其路口。
在國內的相關研究中，目前仍未有人對此枕木紋行人穿越道方面提出偵測方法，因此本篇論文在靜態模式裡便運用雙峰特徵（Bipolarity feature）的演算法，即利用枕木紋行人穿越道一黑一白的交替規律特性，之後於每個區塊內的像素分佈區域，經過計算分析比較後即可消除背景，接著藉由標籤化將最大相似區域標記出來，而標記部份就是本論文所要偵測的枕木紋行人穿越道區域，最後再進行判斷與距離估測。
動態模式則是利用即時影像處理技術結合輪椅機器人平台，於模擬真實場景進行自走通行枕木紋行人穿越道，其影像處理部份需要提供即時的偏移量與偏差角於輪椅機器人作為控制，以便穩定安全到達目的地。而真實場景部份，本論文利用手持數位相機錄製穿越枕木紋行人穿越道，接著利用影像擷取卡與個人電腦進行模擬，其偏移量與偏差角也可即時顯示出來。
關鍵字：枕木紋行人穿越道、影像處理、輪椅機器人

The main purpose of this thesis is to detect pedestrian crossing by static and dynamic image processing. This technique can help the blind and the disabled people to find the pedestrian crossing and walk through it safely.
Until now there is no research about detecting pedestrian crossing in Taiwan. Therefore, this article applies the algorithm of Bipolarity feature in an image-based technique. In this thesis, the Bipolarity is regarded as the main feature in detecting pedestrian crossing. At first, it uses the features of pedestrian crossing, the black road surface is painted with constant-width periodic white stripes. After computation, the analysis and comparison in an image of intensity distribution is obtained. And the background will be eliminated. Secondly, Connected Component Labeling is used to extract the most similar region, and the marked region will be detected by the image. Finally, this thesis will detect whether the crossing exist or not in the marked region and measure the length of crossing.
In dynamic model, the real-time image processing technique combines with wheelchair robot in order to walk through pedestrian crossing automatically, and image processing technique provides real-time offset and angle of displacement for the wheelchair robot to control and reach the destination. In this thesis, the image processing is in PC-base, and it receives the information by using a digital camera to record the real scene of pedestrian crossing.
Keywords:pedestrian crossing , image processing, wheelchair robot

誌謝 i
目錄 ii
圖索引 v
表索引 x
摘要 xi
Abstract xii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 1
1.3 文獻回顧 2
1.4 論文架構 5
第二章 系統架構 6
2.1 影像處理系統 6
2.1.1 數位相機 6
2.1.2 廣角鏡頭攝影機 7
2.1.3 影像擷取卡 8
2.1.4 可攜帶式DVD播放器 9
2.1.5 影像處理介面 10
2.1.6 桌上型電腦 11
2.2 輪椅機器人架構 12
2.2.1 微型電腦 14
第三章 枕木紋行人穿越道之影像處理 16
3.1 靜態影像處理 16
3.1.1 影像擷取 17
3.1.2 灰階化 18
3.1.3 雙峰特徵 18
3.1.4 標籤化 22
3.1.5 取最大區域並恢復此區域 24
3.1.6 框取目標區域與修補 27
3.1.7 判斷是否為目標 29
3.1.8 計算目標距離 30
3.2 動態影像處理 32
3.2.1 前置處理 33
3.2.2 枕木紋行人穿越道 34
3.2.3 盲人專用道及轉彎 40
3.5.4 預設的導引估測 44
3.5.5 即時角度位移修正回授 46
第四章 實驗結果 47
4.1 靜態模式辨別枕木紋行人穿越道 47
4.1.1 不同天候的偵測 47
4.1.2 多種場景的偵測 49
4.1.3 特殊場景 52
4.1.4 數據分析 54
4.2 即時整合輪椅機器人位於枕木紋行人穿越道行進 57
4.2.1 輪椅機器人過彎通行枕木紋行人穿越道 58
4.2.2 輪椅機器人不受到行人影響而直行 61
4.2.3 輪椅機器人於斜坡上行走 62
4.3 動態真實場景模擬 64
4.3.1 白天天候之真實場景模擬 64
4.3.2 行人穿越之真實場景模擬 65
4.3.3 夜間天候之真實場景模擬 66
第五章 結論與未來研究方向 68
5.1 結論 68
5.2 未來研究方向 69
文獻參考 70

