跳到主要內容

臺灣博碩士論文加值系統

(3.231.230.177) 您好!臺灣時間:2021/08/04 10:57
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:陳龍玥
研究生(外文):Lung-YuehChen
論文名稱:基於擴展式卡爾曼濾波器之載具狀態預估與攝影機校正法則之發展
論文名稱(外文):Development of EKF-based Target Vehicle State Estimation and Camera Calibration Algorithms
指導教授:莊智清莊智清引用關係
指導教授(外文):Jyh-Ching Juang
學位類別:碩士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
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:2012
畢業學年度:100
語文別:中文
論文頁數:66
中文關鍵詞:狀態預估載具校正攝影機卡爾曼濾波器
外文關鍵詞:state estimationvehiclecalibrationcamerakalman filter
相關次數:
  • 被引用被引用:1
  • 點閱點閱:421
  • 評分評分:
  • 下載下載:148
  • 收藏至我的研究室書目清單書目收藏:0
有鑑於平日時車禍時常發生,近年來眾人為了減少車禍之發生率,而研發許多提升交通安全性之系統,其中防撞系統亦成為重要議題的其中之一。對於建立完善防撞系統,所以使用各種感測器之特性並加以結合,其中影像感測器可以藉由擷取影像資訊後,經過分析而得知周遭車輛之資訊,來提升交通環境中的安全性與便利性。本論文主要模擬出真實交通環境中部分車輛,其備有基於影像感測器及濾波器之系統的應用與運作情形,換言之即包括如何使用影像感測器預知目標車輛之位置、速度、加速度,以及視覺感測器之校正。
首先建構出虛擬的交通環境,包括:多台移動車輛、影像感測器…等,在車輛軌跡之預估中,車輛使用影像感測元件擷取目標車輛之影像資訊並分析,將多張二維影像資訊與目標車輛狀態之估測值運用至擴展式卡爾曼濾波器中,來進行目標車輛之行駛狀態預估。另外一個探討主題─基於卡爾曼濾波器對攝影機做校正,因載具狀態預估過程中若量測量不準確,則錯誤的預估結果造成駕駛員對行駛決策的誤判,而造成量測量不準確的原因可能為攝影機偏移、傾斜…等問題造成,故須對其做校正,過程中使用視覺感測和車載通訊,將得到資訊當成量測量應用於濾波器中完成校正之工作。

In view of recent increase in traffic accidents, many researches have been devoted to developing systems that enhance the traffic safety. As the result, collision avoidance system had became an important issue. The objective of the research is to investigate the collision avoidance system, by combining different of sensors, including GNSS, vision, laser and other similar sensors. Vision sensors can provide image information of surrounding vehicles and traffic states. Through information processing and traffic state analysis, the safety of traffic environment will be improved. This thesis simulates real traffic environments where some vehicles are equipped with vision sensors. The Extended Kalman filters are used to estimate the trajectory of target vehicle and perform camera calibration at the same time.
At the beginning, the virtual traffic environments, including vehicles, infrastructures and vision sensors, are constructed. Afterwards, the conditions of traffic environment such as motion and equipment of each vehicle and position and velocity of self-vehicle are simulated. In the simulation, vehicles utilize vision information and estimate states of target vehicles, including trajectory, absolute velocity, and head angle, by Extended Kalman filters. In addition, camera calibration based on EKF is discussed in this thesis. Once cameras are subject to severe skew or shifting, the estimation error are likely to increase. If the measurements are invalid, the vehicle state estimation result would be incorrect. If a driver trusts the incorrect result of estimation and makes wrong judgment when driving the vehicle, an accident may occur due to the system. Therefore camera calibration is an important task before running the system of estimating vehicle state during driving. In the procedure of camera calibration, the system utilizes the data of the target vehicle which is transmitted by DSRC and also visual data, and then these measurements are applied in EKF to achieve camera calibration.

