本論文發展一套輔助駕駛系統，系統可偵測前方車輛是否存在以及估測相對距離，來提供駕駛人作參考，避免發生與前車碰撞的危險，因此路面標線偵測與車輛檢測為系統中主要的重點技術，我們透過取樣設備來獲得路面豐富的資訊，利用最大的亮度值梯度變化偵測可能的路面標線，配合路面標線靜態與動態的特性，建立起路面標線偵測系統，而左右標線所包圍的範圍即為車行區域，而車輛辨識系統則透過對車行區域進行動態調整二值化區域，平均灰度值求閥值，濾出前方車輛底部陰影特徵，進而判斷前方是否存在車輛並進行標示，搭配光學成像原理估測出與前車的相對距離。
本系統在不同的天候、道路種類、車輛種類、車況互動下均能正常的運作，標示出車輛並估測相對距離，車輛偵測的辨識率已達到96%以上，此外不需花費太大的計算量即可完成辨識，於典型1.7 Ghz處理器執行可高達每秒80個畫面，因此可適用於實際道路駕駛，降低交通意外的發生。

The thesis develops a driving assistant system that can locate the positions of the lane boundaries and detects the existence of the front-vehicle. It can also provide warning mechanism so as to avoid the danger as possible collides with previous vehicle.
In lane recognition, we utilized the largest gradient of luminance value to detect possible road surface marking, then cooperated with the marking static and dynamic behavior of road surface characteristic to set up road surface marking and detect system.
On the other hand, we considered vehicle detection leach the vehicle bottom shade characteristic from dynamic area threshold processing, and then judge and label where the vehicle exits. By the principle of the optics image formation, we estimated the relative distance from the previous vehicle.
In this thesis, we proposed an easy and fast measure for previous vehicle of 96% correct rate in different environment. Running on typical 1.7Ghz processor system results up to 80 frames per second.

中文摘要………………………………………………………….I
英文摘要………………………………………………………...II
目錄……………………………………………………………..III
圖目錄………………………………………………………………VI
表目錄………………………………………………………………IX


第一章 緒論………………………………………………………1
1.1 研究背景與動機……………………………1
1.2 研究目的……………………………………2
1.3 系統架構……………………………………3
1.4 論文組織……………………………………6

第二章 路面標線偵測……………………………………………7
2.1 前言…………………………………………7
2.2 路面標線偵測架構…………………………8
2.3 色彩轉換……………………………………9
2.4 路面標線的靜態影像特性…………………10
2.5 路面標線的動態影像特性…………………12
2.6 路面標線方程式……………………………14


第三章 車輛檢測與距離估測……………………………………16
3.1 車輛特性分析………………………………16
3.2 系統架構……………………………………17
3.3 二值化處理…………………………………18
3.3.1 動態調整二值化區域……………19
3.3.2 平均灰度值求閥值………………21
3.4 車輛可能位置偵測…………………………22
3.4.1 水平投影尋找前車底部陰影………22
3.4.2 雜訊濾除……………………………24
3.4.3 標示出車輛左右邊界……………26
3.5 型態學辨識車輛……………………………27
3.5.1 尋找水平邊緣……………………28
3.5.2 尋找車輛可能位置………………29
3.5.3 車輛可能位置編碼………………32
3.5.4 車輛陰影特性……………………34
3.5.5 水平邊緣判斷……………………35
3.5.6 對稱性檢測………………………36
3.6 光學距離估測………………………………37
3.7 總結…………………………………………40

第四章 硬體架構…………………………………………………41
4.1 系統硬體架構………………………………41
4.2 取樣設備簡介………………………………43
4.3 影像格式說明………………………………45
4.4 DSP發展系統介紹…………………………46
4.5 ADSP-BF533系統簡介……………………48
4.6 DSP系統發展環境介紹……………………50
4.7 設定DSP輸入影像…………………………52

第五章 實驗方法與結果…………………………………………53
5.1 錄製資料庫平台介紹………………………53
5.2 PC-Based驗證的環境介紹…………………53
5.3 DSP-Based應用的環境介紹………………55
5.4 路面標線的實驗方法………………………57
5.5 車輛檢測的實驗方法………………………60
5.6 車輛檢測的實驗結果………………………61
5.7 系統效能評估……………………………64

