戶外的光線和複雜的環境變化對於開發智慧型車輛辨識系統影響甚大，大部份的研究都是個別針對白天、晚上和特定路段進行辨識系統的開發或測試，程式中也較難使用固定的參數門檻值於不同的環境，因此本研究將利用視覺技術開發道路背景辨識演算法，讓智慧型車輛辨識系統可以自動識別車窗外的影像是白天影像或晚上影像和車輛所在的環境是屬於哪種路段類型，然後選擇合適的演算法運作、程式參數門檻值設定或啟動相關硬體設備。演算法包括候選白天天空區域偵測、道路消失點水平位置搜尋、貝氏分類器、門檻值分類和倒傳遞類神經分類器。此演算法經過測試可以正確辨識高速公路、城市及山路影像路段。
本論文的另一個研究主題是軌道扣件檢測的辨識演算法開發。軌道檢測系統用於確保列車的行車安全營運，目前檢測鋼軌路面的方式，大部分是利用軌道檢查車，將檢測結果提供給工程人員進行修護工作，而鋼軌上的細部零件，大多還是以人力步行方式現場進行巡軌檢查為主，相當的費時費力及危險，檢測結果也可能受到工作人員的精神狀態而影響。另外，固定鋼軌的細部零件扣件常常因為連續鬆脫斷裂，造成列車出軌意外，對行車安全相當的重要。因此本研究將以視覺辨識為基礎，開發一套自動檢測軌道扣件的影像辨識系統，此系統是建立在現場可規劃邏輯陣列晶片上，透過硬體描述語言完成影像處理辨識，縮短系統整體的影像處理辨識時間。此系統演算法包括鋼軌定位、枕木定位及扣件辨識。最後實際測試可以成功的辨識出正常和不正常的扣件的影像，驗證本研究開發的系統具可行性。

Environment variations make a great impact on the performance of intelligent vehicle recognition systems. Most researches concentrate on the development or testing of a recognition system on specific types of road, light conditions and time of day, and it is often essential to use different parameter thresholds or even algorithms to ensure satisfactory performance when the environment changes. Therefore, this research is aimed at developing a driving image recognition algorithm using visual techniques. The algorithm is suitable for use in several different conditions in daytime and nighttime. It can identify the characteristics of road sections and implement an algorithm which sets parameter threshold values or enables relevant hardware devices as necessary. The proposed algorithm includes a detection module for candidate daytime sky regions, a horizontal position search module to calculate the vanishing point of a road, a Bayes classifier module to recognize images, a threshold value setting module to classify images, and a back-propagation neural network module to recognize images. Experimental results confirm the feasibility of the algorithm for identifying highway images, city images and mountain road images in daytime and nighttime.
Another application of pattern recognition of this thesis is to rail clip inspection image recognition algorithm development. Rail surfaces are detected mostly by track inspection cars and results are provided to engineering staff for maintenance. But, there is still no track maintenance vehicle for inspecting detail rail parts. Instead, engineers have to physically walk on the track and perform the inspection. This kind of inspection work done by human beings takes considerable amount of time and wastes manpower. In addition, rail clip system is used to ensure the driving safety of trains. Therefore, this research presents the development of a vision recognition system which can automatically detect status of rail clips. The vision system is implemented in a field-programmable gate array (FPGA) core. It can shorten the total time of image processing and recognition for the system. The system algorithm consists of rail positioning, sleeper positioning, and recognition of rail clips. Experimental test demonstrates the ability of this system to differentiate rail clip images or rail clip disappearing images. Results confirm the feasibility to develop such a recognition system.

[1]M. Hischke, “Collision Warning Radar Interference,” Proceedings of IEEE Intelligent Vehicles '95 Symposium, Detroit, USA, pp.13-18, September 1995.
[2]T. Emura and M. Kumagai, “A Non-scanning Ultrasonic Sensor for Driver Assistant Systems,” Proceedings of IEEE Intelligent Vehicles Symposium, Versailles, France, pp.98-103, June 2002.
[3]S. M. Yoon, H. G. Park, J. H. Ryu, and M. H. Lee, “Lateral Control of Obstacle Avoidance for An Autonomous Vehicle with Laser Scanner,” Proceedings of IEEE International Symposium on Industrial Electronics, Cambridge, UK, pp.1015-1019, June 2008.