摘要 I
Abstract III
誌謝 V
表目錄 IX
圖目錄 X
參數表 XII
第一章 緒論 1
1.1. 前言 1
1.2. 研究動機與目的 1
1.3. 文獻回顧 2
1.4. 主要貢獻 2
1.5. 論文架構 3
第二章 視覺座標系統與三維重建 4
2.1. 座標轉換 4
2.1.1. 世界座標系轉至攝影機座標系 4
2.1.2. 攝影機座標系轉至影像座標系 8
2.2. 三維座標點的重建 10
2.3. 雜訊影響分析 16
2.3.1. 分析概述 18
2.3.2. 分析結果 18
2.3.2.1. 等速度行駛模擬環境 19
第三章 整合卡爾曼與視覺的車間應用 22
3.1. 擴展式卡爾曼濾波器 22
3.2. 載具狀態預估 25
3.2.1. 等速度行駛模擬之系統架構 26
3.2.2. 非固定速度行駛模擬之系統架構 29
3.3. 相機參數校正 31
3.3.1. 相機參數校正系統架構 32
第四章 模擬結果與討論 37
4.1. 載具狀態預估 37
4.1.1. 等速度行駛模擬 41
4.1.2. 非固定速度行駛模擬 46
4.2. 攝影機校正 53
4.2.1. 車輛行駛之攝影機校正模擬 56
第五章 結論與未來工作 62
5.1. 結論 62
5.2. 未來工作 62
參考文獻 64
[1]H. Aghajan, A. Cavallaro, Multi-Camera Networks: Principles and Application, Boston:Elsevier, 2009.
[2]J. Y. Bouguet, “Camera Calibration Toolbox for Matlab, Available: http://www.vision.caltech.edu/bouguetj/calib_doc/#start
[3]N. Buch, S. A. Velastin, and J. Orwell, “A Review of Computer Vision Techniques for the Analysis of Urban Traffic, IEEE Transactions on Intelligent Transportation Systems, Vol. 12, No. 3, 2011.
[4]Y. M. Chan, S. S. Huang, L. C. Fu, P. Y. Hsiao and M. F. Lo, “Vehicle Detection and Tracking under Various Lighting Conditions Using A Particle Filter, IET Intelligent Transport Systems, Vol. 6, No. 1, pp. 1-8, 2012.
[5]M. S. Grewal, A. P. Andrews, Kalman Filtering: Theory and Practice Using MATLAB, New York:Wiley, 2001.
[6]R. C. Gonzalez, R. E. Woods, Digital Image Processing , New Jersey: Pearson/Prentice Hall, 2008.
[7]J. Heikklilä and O. Silvén, “A Four-Step Camera Calibration Procedure with Implicit Image Correction, Proceeding IEEE Conference Computer Vision and Pattern Recognition, Vol. 3, pp. 1106-1112, 1997.
[8]H. W. Hsieh, C. C. Wu, and J. S. Hu, “A Procedure for Simultaneous Calibration of Environmental Cameras and Localization of Mobile Robots, Proceedings of the 7th Asian Control Conference, pp. 905-912, 2009.
[9]D. Huang, H. Leung, “An Expectation-Maximization-Based Interacting Multiple Model Approach for Cooperative Driving Systems, IEEE Transactions on Intelligent Transportation Systems, Vol. 6, No. 2, pp. 206-228, 2005.
[10]F. Janabi-Sharifi and M. Marey, “A Kalman-Filter-Based Method for Pose Estimation in Visual Servoing, IEEE Transactions on Robotics, Vol. 26, No. 5, pp. 939-947, 2010.
[11]J. S. Lee and Y. H. Jeong, “CCD camera calibrations and projection error analysis, Proceeding IEEE International Conference on Science and Technology, Vol. 2, pp. 50-55, 2000.
[12]A. McAndrew, Introduction to digital image processing with MATLAB, Boston: Thomson Course Technology, 2004

[13]P. Negri, X. Clady, S. M. Hanif, and L. Prevost, “A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection, EURASIP Journal on Adavances in Signal Processing, Vol. 2008, No. 136, pp. 1-12, 2008.
[14]T. T. Nguyen, X. D. Pham, J. H. Song, S. Jin, D. Kim, and J. W. Jeon, “Compensating Background for Noise due to Camera Vibration in Uncalibrated-Camera-Based Vehicle Speed Measurement System, IEEE Transactions on Vehicular Technology, Vol. 60, No. 1, pp. 30-43, 2011.
[15]R. Y. Tsai, “A Versatile Camera Calibration Technique for High Accuracy 3d Machine Vision Metrology Using Off-the-shelf TV Cameras and Lenses, IEEE Journal of Robotics and Automation, Vol. RA-3, No. 4, pp. 323–344, 1987.
[16]Y. U. Yim and S. Y. Oh, “Three-Feature Based Automatic Lane Detection Algorithm (TFALDA) for Autonomous Driving, IEEE Transactions on Intelligent Transportation Systems, Vol. 4, No. 4, pp. 219-225, 2003.
[17]P. Zarchan and H. Musoff, Fundamentals of Kalman Filtering: A Practical Approach, American Institute of Aeronautics and Astronautics, 2000.
[18]Z. Zhang, “A Flexible New Technique for Camera Calibration, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, pp. 1330–1334, 2000.
[19]蕭東榕,「智慧型攝影機網路射頻與視覺定位之實現與分析」,國立成功大學電機工程研究所碩士論文, 2010.
[20]交通安全入網口,交通安全統計資訊,網址:http://168.motc.gov.tw/GIPSite/wSite/lp?ctNode=1389&CtUnit=85&BaseDSD=7&mp=1
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