簡易檢索 / 詳目顯示

回結果列表
研究生： 林育誠
Yu-Cheng Lin
論文名稱： 即時產生之環車Perspective Top-View影像與其應用：自動停車系統
Real-Time Generation of Perspective Top-View Images of a Vehicle and its Application: Automatic Parking System
指導教授： 陳世旺
Chen, Sei-Wang
學位類別： 碩士
Master
系所名稱： 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2013
畢業學年度： 101
語文別： 中文
論文頁數： 74
中文關鍵詞： Aerial image 、Perspective Top-View image 、Perspective Top-View transformation 、鳥瞰影像 、色彩混合 、自動停車
英文關鍵詞： Aerial image, Perspective Top-View image, Perspective Top-View transformation, Bird`s eye-view image, Color blending, Automatic parking
論文種類： 學術論文
相關次數： 點閱：447  下載：17 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 行車安全隨著時代的進步愈來愈受到人們的重視，各大車廠及汽車周邊配備廠商也注意到此一現象，紛紛研發各種車輛駕駛輔助系統，旨在提升行車駕駛者的舒適、效率與安全。而車輛四周的視線死角(Blind areas)一直是威脅行車安全的主因之一。目前已經有一些廠商針對此問題推出相關的產品，他們在車輛四周裝設攝影機，建立環車鳥瞰影像(Aerial images)，藉此影像便可消除視線死角，提升行車安全。但這些產品還依然存在著一些缺陷，本研究分析傳統鳥瞰影像建立過程之缺失並提出新的鳥瞰影像建立流程：Perspective Top-View(PTV) transformation，利用PTV transformation與色彩混合(Color blending)我們建立了品質較好的環車全景俯視影像(PTV images)。除此之外，本研究還進一步利用此影像建立一套可自動偵測環境中停車格並自動停車的車駕輔助系統(AP system)。
    另外，為了達到能即時轉換PTV images之目的，我們將Perspective Top-View transformation過程中影像像素之對應關係整合成一轉換表，如此便可用查表法(Look-up table)加速PTV images的建立，達到即時轉換的效果。當有了PTV images之後，使用者便可啟動停車格偵測的程序，此程序找出PTV images中可能的停車格位置供使用者選擇，接著本研究再根據台灣現有的三種標準停車格(路邊停車格、直角停車格、斜角停車格)，分別設計停車的策略，使得車輛可以正確地停入使用者選擇的停車格。
    總的來說，本實驗達成了以下目的: 1.可即時產生監控車周的俯視影像 2.可自動偵測俯視影像中可能之停車格位置並可以將車輛正確地停入停車格。

    With the progress of traffic safety increasing attention has been paid, the major depot and automotive peripherals manufacturers also noticed this phenomenon. They have developed a variety of vehicle driving assistance system for enhancing comfort, efficiency and safety when driving. And the blind areas around the vehicle have been one of the main threats to traffic safety.There are already some manufacturers introduced related products for this problem. They install cameras around the vehicle and build an aerial image. It can eliminate blind areas around the vehicle to improve traffic safety.
    However, these products still have some defects. This study analyzed the lack of conventional aerial image and proposed a new aerial image building process: Perspective Top-View (PTV) transformation. By PTV transformation and color blending, we had established a better quality aerial image (PTV images). In addition, this study further exploited this image to establish a driving assist system(AP system) which can detect parking space around vehicle and parking automatically.

    第一章 簡介　　　　　　　　　　　　　　　　　　　　　　 1-1 1.1 研究動機……………………………………………………………1-1 1.1.1 環車鳥瞰影像………………………………….……………1-2 1.1.2 停車輔助系統……………………………………….………1-4 1.2 停車格位………………………………………………….…………1-5 1.3 文獻探討………………………………………………….…………1-7 1.3.1 環車鳥瞰影像文獻探討…………………….…………....1-7 1.3.2 自動停車輔助系統文獻探討…………….………………..1-12 1.4 比較與改進方法………………………………….………………..1-14 1.4.1 傳統鳥瞰影像建立方法簡介…………………….………..1-14 1.4.2 問題探討與改進之想法…………………………….……..1-16 1.5 文章架構…………………………………………………….……..1-17 　　第二章 系統架構　 　　　　　　　　　　　　　　 2-1 2.1 系統架構……………………………………………………….……2-1 2.2 系統流程圖…………………………………………………….……2-4 第三章 PTV影像的實施步驟 3-1 3.1 前置參數求取........................…………………………….…………3-1 3.2 PTV影像轉換參數.................………………………………………3-3 3.2.1 PTV transform的推導過程…………………………………3-4 3.2.2 取得參考影像……….………………………………………3-7 3.3 解決影像空洞問題………...………………………...……………...3-8 3.4 影像的曝光補償與色彩融合......…………………………………...3-9 第四章 停車格偵測 4-1 4.1 PTV影像的前處理.....………………………………………………4-2 4.2 辨識停車格並估計停車格的中心位置…………………….………4-3 4.2.1 交點累計整合……………………………………….………..4-6 4.2.2 其餘必要的停車格資訊………………..……………...……..4-7 第五章 實驗 5-1 5.1 實驗場景設計與實驗設備…………………..……………….……..5-1 5.2 建立PTV影像的各階段結果與其參數...………………….………5-3 5.3 自動停車系統...…………………………………………………...5-14 5.3.1 直角停車格…………………………………………….…..5-15 5.3.2 路邊停車格…………………………………………….…..5-17 5.3.3 斜角停車格…………………………………….…………..5-19 第六章 結論 6-1 6.1 結論…………………………………………………………………6-1 6.2 未來工作……………………………………………….……………6-2 附錄AmigoBot控制程式碼 附-1 參考著作 參-1