第六章 結論與未來展望………………………………………66

第七章 參考文獻………………………………………………68

[1] M. Bertozzi and A. Broggi, "GOLD: a parallel real-time stereo vision system forgeneric obstacle and lane detection," Proceedings of IEEE Transactions on Image Processing, Vol. 7 Issue: 1, pp. 62-81, January 1998.
[2] M. Bertozzi and A. Broggi, "Real-time lane and obstacle detection on the GOLD
system," Proceedings of the 1996 IEEE Intelligent Vehicles Symposium, pp.
213-218, Tokyo, Japan, September 1996.
[3] K. Yamada, T. Ito, and K. Nishioka, "Road lane recognition system for RCAS",
Proceedings of the 1996 IEEE Intelligent Vehicles Symposium, pp. 177-182
[4] T. Ito and K. Yamada, "Preceding Vehicle and Road Lanes Recognition Methods
for RCAS Using Vision System," Proceedings of the 1994 IEEE Symposium on
Intelligent Vehicles, pp. 85-90
[5] Thorpe, C., "Mixed traffic and automated highways," Proceedings of the 1997
IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol. 2, pp
1011-1017, Genoble, France, September 1997.
[6] C. Knoeppel, A. Schanz, and B. Michaelis, “Robust vehicle detection at large
distance using low resolution cameras,” Proceedings of the 2000 Intelligent
Vehicles Symposium, Vol. 4, pp. 267-272, Dearborn, MI, USA, October 2000.
[7] J. Sparbert, K. Dietmayer, and D. Streller, "Lane detection and street type
classification using laser range images," Proceedings of 4th IEEE International
Conference on Intelligent Transportation Systems, pp. 454-459, Oakland,
California, August 2001.
[8] A. Gern, U. Franke, and P. Levi, "Advanced lane recognition-fusing vision and
radar," Proceedings of the 2000 IEEE Intelligent Vehicles Symposium, pp.45-51,
Dearborn, MI, USA, October 2000.
[9] Real-time vehicle following through a novel symmetry-based approach
Du, Y.; Papanikolopoulos, N.P.; Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on ,Volume: 4 , 20-25 April 1997 Pages:3160 - 3165 vol.4
[10] M. Robert ,and G. Linda, “Computer And Robot Vision”
[11] Visual perception of obstacles and vehicles for platooning Broggi, A.; Bertozzi, M.; Fascioli, A.; Guarino Lo Bianco, C.; Piazzi, A.;Intelligent Transportation Systems, IEEE Transactions on ,Volume: 01 , Issue: 3 , Sept. 2000 Pages:164 - 176
[12] ARGO and the MilleMiglia in Automatico Tour Broggi, A.; Bertozzi, M.; Fascioli, A.; Intelligent Systems, IEEE [see also IEEE Expert] ,Volume: 14 , Issue: 1 , Jan.-Feb. 1999 Pages:55 - 64
[13] GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection Bertozzi, M.; Broggi, A.;Image Processing, IEEE Transactions on ,Volume: 7 , Issue: 1 , Jan. 1998 Pages:62 - 81
[14] Automated lane change controller design Hatipoglu, C.; Ozguner, U.; Redmill, K.A.; Intelligent Transportation Systems, IEEE Transactions on ,Volume: 4 , Issue: 1 , March 2003 Pages:13 – 22
[15] S.G. Jeong, C.S. Kim, K.S. Yoon, J.N. Lee, J.I. Bae, and M.H. Lee, "Real-time lane detection for autonomous navigation," Proceedings of 4th IEEE International Conference on Intelligent Transportation Systems, pp. 508-513, Oakland, California, August 2001.
[16] J. Goldbeck and B. Huertgen, "Lane detection and tracking by video sensors ,"Proceedings of the 1999 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems, pp. 74-79, Tokyo, Japan, October 1999.
[17] D. Pomerleau, "RALPH: rapidly adapting lateral position handler," Proceedings of the Intelligent Vehicles 95 Symposium, pp. 506-511, Detroit, Michigan, September1995.
[18] ADSP-BF533 EZ-KIT Lite Evaluation System Manual. Rev1.0, April 2003
[19] ADSP-BF533 Blackfin Processor Hardware Reference. Preliminary Revision, March 2003
[20] Visual DSP++3.0 C/C++ Compiler and Library Manual for Blackfin DSPs
[21] Visual DSP++ 3.0 Assember and Preprocessor Manual for Blackfin DSPs Rev2.0,April 2002
[22] Blackfin Processor Instruction Set Reference. Rev 2.0, May 2003
[23] VisualDSP++ 3.0 Getting Started Guide for Blackfin Family DSPs. 2002.4
[24] VisualDSP User’s Guide for Blackfin Family DSPs. 2002.4
[25] 林宸生，”數位訊號-影像與語音處理”，全華
[26] 鍾國亮，”影像處理與電腦視覺”，東華
[27] 蕭進松，”數位影像處理”，全華
[28] 顏睿余，”高性能DSP Based 影像擷取辨識系統”，國立中山大學電機工程 研究所，碩士論文，2002
[29] 徐嘉宏，”DSP Based之手寫數字與形狀辨識系統”，國立中山大學電機工程 研究所，碩士論文，2003
[30] 張懿，” 即時路面標線、車輛偵測與距離估計”，淡江大學資訊工程研究所， 碩士論文，2002
[31] 孫正泰，”以電腦視覺為基礎之道路上障礙物偵測”，國立台灣大學資訊工程 研究所，碩士論文，2001
[32] 詹佩珊 編譯，Visual C++ 6 24小時自學手冊，第三波
[33] 鄭家瑜 編著，『C++物件導向程式設計入門與應用 』，博碩
[34] 莊益瑞、吳權威 編著，C++程式設計實務，??峯
[35] 江義華 編著，C & C++完美經典，金禾