(3.236.122.9) 您好!臺灣時間:2021/05/09 05:51
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:廖光仁
研究生(外文):Guang-Ren Liao
論文名稱:影像監控用於追蹤道路線之自動駕駛系統
論文名稱(外文):An Automatic Driving System for Tracking Lane Using Image Monitoring
指導教授:李孝貽李孝貽引用關係Hsiao-Yi Lee
指導教授(外文):楊志雄Chih-Hsiung Yang
學位類別:碩士
校院名稱:國立高雄應用科技大學
系所名稱:電機工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:104
畢業學年度:100
語文別:中文
論文頁數:82
中文關鍵詞:自動駕駛行車線檢測差速控制影像辨識
外文關鍵詞:Automatic drivingLane detectionDifferential velocity controlImage recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:1075
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:122
  • 收藏至我的研究室書目清單書目收藏:0
本研究設計與製作一套以影像辨識為基礎的自動駕駛系統。控制器使用Samsung公司ARM9系列的S3C2440與Atmel公司的ATmega16L,並在S3C2440嵌入Linux作業系統。本系統整合以上兩組控制器,並規劃三大子系統,分別是行車線檢測系統、導航修正系統與差速控制系統。ARM經由攝影機連續拍攝取得影像,經過一連串的影像辨識技術根據色差取得道路框線,如平滑處理、Canny邊緣檢測與霍夫轉換,再進一步分析與比較記憶資料的角度與座標,確保取得安全的行進路線,有效消除如路燈影子形成的雜訊。導航修正系統依據影像中的道路線角度初步判斷車子的轉向角度,再根據行車線在影像中的座標做修正,最後利用空間轉換的方法,對應為現實世界的轉向角度,並透過UART介面將轉向角度傳給ATmega16,由ATmega16控制RC伺服馬達執行精確的角度切換,完成導航修正系統的作業程序。差速控制系統由ATmega16控制驅動輪,修正內側車輪與外側車輪的轉速,使車子行駛彎道更平滑。經由三大子系統整合的自動駕駛系統,經實際測試後不但可降低因邊線雜訊而追蹤失敗的問題,若遇到行車線阻斷時亦可即時檢知,系統會強迫停車並等待駕駛者之處理訊息,以增加自動駕駛的安全性。
This study is about an automatic driving system based on image recognition. The central controller is made up of Atmel’s ATmega16L and Samsung’s ARM9-S3C2240, which is inserted in the Linux operating system.
These two sets of controllers are integrated into this system, and it contains three subsystems─driving lane detection system, navigation correction system, and differential velocity control system.
ARM obtains the vision by continuously quick photographing. After using a series of image recognition techniques, including smoothing, Canny edge detection, and Hough transformation, the controller can get information about road dividers in the front. Then, the system will compare this information with the coordinate and the angle in database, and make sure that the car is driven in the correct direction. This comparison could effectively eliminates noise like the shadows of street lights.
The navigation correction system correct the angle deviation according to angle between the road dividers and the front of the car in the beginning, and then it correct the direction again based on the coordinate in the data of image. Finally, this angle correction corresponds to a change on steering direction in terms of space conversion. This command will be delivered to ATmega16L controller through UART interface, and the ATmega16L controller will control RC servo motor to turn the car precisely, finishing the navigation correction procedure.
The principle of differential velocity control system is forming a rotational speed difference between the inner wheel and the outer one by controlling the driving gear with ATmega16L. The difference can help the car curve much smoother.
Through down-to-earth test, the automatic driving system can not only lessen the failure of tracking due to edge noise, but also stop the car and wait for the driver to deal with the message when finding the lane is blocked and alerting. It will increase the security of automatic driving.