[4]M. Betke, E. Haritaoglu, and L. S. Davis, “Multiple Vehicle Detection and Tracking in Hard Real-time,” Proceedings of IEEE Intelligent Vehicles Symposium, Tokyo, Japan, pp.351-356, September 1996.
[5]K. T. Song and C. C. Yang, “Front Vehicle Tracking Using Scene Analysis,” Proceedings of IEEE International Conference on Mechatronics & Automation, Niagara Falls, Canada, pp.1328-3282, July 2005.
[6]M. Krips, J. Velten, A. Kummert, and A. Teuner, “AdTM Tracking for Blind Spot Collision Avoidance,” Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy, pp.544-548, June 2004.
[7]E. Y. Chung, H. C. Jung, E. Chang, and I. S. Lee, “Vision Based for Lane Change Decision Aid System,” Proceedings of 1st International Forum On Strategic Technology, Ulsan, Korea, pp.10-13, October 2006.
[8]N. Blanc, B. Steux, and T. Hinz, “LaRASideCam: A Fast and Robust Vision-based Blindspot Detection System,” Proceedings of IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, pp.480-485, June 2007.
[9]C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. von Seelen, “Walking Pedestrian Recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol.01, No.3, pp.155-163, September 2000.
[10]M. Bertozzi, A. Broggi, M. Felisa, G. Vezzoni, and M. Del Rose, “Low-level Pedestrian Detection by Means of Visible and Far Infra-red Tetra-vision,” Proceedings of IEEE Intelligent Vehicles Symposium, Tokyo, Japan, pp.231-236, June 2006.
[11]C. Alippi, E. Casagrande, F. Scotti, and V. Piuri, “Composite Real-time Image Processing for Railways Track Profile Measurement,” IEEE Transactions on Instrumentation and Measurement, Vol. 49, No.3, pp.559-564, June 2000.
[12]W. Jin, X. Zhan, and B. Jiang, “Non-contact Rail-wear Inspecting System Based on Image Understanding,” Proceedings 2007 IEEE International Conference on Mechatronics and Automation, Harbin, China, pp.3854-3858, August 2007.
[13]P. W. Loveday, “Modeling and Measurement of Piezoelectric Ultrasonic Transducers for Transmitting Guided Waves in Rails,” Proceedings 2008 IEEE International Ultrasonics Symposium, Beijing, China, pp.410-413, November 2008.
[14]E. Stella, P. Mazzeo, M. Nitti, G. Cicirelli, A. Distante, and T. D'Orazio, “Visual Recognition of Missing Fastening Elements for Railroad Maintenance,” Proceedings IEEE 5th International Conference on Intelligent Transportation Systems, Singapore, pp.94-99, September 2002.
[15]P. L. Mazzeo, N. Ancona, E. Stella, and A. Distante, “Visual Recognition of Hexagonal Headed Bolts by Comparing ICA to Wavelets,” Proceedings 2003 IEEE International Symposium, Houston, Texas, USA, pp.636-641, October 2003.
[16]P. L. Mazzeo, M. Nitti, E. Stella, N. ANCONA, and A. Distante, “An Automatic Inspection System for the Hexagonal Headed Bolts Detection in Railway Maintenance,” Proceedings 7th International IEEE Conference on Intelligent Transportation Systems, Washington, D.C., USA, pp.417-422, October 2004.
[17]P. L. Mazzeo, M. Nitti, E. Stella, and A. Distante, “Visual Recognition of Fastening Bolts for Railroad Maintenance,” Pattern Recognition Letters, Vol. 25, No. 6, pp.669-677, 2004.
[18]M. Singh, S. Singh, J. Jaiswal, and J. Hempshall, “Autonomous Rail Track Inspection using Vision Based System,” Proceedings 2006 IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety, Alexandria, VA, USA, pp.56-59, October 2006.
[19]X. Gibert-Serra, A. Berry, C. Diaz, W. Jordan, B. Nejikovsky, and A. Tajaddini, “A Machine Vision System for Automated Joint Bar Inspection from a Moving Rail Vehicle,” Proceedings of the ASME/IEEE Joint Rail Conference & Internal Combustion Engine Spring Technical Conference, Pueblo, Colorado, pp. 289-296, 2007.
[20]S. Yella, M. Dougherty, and N.K. Gupta, “Condition Monitoring of Wooden Railway Sleepers,” Transportation Research Part C: Emerging Technologies, Vol.17, No.1, pp.38-55, February 2009.
