臺灣博碩士論文加值系統

在理想的情況下，單一張訊框能識別出道路線種類，但是在瞬息萬變的行車環境下，這是一個很大的挑戰，因此本論文以時間序列概念為基礎，累積行車影像的連續訊框資料進行道路線種類辨識，不但能避免突發雜訊所造成的誤判問題，也可以更精確的辨識出道路線種類，且若判斷出標記線為非道路線，便能輔助道路線偵測與追蹤系統進行初始化動作，重新搜尋道路線。
本論文提出的方法經由實驗模擬證明，可以在實際的道路影像中辨識出道路線種類，而當道路線偵測與偵測系統標記錯誤時，也能有效的初始化道路線偵測與追蹤系統。

Ideally, a kind of lane-marking can be identified in single frame. However, it is a huge challenge to identify correctly a kind of lane-marking because various driving environment could be hardly considered in single frame. To avoid above problem, the proposed method is based on time sequence of collecting several consecutive image frames to perform identification, then we can use the past data to remove the noise, and if the pattern is judged as non-lane marking pattern, the proposed system will return to initial detection process.
The experimental results show that the developed system can robust improvement of lane-marking detection and tracking mechanism and effectively identify lane-marking in various driving environment.

摘要 I
ABSTRACT V
誌謝 VI
目錄 VII
圖目錄 IX
表目錄 XI
符號表 XII
第一章 緒論 1
1-1 前言 1
1-2 文獻回顧 3
1-3 動機與目的 4
1-4 研究方法與貢獻 6
1-5 論文架構 8
第二章 道路線偵測與追蹤演算法 11
2-1 道路線亮度強化 12
2-2 道路線之偵測系統 15
2-2-1 道路線之初始位置偵測 15
2-2-2 最鄰近峰值法 21
2-2-3 迴歸分析 24
2-2-4 可靠度與消失點調整 26
2-3 問題與討論 32
第三章 道路線種類辨識 35
3-1 道路線種類辨識前處理 36
3-2 道路線特徵萃取 39
3-3 基於時間序列之道路線種類辨識 44
3-3-1 特徵暫存器 45
3-3-2 道路線分類 47
3-3-3 道路線校正 49
3-3-4 道路線偵測重置機制 53
3-4 道路線系統處理流程 54
第四章 實驗模擬 55
4-1 道路線校正 55
4-1-1 實驗說明 55
4-1-2 實驗結果 55
4-2 道路線種類辨識系統辨識率 62
4-2-1 實驗說明 62
4-2-2 實驗結果 62
4-3 道路線偵測系統重置機制 64
4-3-1 實驗說明 64
4-3-2 實驗結果 65
4-4 道路線辨識率比較 66
4-4-1 實驗說明 66
4-4-2 實驗結果 67
第五章 結論與未來工作 69
5-1 結論 69
5-2 未來工作 69
參考文獻 71
作者簡歷 73