摘 要 i
Abstract ii
誌 謝 iii
目 錄 iv
圖 目 錄 vi
表 目 錄 ix
第1章 緒 論 1
1-1 研究目的與動機 1
1-2 相關回顧 2
1-3 論文架構 2
第2章 車體架構設計 4
2-1 車體概觀 4
2-2 底盤規劃 5
2-3 後輪規劃 6
2-4 前輪與轉向機構規劃 7
2-5 攝影機配置 12
第3章 硬體元件與電路設計 14
3-1 硬體架構 14
3-2 中央處理單元 15
3-3 輔助處理單元 17
3-4 通訊電路 20
3-5 RC伺服馬達 22
3-6 微型減速馬達 23
3-7 電源電路 27
3-8 實體電路 28
第4章 行車系統設計與實測 30
4-1 程式架構簡介 30
4-1.1 中央處理單元程式架構 30
4-1.2 輔助處理單元程式架構 32
4-2 軟體介紹與移植 35
4-2.1 MJPG-streamer介紹與移植 35
4-2.2 OpenCV介紹與移植 36
4-3 行車線檢測系統 37
4-3.1 影像處理 37
4-3.2 Hough轉換 41
4-3.3 線段檢測 42
4-4 減速馬達控制 47
4-5 RC伺服馬達控制 49
4-6 導航修正系統 52
4-6.1 程式架構 52
4-6.2 行車線種類之判別 54
4-7 差速控制系統 56
第5章 實驗結果 60
5-1 自動駕駛系統實驗結果 60
第6章 結論與未來展望 66
參考文獻 67
[1]P.-Y. Hsiao, C.-W. Yeh, S.-S. Huang, L.-C. Fu, "A Portable Vision-Based Real-Time Lane Departure Warning System:Day and Night," IEEE Transactions on Vehicular Technology, vol. 58, no. 4, pp.2089 – 2094, 2009
[2]H.-Y. Cheng, B.-S. Jeng, P.-T. Tseng, K.-C. Fan, "Lane Detection With Moving Vehicles in the Traffic Scenes," IEEE Transactions on Intelligent Transportation Systems, vol. 7, no. 4, pp.571 – 582, 2006
[3]J. Kaszubiak, M. Tornow, R.W. Kuhn, B. Michaelis, C. Knoeppel, "Real-time vehicle and lane detection with embedded hardware," Proc. IEEE Intelligent Vehicles Symposium, pp.619 – 624, 2005
[4]Z. Kim, "Robust Lane Detection and Tracking in Challenging Scenarios," IEEE Transactions on Intelligent Transportation Systems, vol. 9, no. 1, pp.16 – 26, 2008
[5]鳥哥著,鳥哥的Linux私房菜 - 基礎學習篇(第三版),碁峯資訊股份有限公司
[6]施威銘研究室,Linux 實務應用 Fedora 10,旗標出版股份有限公司
[7]許永和,嵌入式系統概論 以S3C2440核心為架構,學貫行銷股份有限公司
[8]孫弋,基於S3C2440的嵌入式Linux開發實例,西安電子科技大學出版社
[9]Gary Bradski and Adrian Kaehler, Learning OpenCV
[10]P. Bao, L. Zhang, X. Wu, "Canny edge detection enhancement by scale multiplication," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 9, pp.1485 – 1490, 2005
[11]M. Jacob, M. Unser, "Design of Steerable Filters for Feature Detection Using Canny-Like Criteria," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp.1007 – 1019, 2004
[12]R.K. Satzoda, S. Sathyanarayana, T. Srikanthan, S. Sathyanarayana, "Hierarchical Additive Hough Transform for Lane Detection," IEEE Embedded Systems Letters, vol. 2, no. 2, pp.23 – 26, 2010
[13]J. Gall, A. Yao, N. Razavi, L. Van Gool, V. Lempitsky, "Hough Forests for Object Detection, Tracking, and Action Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 11, pp.2188 – 2202, 2011
[14]A.L. Kesidis, N. Papamarkos, "On the Inverse Hough Transform," IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 21, no. 12, pp.1329 – 1343, 1999
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