在智慧型運輸系統(Intelligent Transportation System, ITS)所涵蓋的內容中，先進車輛控制與安全系統(Advanced Vehicle Control and Safety System, AVCSS)為各國家研究之重點，AVCSS是結合感測器、電腦、通訊及控制技術應用於車輛上，用於協助駕駛人提高行車安全性，其技術層面涵蓋防碰撞警示系統、自動橫向及縱向控制、自動停放車輛等，在防碰撞及縱向、橫向之控制為其重要。
本文的研究著重於車輛橫向控制之輸入，亦即CCD攝影機所擷取的道路環境資訊，用於控制步驟前的辨別。本論文將進行對結構性道路與非結構性道路之分析，結構性道路即為道路線明顯之車道，如同一般平面道路、高速公路等，而非結構性道路則為無道路線或道路線不明顯之道路，如產業道路、校園道路等，由於結構性道路之特徵較為明顯，較容易辨識其路線，而目前國內外對於非結構性道路之分析較少，所以本文特別針對非結構性道路作分析，運用多重系統，並實現於數位訊號處理器(DSP)，最後搭配智慧型控制系統，成功的使車輛在結構與非結構道路中做自動駕駛。

In Intelligent Transportation Systems, Advanced Vehicle Control and Safety System are one of the most important researches around the world. AVCSS is a technique applied on vehicle and is composed by sensor, computer, communication, and control. In order to keep driver safe, the technique covered Collision Avoidance, Longitudinal Automated Control, Lateral Automated Control, Automated Parking, etc, and Collision Avoidance, Longitudinal Automated Control, Lateral Automated Control are most important.
This thesis implemented the Lateral Automated Control by using a CCD camera to extract the road environment. And I presented and analyzed lane detection about structured road and unstructured road. The structured road stands for its obvious lane mark such as general road and freeway; and the unstructured road stands for its unobvious lane mark or without lane mark such as country road and campus road. Because of the characteristic of lane mark, the structured road is easier to detect, and there were less research about unstructured road around the world. So this thesis focused on the unstructured lane detection, and implemented multi-system on DSP (Digital Signal Process). Finally, we applied intelligent control system to vehicle and successfully guided the vehicle in structure and unstructured road.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
第一章 緒論 1
1.1 研究動機與目的 1
1.2 文獻回顧 3
1.3 貢獻 12
1.4 論文架構 13
第二章 系統架構 14
2.1 影像道路偵測系統 14
2.1.1 CCD攝影機 14
2.1.2 影像擷取卡 15
2.1.3 影像擷取器 16
2.1.4 可攜帶式DVD播放器 16
2.2 雷射測距儀系統 17
2.3 整合系統 20
第三章 系統設計 23
3.1 影像道路偵測系統於結構道路 23
3.1.1 前處理 23
3.1.1.1 灰階化 25
3.1.1.2 Sobel邊緣偵測法 26
3.1.1.3 Binary(二值化) 27
3.1.1.4 Otsu 28
3.1.1.5 Lane detection(道路偵測) 29
3.1.2 後處理 31
3.1.2.1基於三特徵之自動道路偵測演算法 31
3.1.2.2 第一特徵之特性 32
3.1.2.3 第二特徵之特性 33
3.1.2.4 第三特徵之特性 35
3.1.2.5 多重TFALDA 36
3.2 影像道路偵測於非結構道路 39
3.2.1 前處理 39
3.2.2 路面邊界偵測 41
3.2.3 後處理 42
3.3 雷達道路偵測系統 44
3.3.1 座標轉換 45
3.3.2 安全島偵測 46
3.3.3 後處理 47
3.4 系統切換判定 48
3.4.1 Shadow detect 50
第四章 系統實現 54
4.1 實驗車輛 55
4.2 數位訊號處理發展板（TMS320DM642） 56
4.2.1 記憶體配置 58
4.2.2 最佳化設計 59
4.3 數位訊號處理發展板（eZdspTMF2812） 62
4.3.1 方向盤控制器 64
4.3.2 模糊控制器之設計 64
4.3.3 模糊化 65
4.3.4 模糊規則庫 67
4.3.5 模糊推論 68
4.3.6 解模糊化 69
4.4 軟體系統 70
第五章 實驗結果 72
5.1 影像道路偵測系統 72
5.1.1 結構道路 72
5.1.1.1 以PC為基礎 72
5.1.1.2 以DSP為基礎 75
5.1.2 非結構道路 82
5.1.2.1 以PC為基礎 82
5.1.2.2 以DSP為基礎 84
5.2 雷達道路偵測系統 89
5.3 系統切換判定 92
5.4 自動駕駛系統 99
第六章 結論與未來展望 101
6.1 結論 101
6.2 未來展望 101
參考文獻 102
附錄 106

[1] 日本『21世紀高度汽車社會』通產資料調查會。
[2] TRI (Taiwan Research Institute)：http://www.tri.org.tw
[3] Taiwan Area National Freeway Bureau, MOTC：
http://www.freeway.gov.tw/Publish.aspx?cnid=516&p=128
[4] R. Wallace, A. Stentz, C. Thorpe, H. Moravec, W. Whittaker and T. Kanade, "First results in robot road-following", International Joint Conference on Artificial Intelligence (IJCAI-85), Vol. 2, CA, pp. 1089-1095, 1985.