[21]G. De Ruvo, P. De Ruvo, F. Marino, G. Mastronardi, P.L. Mazzeo, and E. Stella, “A FPGA-Based Architecture for Automatic Hexagonal Bolts Detection in Railway Maintenance,” Proceedings on the 7th international Workshop on Computer Architecture for Machine Perception, Palermo, Italy, pp.219-224, July 2005.
[22]F. Marino, A. Distante, G. Mastronardi, P.L. Mazzeo, and E. Stella, “A Real-Time Visual Inspection System for Railway Maintenance: Automatic Hexagonal-Headed Bolts Detection,” IEEE Trans. on Systems, Man, and Cybernetics, Part C: Applications and Reviews, Vol.37, No.3, pp.418-428, May 2007.
[23]H. Y. Hsieh, N. Chen and C. L. Liao, “Visual Recognition System of Elastic Rail Clips for Mass Rapid Transit Systems,” Proceedings of the ASME/IEEE Joint Rail Conference & Internal Combustion Engine Spring Technical Conference, Pueblo, Colorado, pp. 319-326, 2007.
[24]http://teledynedalsa.com/, Teledyne DALSA, Inc.
[25]劉鈺韋，「高速影像擷取與枕木定位應用於軌道監視系統」，國立臺灣科技大學碩士論文，民國九十九年。
[26]P. G. Michalopoulos, “Vehicle Detection through Video Image Processing: The Autoscope System,” IEEE Transactions on Vehicular Technology, Vol. 40, No. 1, pp. 21-29, February 1991.
[27]L. Wixson, K. Hanna, and D. Mishra, “Improved Illumination Assessment for Vision-based Traffic Monitoring,” Proceedings of IEEE Workshop on Visual Surveillance, Bombay, India, pp.34–41, January 1998.
[28]R. Cucchiara, M. Piccardi, and P. Mello, “Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, No. 2, pp. 119-130, June 2000.
[29]E. Y. Chung, H. C. Jung, E. Chang, I. S. Lee, “Vision Based for Lane Change Decision Aid System,” Proceedings of the International Forum on Strategic Technology Conference, Korea, pp.10-13, October 2006.
[30]A. Vailaya and A. Jain, “Detecting Sky and Vegetation in Outdoor Images,” Proceedings of IS&T/SPIE Symposium on Storage and Retrieval for Media Databases, San Jose, California, pp.411-420, January 2000.
[31]B. Zafarifar, de With, and H.N. Peter, “Blue Sky Detection for Content-based Television Picture Quality Enhancement,” Proceedings of IEEE International Conference on Consumer Electronics, Las Vegas, USA, pp.1-2, January 2007.
[32]J. Luo and S. P. Etz, “A Physical Model-based Approach to Detecting Sky in Photographic Images,” IEEE Transactions on Image Processing, Vol.11, No.3, pp.201-212, March 2002.
[33]P.C. Mahalanobis, “On the Generalized Distance in Statistics,” National Institute of Science of India, Vol. 12, pp.49-55, April 1936.
[34]K. Kluge, “Extracting Road Curvature and Orientation from Image Edge Points without Perceptual Grouping into Features,” Proceedings of IEEE Intelligent Vehicles Symposium, Paris, France, pp.109-114, October 1994.
[35]A.K. Dawoud, S. G. Foda, and A. S. Tolba, “A Robust Neural Network Multi-lane Recognition System,” Proceedings of IEEE International Conference on Microelectronics, Monastir, Tunisia, pp.178-182, December 1998.
[36]M. Bertozzi and A. Broggi, “GOLD: A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection,” IEEE Transactions on Image Processing, Vol. 7, No. 1, pp. 62-81, January 1998.
[37]Y. Wang, E.K. Teoh, and D. Shen, “Lane Detection Using B-Snake,” Proceedings of IEEE International Conference on Information Intelligence and Systems, Tokyo, Japan, pp.438-443, October 1999.
[38]R. O. Duda and R. E. Hart, “Use of the Hough Transform to Detect Lines and Curves in Pictures,” Communications of the ACM, Vol.15, No.1, pp.11-15, January 1972.
[39]R. C. Gonzalez, R. E. Woods, Digital Image Processing, 3rd Edition, Prentice Hall, 2007.
