單目視覺倒車入庫系統｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	蔡金倫 Jin-Lun Cai
論文名稱：	單目視覺倒車入庫系統 A Backward Parking System based on Monocular Vision
指導教授：	羅吉昌 Ji-Chang Lo
口試委員:
學位類別：	碩士 Master
系所名稱：	工學院 - 光機電工程研究所 Graduate Institute of Opto-mechatronics Engineering
論文出版年：	2020
畢業學年度：	108
語文別：	中文
論文頁數：	74
中文關鍵詞：	單目視覺、相機校正、自走車、停車、輪廓檢測
外文關鍵詞：	Monocular vision, Camera calibration, Selfguiding vehicle, parking, Contour detection
相關次數：	點閱：6 下載：0
分享至:	分享至facebook 分享至twitter

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

本研究使用單晶片電腦RaspberryPi 搭載單目鏡頭作為機器視覺系
統，經由UART 將控制所需之回授訊號傳輸至車體控制系統之微處理器
Arduino 控制自走車。機器視覺系統方面利用二值化、Canny 邊緣檢測、
閉運算、輪廓檢測等影像處理技術判斷鏡頭是否捕捉到停車格影像，並
利用相機校正取得單目相機之內參及外參，從而建立三維世界座標與二
維像素座標之間的對應關係，解算後取得相機與停車格之距離與偏航角
作為車體控制所需之參數。車體控制系統方面利用Arduino 接收之訊號
控制鏡頭轉動，並使用PID、PI 控制法輸出PWM 訊號控制馬達實現自
走車倒車入庫。

This research uses a singlechip
microcomputer RaspberryPi equipped
with a monocular len as a machine vision system, and transmits the
values required for control via UART to the microprocessor Arduino, serving
as a vehicle body control system, to control the selfguiding
vehicle.
The machine vision system uses image processing techniques such as
binarization, Canny edge detection, closed operation, and contour detection
to determine whether the camera captures a parking grid image,
and uses camera calibration to obtain the internal and external parameters
of the monocular camera, thereby establish the correspondence between
the threedimensional
world coordinates and the twodimensional
pixel coordinates, After calculation, the distance between the camera,
the parking space and the yaw angle are obtained as parameters required
for vehicle body control. In the body control system, the signal
received by the Arduino is used to control the lens rotation, and the PID
and PI control methods are used to output PWM signals to control the
motor to realize selfguiding
vehicle backward parking.

目錄viii
一、緒論1
1 背景介紹.................................................................. 1
2 研究目的與動機......................................................... 1
3 文獻回顧.................................................................. 2
4 論文架構.................................................................. 3
二、系統架構及硬體元件5
1 系統架構.................................................................. 5
2 硬體元件.................................................................. 6
2.1 影像處理系統................................................... 7
2.2 控制系統......................................................... 8
2.3 電源系統......................................................... 9
2.4 馬達系統......................................................... 10
3 硬體通訊介面............................................................ 13
3.1 UART 通信介面................................................ 13
三、影像處理背景知識14
1 影像處理演算法......................................................... 14
1.1 灰階與二值化................................................... 14
1.2 Canny 邊緣檢測................................................ 17
1.3 形態學............................................................ 18
1.4 停車格檢測...................................................... 22
2 相機校正.................................................................. 25
2.1 針孔成像......................................................... 25
2.2 座標系關係...................................................... 27
2.3 座標系轉換...................................................... 30
2.4 張式校正法...................................................... 35
2.5 相機畸變......................................................... 41
四、停車格資訊辨識實驗45
1 單目視覺處理系統...................................................... 45
2 相機位姿估計............................................................ 46
2.1 PnP 求解......................................................... 46
3 視覺回授資訊量測...................................................... 49
3.1 實驗環境......................................................... 49
3.2 角點座標排序................................................... 50
3.3 特徵點世界座標匹配.......................................... 51
3.4 視覺回授數據................................................... 53
五、控制流程與實驗結果57
1 倒車入庫控制系統...................................................... 57
1.1 自走車架構...................................................... 58
2 控制流程設計............................................................ 60
2.1 控制器設計...................................................... 60
2.2 中斷處理......................................................... 62
2.3 倒車入庫控制流程............................................. 63
3 實驗結果.................................................................. 67
六、結論與未來展望69
1 結論........................................................................ 69
2 未來展望.................................................................. 71
參考文獻72

                                

