跳到主要內容

臺灣博碩士論文加值系統

(44.192.22.242) 您好!臺灣時間:2021/08/01 11:59
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:洪肇澤
研究生(外文):Chao-Tse Hong
論文名稱:利用調整光流法進行障礙物偵測基於逆透視轉換運用於行車安全
論文名稱(外文):An Improved Obstacle Detection Using Optical Flow Adjusting Based on Inverse Perspective Mapping for the Vehicle Safety
指導教授:駱榮欽駱榮欽引用關係
口試委員:林啟芳王振興
口試日期:2012-07-27
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電腦與通訊研究所
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:英文
論文頁數:43
中文關鍵詞:攝影機校正逆透視轉換鳥瞰圖光流法障礙物偵測影像處理
外文關鍵詞:Camera CalibrationInverse Perspective MappingOptical FlowObstacle DetectionImage Processing
相關次數:
  • 被引用被引用:3
  • 點閱點閱:467
  • 評分評分:
  • 下載下載:51
  • 收藏至我的研究室書目清單書目收藏:0
本論文中,我們實現了一個基於逆透視轉換的光流法來檢測車輛周圍的障礙物。然而,類似的方法已被提出並且在車輛上使用。但這種方法只限於車輛是直線行駛時。如果車輛在轉彎的情況下,會使車輛左右兩側影像的光流值有所不一致,這將導致障礙物誤辨識。因此我們提出了一個方法來改善這個問題,這個方法是利用車輛的移動軌跡來計算轉彎的中心點。再利用轉彎的中心點來修正光流值的不一致。經過改善方法後可以讓光流值保持一致性,即使車輛在轉彎中。並且利用CUDA加速,使此系統可即時運行。

In this paper, we implement and improve a method to detect obstacles around the vehicle by optical flow computation based on inverse perspective mapping. However, similar methods had been proposed and used on the vehicle. But this approach is limited on a trajectory of the vehicle which moves along with a straight line. If the trajectory of the vehicle moves along with an arc line, the optical flow values will inconsistent in the left side and in the right side of this image which causes mistakes in obstacle detection. So we propose a method to improve this problem which uses the trajectory of vehicle to calculate the center of turning circle. And the center of turning circle can be used to adjust the inconsistent with optical flow values. After our improvement, the optical flow values can keep the consistence even if the trajectory is along with an arc line. Besides, we implement this system with CUDA in real-time.

摘 要 i
ABSTRACT ii
TABLE OF CONTENTS iii
LIST OF FIGURES v
Chapter 1 INTRODUCTION 1
1.1 Research Motivation 1
1.2 Survey of Related Research 2
1.3 Overview of Proposed Approaches 3
1.4 Thesis Organization 5
Chapter 2 CAMERA CALIBRATION 6
2.1 Camera Model 6
2.2 Lens Type 8
2.3 Correction of Lens Distortion 9
Chapter 3 AROUND VIEW 13
3.1 Perspective Effect 13
3.2 Homography Matrix 14
3.3 Image Alignment 16
3.4 Image Arrangement 18
Chapter 4 OPTICAL FLOW UNDER BIRD’S-EYE-VIEW 19
4.1 Optical Flow Basic Definition 19
4.2 Lucas-Kanade Method 19
4.3 Estimation of the Optical Flow 20
4.4 No Perspective Effect 22
Chapter 5 ADJUSTED OPTICAL FLOW 24
5.1 Finding the Center of Turning Circle 24
5.2 Ackermann Steering Geometry 26
5.3 Optical Flow Values Adjusting 27
Chapter 6 CUDA ACCELERATION 29
6.1 A Brief Introduction to CUDA 29
6.2 CUDA Execution Model 30
Chapter 7 EXPERIMENTAL RESULTS 32
7.1 Experimental Device and Environment 32
7.2 Experimental Results 34
7.3 Discussion 36
Chapter 8 CONCLUSION 37
8.1 Conclusion 37
REFERENCE 38
APPENDIX 40
Appendix A. Prove the Formula of Camera Calibration 41


[1] S. Shah and J. K. Aggarwal, "Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation," Pattern Recognition., vol. 29, no. 11, 1996, pp.1775 – 1788.
[2] S . Hong , J . Lee and S . Choi, "Exposure blancing and difference blurring to eliminate seam-lines in a real-time bird''s eye view monitor" Control Automation Robotics & Vision, 2010, pp. 216-221.
[3] H. A. Mallot, H. H. Bülthoff, J. J. Little and S. Bohrer, "Inverse perspective mapping simplifies optical flow computation and obstacle detection," Biological Cybernetics, 1991, pp. 177–185.
[4] C. C. Lin and M. S. Wang, "Topview Transform Model for The Vehicle Parking Assistance System," International Computer Symposium," Dec, 2010, pp.306–311
[5] Y.-C. Liu, K.-Y. Lin, and Y.-S. Chen, “Bird’s-eye view vision system for vehicle surrounding monitoring”, in Robot Vision : Proceedings of Second International Workshop, RobVis 2008, ser. Lecture Notes in Computer Science, vol. 4931/2008. Springer, 2008, pp. 207-218.
[6] T. Gandhi and M. Trivedi, “Parametric ego-motion estimation for vehicle surround analysis using an omnidirectional camera,” Machine Vision and Applications, vol.16, no.2, pp.85-95, 2005.
[7] B. Lucas and T. Kanade, "An Iterative Image Restoration Technique with an Application to Stereo Vision," Proceedings of the DARPA IU Workshop, 1981, pp. 121–130.
[8] J. Y. Wong, Theory of Ground Vehicle , 3rd Edition, John Wiley & Sons, Inc., 2001, pp. 336-339.
[9] S. Shah and J. K. Aggarwal, "Intrinsic parameter calibration procedure for a (high-distortion) fish-eye lens camera with distortion model and accuracy estimation," Pattern Recognition., vol. 29, no. 11, 1996, pp.1775 – 1788.
[10] 陳彥豪 ,劉育全,倒車攝影機影像之變形校正,台灣2008年國際科學展覽會-電腦科學組
[11] Multiple View Geometry in Computer Vision
[12] 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, 2009, pp. 963–967
[13] 何祈磊,具有影像優化處理的環場鳥瞰監視停車輔助系統,碩士論文,國立中央大學資訊工程研究所,桃園,2009
[14] C. C. Lin and M. S. Wang, "Topview Transform Model for The Vehicle Parking Assistance System," International Computer Symposium," Dec, 2010, pp.306–311,
[15] B. K. P. Horn, and B. G. Schunck, "Determining Optical Flow," Institute of Technology Massachusetts, SUA, A.I. Memo, No. 572,1980


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