[40]T. Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, Vol.27, No.8, pp.861-874, 2006.
[41]P. Cheeseman, J. Kelly, M. Self, J. Stutz, W. Taylor, and D. Freeman, “Bayesian Classification,” Proceedings of International Conference on Machine Learning, Michigan, USA, pp.607-611, June 1988.
[42]S. Hirata, Y. Shirai, and M. Asada, “Scene Interpretation Using 3D Information Extracted from Monocular Color Images,” Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Raleigh, North Carolina, USA, pp.1603-1610, July 1992.
[43]S. Todorovic and M. C. Nechyba, “A Vision System for Intelligent Mission Profiles of Micro Air Vehicles,” IEEE Transactions on Vehicular Technology, Vol. 53, No. 6, pp. 1713-1725, November 2004.
[44]A.C. Berg, F. Grabler, and J. Malik, “Parsing Images of Architectural Scenes,” Proceedings of IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, pp.1-8, October 2007.
[45]F. F. Li and M. Perona, “A Bayesian Hierarchical Model for Learning Natural Scene Categories,” Proceedings of IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, San Diego, California, USA, pp.524-531, June 2005.
[46]P. Quelhas, F. Monay, J.-M. Odobez, D. Gatica-Perez, T. Tuytelaars, and L. Van Gool, “Modeling Scenes with Local Descriptors and Latent Aspects,” Proceedings of the Tenth IEEE International Conference on Computer Vision, Beijing, China, pp.883-890, October 2005.
[47]E. B. Sudderth, A. Torralba, W. T. Freeman, and A. S. Willsky, “Describing Visual Scenes using Transformed Objects and Parts,” International Journal of Computer Vision, Vol. 77, No. 1-3, pp. 291-330, August 2007.
[48]A. Oliva and A. Torralba, “Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope,” International Journal of Computer Vision, Vol. 42, No. 3, pp. 145-175, May-June 2001.
[49]J. Luo and M. Boutell, “Natural Scene Classification Using Overcomplete ICA,” Pattern Recognition, Vol. 38, No. 10, pp. 1507-1519, October 2005.
[50]L. Yi and L.G. Shapiro, “Consistent Line Clusters for Building Recognition in CBIR,” Proceedings of International Conference on Pattern Recognition, Quebec City, QC, Canada, pp.952-956, August 2002.
[51]Q. Yanyun, Z. Nanning, L. Cuihua, and Y. Zejian, “Salient Building Detection in Natural Image Using SVM,” Proceedings of IEEE International Conference on Vehicular Electronics and Safety, Xian, Shanxi, China, pp.126-130, October 2005.
[52]Y. Kim, K. Lee, K. Choi, and S.I. Cho, “Building Recognition for Augmented Reality Based Navigation System,” Proceedings of IEEE International Conference on Computer and Information Technology, Seoul, Korea, pp.131-136, September 2006.
[53]M. K. Hu, “Visual Pattern Recognition by Moment Invariants,” IEEE Transactions on Information Theory, Vol. 8, No. 2, pp. 179-187, February 1962.
[54]A. Carling, Introducing Neural Networks, Sigma Press, 1992, pp. 133-154.
[55]http://www.adlinktech.com/big5/，凌華科技公司。
[56]http://www.trtc.com.tw/，臺北捷運公司。
[57]M. Bertozzi, A. Broggi, and A. Fascioli, “A Stereo Vision System for Real-Time Automotive Obstacle Detection,” Proceedings IEEE International Conference on Image Processing, Lausanne, Switzerland, pp.681-684, September 1996.
[58]N. Atzpadin, P. Kauff, and O. Schreer, “Stereo Analysis by Hybrid Recursive Matching for Real-Time Immersive Video Conferencing,” IEEE Trans. on Circuits and Systems for Video Technology, Vol.14, No.3, pp.321-334, March 2004.
[59]S.J. Krotosky and M.M. Trivedi, “On Color-, Infrared-, and Multimodal-Stereo Approaches to Pedestrian Detection,” IEEE Trans. on Intelligent Transportation Systems, Vol.8, No.7, pp.619-629, December 2007.
[60]R. Jain, R. Kasturi, and B.G. Schunck, Machine Vision, McGraw-Hill, New York, 1995.
[61]S. Theodoridis and K. Koutroumbas, Pattern Recognition, Academic Press, 2006.
[62]http://www.altera.com/, Altera, Inc.