[1] Intelligent Transportation Society of America, http://www.itsa.org/, 08, Aug. 2013.
[2] 交通部運輸研究所, http://www.iot.gov.tw/, 08, Aug. 2013
[3] L. Yunchong, H. Kezhong, and J. Peifa, “Road Markers Recognition Based on Shape Information” in Proc. IEEE Int. Symp. on Intelligent Vehicles Symposium, pp.117-122, 2007.
[4] X. Zhe and L. Zhifeng“A robust lane detection method in the different scenarios” in Proc. IEEE Int. Symp. on Mechatronics and Automation (ICMA), pp. 1358-1363, 2012.
[5] Alasdair McAndrew, Introduction to digital image processing with MATLAB, Course Technology, 2004.
[6] S. Nedevschi, V. Popescu, R. Danescu, T. Marita, and F. Oniga, “Accurate Ego-Vehicle Global Localization at Intersections Through Alignment of Visual Data With Digital Map” in Proc. IEEE Int. Symp. on Intelligent Transportation Systems, pp. 1-15, Dec., 2012, Popescu.
[7] 內政部警政署, http://www.npa.gov.tw/NPAGip/wSite/, 08, Aug. 2013.
[8] 黃偉秩，適用於嵌入式系統之快速道路線追蹤演算法，國立東華大學碩士論文，2009。
[9] C. L. Huo, Y. H. Yu and T. Y. Sun, “Lane Departure Warning System based on Dynamic Vanishing Point Adjustment,” in Proc. IEEE Global Conference on Consumer Electronics, pp. 440-443, Tokyo, Japan, Oct. 2012.
[10] X. R. Li and Y. Bar-Shalom, “Tracking in clutter with nearest neighbor filters: analysis and performance,” IEEE Trans. on Aerospace and Electronic Systems, Vol. 32, No. 3, pp. 995—1010, July 1996.
[11] S. T. Park, S. Y. Yang, and J. H. Jung, “Real-time lane recognition by simulated annealing algorithm,” in Proc. the 4th Korea-Russia International Symposium on Science and Technology, Vol. 3, pp. 95 – 98, Korea, July 2000.
[12] T. Y. Sun, S. J. Tsai, and V. Chan, “HSI color model based lane-marking detection,” in Proc. IEEE Intelligent Transportation Systems Conference, pp. 1168-1172, Toronto, Canada, Sep. 2006.
[13] 許智誠，結合慣性道路線標記與車輛陰影之前車偵測演算法，國立東華大學碩士論文，2011。
[14] Wikipedia, http://www.wikipedia.org/, 08, Aug. 2013.
[15] P. Foucher, Y. Sebsadji, J.-P Tarel, P. Charbonnier, and P. Nicolle, “Detection and recognition of urban road markings using images” in Proc. IEEE Int. Symp. on Intelligent Transportation Systems (ITSC), pp.1747-1752, 2011
[16] C. L. Huo, Y. H. Yu, J. C. Syu, and T. Y. Sun, “Vehicle warning system for land departure and collision avoidance: Using fuzzy decision making,” in Proc. IEEE Int. Conf. Fuzzy Syst., pp. 1554- 1559, 27-30, June 2011, Taipei, Taiwan.
[17] T. Y. Sun and W. C. Huang “Embedded vehicle lane-marking tracking system,” in Proc. IEEE Int. Symp. on Consumer Electronics, pp. 627-631, May 2009.
[18] T. Y. Sun, W. C. Huang, and S. J. Tsai, “Robust Lane-markings Tracking Algorithm Based on Boundary Detection and Kalman Filter” in Proc. Int. Symp. on Advanced Vehicle Control, Vol. 1, pp. 164-167, Oct., 2008.
[19] J. M. Collado, C. Hilario, A. de la Escalera, and J.M. Armigol, “Detection and classification of road lanes with a frequency analysis,” in Proc. IEEE Intell. Veh. Symp., Las Vegas, NV, 2005, pp. 78–83.
[20] J. Sparbert, K. Dietmayer, and D. Streller, “Lane detection and street type classification using laser range images,” in Proc. IEEE Intelligent Transportation Systems, pp. 454 – 459, Oakland, California, USA, Aug. 2001.
[21] S. Hao, W. Cheng, and N. El-Sheimy, “Automatic Traffic Lane Detection for Mobile Mapping Systems” in Proc. IEEE Int. Symp. on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), pp. 1-5, 2011.
[22] M. Boumediene, A. Ouamri, and N. Dahnoun, “Lane boundary detection and tracking using NNF and HMM approaches,” in Proc. IEEE Intelligent Vehicles Symposium, pp. 1107-1111, Istanbul, Turkey, June 2007.
[23] 曾俊元，以視覺感知的智慧型車輛防撞系統之研究，國立東華大學碩士論文，2003。
[24] 蔡尚錚，以視覺為主的智慧型車輛導航之研究，國立東華大學碩士論文，2002。
[25] 陳慶嘉，以電腦視覺為基礎之行車環境資訊擷取系統，國立東華大學碩士論文，2006。
[26] 紀富翔，以電腦視覺為主的快速前車偵測與警示系統，2013。
[27] 交通部公路總局, http://www.thb.gov.tw/TM/Default.aspx , 08, Aug. 2013.