1. 王振維. 利用影像分析做自走車自動停車之研究碩士論文(國立高雄應用科技大
學, 高雄市, 2011). 88 pp. https://hdl.handle.net/11296/8spef3.
2. 廖育聖. 以對應點為基礎應用立體視覺之自動停車系統碩士論文(國立臺北科技
大學, 台北市, 2008). 85 pp. https://hdl.handle.net/11296/z2s4e6.
3. 呂承翰. 應用數位影像處理之自動停車系統碩士論文(國立臺灣海洋大學, 基隆市,
2012). 86 pp. https://hdl.handle.net/11296/9bygde.
4. 黃俊翰. 以雙眼視覺輔助路邊停車碩士論文(國立中山大學, 高雄市, 2012). 74 pp.
https://hdl.handle.net/11296/abt8zu.
5. 康畯欽. 立體視覺測距輔助移動機器人自動停車碩士論文(國立臺灣科技大學, 台
北市, 2011). 73 pp. https://hdl.handle.net/11296/d5gc52.
6. Canny, J. A Computational Approach to Edge Detection. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 679–698. ISSN: 01628828.
http://
ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4767851 (Nov.
1986).
7. Suzuki, S. Topological Structural Analysis of Digitized Binary Images by Border
Following, 15.
8. Douglas, D. H. & Peucker, T. K. ALGORITHMS FOR THE REDUCTION OF THE
NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR
ITS CARICATURE. Cartographica: The International Journal for Geographic Information
and Geovisualization, 112–122. ISSN: 03177173,
19119925.
https:
//utpjournals.press/doi/10.3138/FM57-6770-U75U-7727 (Dec. 1973).
9. Heckbert, P. S. & Garland, M. Survey of Polygonal Surface Simplification Algorithms,
31.
10. Tsai, R. Y. A Versatile Camera Calibration Techniaue for HighAccuracy
3D Machine
Vision Metrology Using Offtheshelf
TV Cameras and Lenses, 22.
11. Zhang, Z. A flexible new technique for camera calibration. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 1330–1334. ISSN: 01628828. http:
//ieeexplore.ieee.org/document/888718/ (Nov. 2000).
12. Zhang, Q.s.
& Mei, X. Study on the Method of Measuring the Preceding Vehicle
Distance Based on Trilinear Method in 2010 Second International Conference on
Computer Modeling and Simulation 2010 Second International Conference on
Computer Modeling and Simulation (ICCMS) (IEEE, Sanya, China, Jan. 2010),
475–479. ISBN: 9781424456420.
http://ieeexplore.ieee.org/document/
5421136/.
13. Barnada, M., Conrad, C., Bradler, H., Ochs, M. & Mester, R. Estimation of automotive
pitch, yaw, and roll using enhanced phase correlation on multiple farfield
windows in 2015 IEEE Intelligent Vehicles Symposium (IV) 2015 IEEE Intelligent
Vehicles Symposium (IV) (IEEE, Seoul, South Korea, June 2015), 481–486. ISBN:
9781467372664.
http://ieeexplore.ieee.org/document/7225731/.
14. Joglekar, A., Joshi, D., Khemani, R., Nair, S. & Sahare, S. Depth Estimation Using
Monocular Camera, 6 (2011).
15. Zheng, Z., Ren, X. & Cheng, Y. An Object Distance Measuring Method of Monocular
Vision Mobile Robot. International Journal of Control and Automation, 117–
128. ISSN: 20054297, 20054297. http://article.nadiapub.com/IJCA/vol11_
no3/11.pdf (Mar. 31, 2018).
16. Said, Z., Sundaraj, K. & Wahab, M. Depth Estimation for a Mobile Platform Using
Monocular Vision. Procedia Engineering, 945–950. ISSN: 18777058. https://
linkinghub.elsevier.com/retrieve/pii/S1877705812026677 (2012).
17. Taylor, T., Geva, S. & Boles, W. W. Monocular Vision as a Range Sensor, 11
(2004).
18. Slabaugh, G. G. Computing Euler angles from a rotation matrix, 7.
19. 黃義文. 應用自組織模糊控制器於自動路邊停車之設計碩士論文(國立臺北科技
大學, 台北市, 2009). 74 pp. https://hdl.handle.net/11296/36wr32.
20. 許裕昇. 自動停車之停車位偵測與路徑追蹤控制研究碩士論文(國立臺北科技大
學, 台北市, 2009). 91 pp. https://hdl.handle.net/11296/5hhz25.
21. 林建良. 利用光流偵測停車空間與模糊控制決策實現自動倒車入庫系統碩士論
文(國立臺北科技大學, 台北市, 2013). 51 pp. https://hdl.handle.net/11296/
y9j75g.
22. Riyanto, I. PID Controllerbased
Object Tracking and Speed Control System for
Wheeled Soccer Robot preprint (INARxiv,
Nov. 7, 2017). https : / / osf . io /
xqu9a.
23. PWM 圖https : / / www . sunfounder . com / learn / sensor - kit - v2 - 0 - for -
raspberry - pi - b - plus / lesson - 2 - rgb - led - module - sensor - kit - v2 - 0 -
for-b-plus.html.
24. UART 時序圖https://kknews.cc/code/xjmxr5g.html.
25. OpenCV: OpenCV Tutorials https : / / docs . opencv . org / master / d9 / df8 /
tutorial_root.html.
26. 最大值抑制示意圖Medium. https://medium.com/@bob800530.
27. 高哲立茲, 伍茲, 繆紹綱, Gonzalez, R. C. & Woods, R. E. 數位影像處理OCLC:
294947657. ISBN: 9789867594112
(臺灣培生教育出版; 普林斯頓國際發行: 新
科技總經銷, 臺北市; 臺北縣五鄉股, 2003).
28. 鍾國亮. 影像處理與電腦視覺= Image processing and computer vision ISBN:
9789574836970
(臺灣東華, 臺北市, 2012).
29. What Is Camera Calibration? MATLAB
& Simulink https://www.mathworks.
com/help/vision/ug/camera-calibration.html?w.mathworks.com.
30. 廖紘億. 自動相機校正與二維影像輪廓萃取研究碩士論文(國立中央大學, 桃園縣,
2015). 81 pp. https://hdl.handle.net/11296/a78gb8.
31. Ordering coordinates clockwise with Python and OpenCV PyImageSearch. https:
//www.pyimagesearch.com/2016/03/21/ordering-coordinates-clockwisewith-
python-and-opencv/.

簡易檢索 / 詳目顯示

相關論文