[1] 吳成柯、戴善榮、程湘軍、雲立實譯，“數位影像處理”，儒林出版，1996年。
[2] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Addison–Wesley, 1987.
[3] 影像診斷學於21世紀的展望：
http://www.cgmh.org.tw/new1/new8902-203.htm。
[4] B. Thylefors, A. D. Negrel, R. Pararajasegaram, and K. Y. Dadzie, “Global data on blindness,” Bull. WHO, vol. 73, no. 1, pp. 115–121, 1995.
[5] “Blindness and visual disability: Seeing ahead–projections into the next century,” WHO Fact Sheet, no. 146, 1997.
[6] 台灣導盲犬協會： http://www.guidedog.org.tw.htm。
[7] J. A. Leese, C. S. Novak, and Taylor, V. R. “The Determination of Cloud Motion Patterns from Geosynchronous Satellite Image Data,” Patter Recognition, vol. 2, pp. 272–292, 1970.
[8] K. P. Horn, and B. G. Schunck, ”Determining optical flow,” Artificial Intelligance, vol. 17, pp. 185–203, 1981.
[9] C. S. Fuh, and P. Maragos, “Region–based Optical Flow Estimation,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 130–135, 1989.
[10] F. Xu, X. Liu, and K. Fujimura, “Pedestrian Detection and Tracking With Night Vision,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 1, pp. 63–71, 2005.
[11] S. F. Lin, and C. D. Lin, ”Estimation of the Pedestrians on a Crosswalk,” SICE-ICASE International Joint Conference, pp. 4931–4936, 2006.
[12] G. Alessandretti, A. Broggi, and P. Cerri, “Vehicle and Guard Rail Detection Using Radar and Vision Data Fusion,” IEEE Transactions on Intelligent Transportation Systems, vol. 8, no. 1, pp. 95–105, 2007.
[13] S. Y. Kim, S. Y. Oh, J. K. Kang, Y. W. Ryu, K. Kim, S. C. Park, and K. H. Park, “Front and Rear Vehicle Detection and Tracking in the Day and Night Times Using Vision and Sonar Sensor Fusion,” IEEE Intelligent Robots and Systems, pp. 2173–2178, 2005.
[14] L. W. Tsai, J. W. Hsieh, C. H. Chuang, Y. J. Tseng, K. C. Fan, and C. C. Lee, “Road sign detection using eigen colour,” Computer Vision, IET, vol. 2, no. 3, pp. 164–177, 2008.
[15] W. Liu, X. Chen, B. Duan, H. Dong, P. Fu, H. Yuan, and H. Zhao, “A System for Road Sign Detection, Recognition and Tracking Based on Multi–cues Hybrid,” IEEE Intelligent Vehicles Symposium, pp. 562–567, 2009.
[16] Y. He, H. Wang, and B. Zhang, “Color-Based Road Detection in Urban Traffic Scenes,” IEEE Transactions on Intelligent Transportation Systems, vol. 5, no. 4, pp. 309–318, 2004.
[17] R. Labayrade, J. Douret, and D. Aubert, “A Multi-Model Lane Detector that Handles Road Singularities,” IEEE Intelligent Transportation Systems Conference, pp. 1143–1148, 2006.
[18] Y. Wang, L. Bai, and M. Fairhurst, “Robust Road Modeling and Tracking Using Condensation,” IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 4, pp. 570–579, 2008.
[19] T. T. Son, S. Mita, and A. Takeuchi, “Road Detection using Segmentation by Weighted Aggregation based on Visual Information and a Posteriori Probability of Road Regions,” IEEE International Conference on Systems Man and Cybernetics, pp. 3018–3025, 2008.
[20] D. Gao, W. Li, J. Duan, and B. Zheng, ”A Practical Method of Road Detection for Intelligent Vehicle,” IEEE International Conference on Automation and Logistics, pp. 980–985, 2009.
[21] M. S. Uddin, and T. Shioyama, ”Detection of Pedestrian Crossing Using Bipolarity and Projective Invariant” IAPR Conference on Machine Vision Applications, pp. 22–22, 2005.
[22] M. S. Uddin, and T. Shioyama, ”Detection of Pedestrian Crossing and Measurement of Crossing Length – an Image–Based Navigational Aid for Blind People,” IEEE Conference on Intelligent Transportation Systems, pp. 331–336, 2005.
[23] M. S. Uddin, and T. Shioyama, ”Detection of Pedestrian Crossing Using Bipolarity Feature––An Image–Based Technique,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 4, pp. 439–445, 2005.
[24] 余明興、吳明哲、黃世陽，BCB（Borland C++ Builder 6），文魁資訊股份有限公司，2004年。
[25] 康陽股份有限公司：
http://www.karma.com.tw/04_product/detail.asp?pcb=&act=2&sn=25。
[26] 研揚科技：
http://www.aaeon.com/PD_Products_Detail_0754DED8CBA24C4580_BB4E043BFCF44F01B6_8AEE236C4374464B95_BIG5_UTF-8.html。
[27] R. Jain, R. Kasturi, and B. G. Sclection,” Machine Vision,” International Editions, 1995.
[28] 全國法規資料庫：
http://law.moj.gov.tw/LawClass/LawContent.aspx?PCODE=K0040014。
[29] 繆紹綱，”數位影像處理 活用Matlab”，全華科技圖書股份有限公司，2004年。
[30] C. F. Gauss, “Theoria Motus Corporum Coelestium in sectionibus conicis solem ambientium,” On the Revolutions, 1809.