    [Gov 1] http://www.motc.gov.tw/uploaddowndoc?file=survey/201203091759310.pdf&filedisplay=99年自用小客車使用狀況調查報告.pdf&flag=doc
    [Gov 2] http://sowf.moi.gov.tw/stat/week/week10053.doc
    [Gov 3] http://202.39.131.142/web_law/Attachment/lawitem/A0011/第190條附圖.doc
    [Gov 4] http://w3.cpami.gov.tw/district6/i2.htm
    [Gov 5] http://202.39.131.142/web_law/Attachment/law/G0058/停車格位與禁停標線之劃設原則.doc
    [BVI01] http://news.u-car.com.tw/7588.html
    [BVI02] http://news.u-car.com.tw/9466.html
    [BVI03] http://www.youtube.com/watch?v=HkNIXDcMnOk
    [BVI04] http://www.fujitsu.com/downloads/MICRO/fma/pdf/360_OmniView_FS.pdf
    [BVI05] http://www.spiegel.de/fotostrecke/audi-a6-avant-kamera-laeuft-fotostrecke- 78072-6.html
    [BVI06] http://www.auto123.com/en/mercedes/gl-class/2013/review?carid=11340057 01&artid=146361
    [BVI07]http://www.whetron.com.tw/WEn/productInfo.php?fkWEProductKind=2&id=14
    [BVI08]http://www.itri.org.tw/chi/msl/p4.asp?RootNodeId=070&NavRootNodeId=0733&NodeId= 073322&ArticleNBR =3030
    [BVI09] http://www.artc.org.tw/chinese/02_research/02_01detail.aspx?pdid=34
    [BVI10] http://autos.udn.com/topic/car/news/article.jsp?type=article&f_SUB_ID=45&f_ART_ID=18761
    [BVI11]http://www.mobile01.com/newsdetail.php?id=9254
    [BVI12]http://chinese.engadget.com/2013/03/06/ford-active-system-chinese-hands-on

    [Cla05] D. Claus and A.W. Fitzgibbon, "A Plumbline Constraint for the Rational Function Lens Distortion Model," Proc. of the British Machine Vision, 2005.

    [Cla05] D. Claus and A. W. Fitzgibbon, "A Rational Function Lens Distortion Model forGeneral Cameras," Proc. of Computer Vision and Pattern Recognition, vol. 1, pp.213–219,2005.

    [Har03] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Second Edition, pp.33-44, 2003.

    [Hon10] S. Hong, J.S. Lee, and S.B. Choi, "Exposure balancing and difference blurring to eliminate seam-lines in a real-time bird's eye view monitor," International Conference on Control Automation Robotics & Vision (ICARCV), pp.216-221, 2010.

    [Hsu10] 許之凡, "基於環車鳥瞰影像之自動停車系統," 臺灣師範大學, 碩士論文, 2010

    [Kan00] Sing Bing Kang, Richard Weiss, "Can We Calibrate a Camera Using an Image of a Flat,Textureless Lambertian Surface?," European Conference on Computer Vision, pp.640-653, 2000.

    [Low06] M. Brown and D. Lowe, "Automatic Panoramic Image Stitching Using Invariant Features," Int’l Journal of Computer Vision, vol.74, no.1, pp.59-73, 2006.

    [Luo09] L.B. Luo, I.S. Koh, S.Y. Park, R.S. Ahn, and J.W. Chong, "A software-hardware cooperative implementation of bird's-eye view system for camera-on-vehicle," IEEE International Conference on Network Infrastructure and Digital Content, pp.963-967, 2009.

    [Luo10] L.B. Luo, I.S. Koh, K.Y. Min, Jun Wang, and J.W. Chong, "Low-cost implementation of Bird's-eye view system for camera-on-vehicle," International Conference on Consumer Electronics (ICCE), pp.311-312, 2010.

    [Tho11] B. Thomas, R. Chithambaran, Y. Picard,and C. Cougnard, "Development of a cost effective bird's eye view parking assistance system," IEEE Recent Advances in Intelligent Computational Systems (RAICS), pp. 461-466, 2011.

    [Zha00] Z. Zhang, "A Flexible New Technique for Camera Calibration," IEEE Trans. On Pattern Analysis and Machine Intelligence, vol.22, no.11, pp.1330-1334, 2000

    下載圖示
    QR CODE