[5] J. Crisman, "Color region tracking for vehicle guidance", Active Vision, MIT Press, MA, pp. 107-120.
[6] R. Wallace, "Robot road following by adaptive color classification and shape tracking," ICRA, pp. 258-263, 1987.
[7] D. pomerleau, "Ralph : rapidly adaptive lateral position handler," Proceeding of the IEEE Symposium on Intelligent Vehicle, pp. 506-511, 1995.
[8] Abdulhakam. AM. Assidiq, Othman O. Khalifa, Md. Rafiqul Islam, Sheroz Khan, "Real Time Lane Detection for Autonomous Vehicles", Proceeding of the International Conference on Computer Communication Engineering, pp. 82-88, May 13-15, 2008.
[9] Q.-B. Truong, B.-R. Lee, "New Lane Detection Algorithm for Autonomous Vehicles Using Computer Vision", International Conference on Control, Automation and Systems, pp. 1208-1213, Oct. 14-17, 2008.
[10] Z. W. Kim, Member, IEEE, "Robust Lane Detection and Tracking in Challenging Scenarios", IEEE Transactions on Intelligent Transportation System, Vol. 9, No. 1, pp. 16-26, Mar. 2008.
[11] Q. Lin, Y. Han, H. Hahn, "Real-time Lane Detection Based on Extended Edge-linking Algorithm", International Conference on IEEE Computer Research and Development, pp. 725-730, 2010.
[12] W. Wu, G. ShuFeng, "Research on Unstructured Road Detection Algorithm Based on the Machine Vision", Asia-Pacific Conference on Information Processing IEEE Computer Society, Vol. 2, pp. 1-4, 2009.
[13] P. Jeong, S. Nedevschi, Member, IEEE, "Efficient and Robust Classification Method Using Combined Feature Vector for Lane Detection", IEEE Transaction on Circuits and Systems for Video Technology, Vol. 15, No. 4, pp. 528-537, Apr. 2005.
[14] J. Huang, B. Kong, B. Li, F. Zheng, "A New Method of Unstructured Road Detection Based on HSV Color Space and Road Features", IEEE International Conference on Information Acquisition, pp. 596-601, July 9-11, 2007.
[15] H. Zhang, D. hou, Z. Zhou, "A Novel Lane Detection Algorithm Based on Support Vector Machine", Progress In Electromagnetics Research Symposium, August 22-26, Vol. 1, No. 4, pp. 390-394, 2005.
[16] Y.-R. Huang, Y.-L. Pan, "Fast Algorithm for Structured and Unstructured Road Detection", IEEE International Congress on Image and Signal Processing, pp. 1-5, 2009.
[17] Q. Gao, Q. Luo, S. Moli, "Rough Set based Unstructured Road Detection through Feature Learning", IEEE International Conference on Automation and Logistics, pp. 101-106, August, 2007.
[18] C. Rasmussen, "Grouping Dominant Orientations for Ill-Structured Road Following", IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04), Vol. 1, pp. I-470 - I-477, 2004.
[19] H.-Y. Cheng, C.-C. Yu, C.-C. Tseng, K.-C. Fan, J.-N. Hwang, B.-S. Jeng, "Environment classification and hierarchical lane detection for structured and unstructured roads", The Institution of Engineering and Technology, Vol. 4, Iss. 1, pp. 37-49, 2010.
[20] H.-Y. Cheng, C.-C. Yu, C.-C. Tseng, K.-C. Fan, J.-N. Hwang, B.-S. Jeng, "Hierarchical Lane Detection for Different Types of Roads", International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1349-1352, 2008.
[21] J. Wang, Z. Ji, Y.-T. Su, "UNSTRUCTURED ROAD DETECTION USING HYBRID FEATURES", IEEE International Conference on Machine Learning and Cybernetics, Baoding, pp. 482-486, July 12-15, 2009.
[22] Z. Li, B. Dai, H. He, "A Novel Fast Segmentation Method of Unstructured Roads", IEEE International Conference on Vehicular Electronics and Safety (ICVES), pp. 53-56, 2006.
[23] 施克光電：http://www.sick.com
[24] 范逸之，江文賢，陳立元，“C++ Builder與RS-232串列通訊控制”，文魁資訊股份有限公司，2001。
[25] 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。
[26] 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。
[27] Y. U. Yim, S.-Y. Oh, Senior Member, IEEE, "Three-Feature Based Automatic Lane Detection Algorithm (TFALDA) for Autonomous Driving", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, Vol. 4, No. 4, Dec. 2003.
[28] C. Yu, D. Zhang, "Road Curbs Detection Based on Laser Radar", International Conference on IEEE Signal Processing, Vol. 4, 2006.
[29] 溫逸軒，“智慧型車輛行駛控制器之設計與實現”，國立中山大學機械與機電工程學系，碩士論文，2010。
[30] DMEK642/DMDK642/DMCK User's Manual.
[31] 盧怡仁，蔡偉和，“單晶片於數位訊號處理的應用”，文魁資訊股份有限公司，2007。
[32] Shehrzad Qureshi, Embedded Image Processing on the TMS320C6000TMDSP.
[33] TMS320C64X DSP Turbo-Decoder Coprocessor Reference Guide (SPRU 534).
[34] Using TMS320C6416 Coprocessors: Turbo Coprocessor (SPRA 749).
[35] Texas Instruments：http://www.ti.com