跳到主要內容

臺灣博碩士論文加值系統

(44.192.20.240) 您好!臺灣時間:2024/03/04 12:57
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:孫正泰
研究生(外文):Zheng-Tie, Sun
論文名稱:以電腦視覺為基礎之道路上障礙物偵測
論文名稱(外文):On-Road Computer Vision Based Obstacle Detection
指導教授:傅立成傅立成引用關係
指導教授(外文):Li-Chen, Fu
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊工程學研究所
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:2001
畢業學年度:89
語文別:英文
論文頁數:79
中文關鍵詞:電腦視覺汽車駕駛安全警告系統障礙物偵測立體視覺顏色資訊行人偵測機車腳踏車偵測汽車偵測
外文關鍵詞:Computer VisionSafety Waring System for Vehicle DrivingObstacle DetectionStereo VisionColor InformationPedestrian DetectionBike DetectionVehicle Detection
相關次數:
  • 被引用被引用:11
  • 點閱點閱:534
  • 評分評分:
  • 下載下載:122
  • 收藏至我的研究室書目清單書目收藏:1
將電腦技術應於汽車行駛已有多年的歷史。目前在世界上有很多大學實驗室及公私立關機乃至政府組織對於智慧型傳輸系統(Intelligent Transportation System —ITS)均有在著手進行,它主要是利用硬體及軟體的技術來更有效率地利用交通資源並可以增進駕駛人及行人的安全性。而在這個領域中,障礙物的辨識對於輔助駕駛人在一些危險的情況扮養了很重要的角色。在本篇論文中,我們將會把車輛前方的障礙物給辨識出來,包括行人、機車腳踏車及車輛。
在本篇論文裡,我們採用電腦視覺來實作,因為它跟其他的偵測方式比較起來有較大的偵測範圍及較佳的環境容忍度。障礙物大概位置的偵測:對於行人及機車腳踏車,我們採用一個簡化的立體視覺比對方法;對於車輛,則採用車輛較暗的底下部份Sign Pattern [9]來快速偵測車輛的大約之位置。
對於不同的障礙物,我們依據它們不同的外觀特性採用不的比對及確認的方式,對於行人及機車腳踏車我們採用M-Estimation based Hausdorff distance來做模板的比對以解決它們外型上的變動性,對於行人我們更採用一模板投票程序,藉由其我們可以把模板比對的次數降到最低。對於車輛,我們則利用一些啟發性的方式來確認是否為車輛。在擷取分析出影像中障礙物之後,它們的位置及色彩資訊將會被儲存下來用以做為以後追蹤之用。
在一些駕駛人可能因為疏忽而導致危險情況發生的狀況下,本系統可以增進駕駛人及行人的安全。
Applying computer technology to vehicle driving has been studied for many years. There are many university labs, governmental organizations, and private companies in the world which have spent a lot of efforts on the so-called ITS (Intelligent Transportation System) by developing hardware and software technologies for utilizing various traffic resources more efficiently and for increasing more safety for drivers as well as pedestrians. In this research field, obstacle detection plays an important role in assisting drivers with warning mechanism when some dangerous situations may happen. In this paper, we propose a fast method for detecting and tracking bikes, pedestrians, and vehicles in front of a moving vehicle.
In order to detect bikes and pedestrians efficiently, we apply a simplified fast stereovision method to estimate their approximate positions. On the other hand, we apply the so-called sign pattern technique to estimate the vehicle positions. After that, different methods are used to classify and confirm different kinds of obstacles for adapting their heterogeneity.
CONTENTSI
LIST OF FIGURESIV
LIST OF TABLESV
ABSTRACTVI
CHAPTER 1 INTRODUCTION1
1.1 MOTIVATION1
1.2 RELATED WORKS2
1.3 OBJECTIVE3
1.4 ORGANIZATION4
CHAPTER 2 PRELIMINARY5
2.1 PROBLEM DEFINITION5
2.2 STEREO VISION6
2.3 COLOR INFORMATION7
2.4 CAMERA CALIBRATION8
2.5 OBSTACLE CONFIRMATION PROCEDURE10
2.5.1 Existence Problem11
2.5.2 Classification Problem11
2.5.3 Location Problem13
2.6 SYSTEM REQUIREMENT15
2.6.1 Detection Range15
2.6.2 Dangerous Area18
2.7 SYSTEM DESCRIPTION20
CHAPTER 3 OBSTACLE DETECTION23
3.1 OVERVIEW23
3.2 FAST BINOCULAR CORRESPONDENCE
- STRUCTURE CLASSIFICATION24
3.2.1 Definition24
3.2.2 Modified Structure Classification25
3.3 POTENTIAL OBSTACLES26
3.3.1 Separation of Road and Objects26
3.3.2 Sparse Depth Map28
3.3.3 Disparity Histogram29
3.4 HAUSDORFF DISTANCE30
3.4.1 Definition30
3.4.2 Variations of the Hausdorff Distance31
3.4.3 Hausdorff Distance Transform32
3.4.4 Hausdorff Distance Base Matching33
3.5 BIKE DETECTION PROCEDURE35
3.6 TEMPLATE VOTING PROCEDURE37
3.6.1 Presumption and Concept37
3.7 PEDESTRIAN DETECTION PROCEDURE45
3.8 VEHICLE DARK UNDERNEATH CHECKING
- SIGN PATTERN49
3.9 VEHICLE DETECTION PROCEDURE50
CHAPTER 4 ENHANCEMENT OF DETECTION EFFICIENCY
BY OBSTACLE TRACKING53
4.1 OVERVIEW53
4.2 COLOR INDEXING53
4.2.1 Definition53
4.2.2 Matching Strategy54
4.3 TRACKING METHODS55
4.4 TRACKING PROCEDURE56
CHAPTER 5 EXPERIMENT60
5.1 ENVIRONMENT DESCRIPTION60
5.2 EXPERIMENT RESULTS62
5.2.1 Zooming Mechanism63
5.2.2 Structure Classification65
5.2.3 M-estimated Hausdorff Distance Matching 68
5.2.4 Template Voting Procedure69
5.2.5 Bike Detection72
5.2.6 Pedestrian Detection73
5.2.7 Vehicle Detection74
5.2.8 Performance Discussion75
CHAPTER 6 CONCLUSION77
REFERENCE79
[1] M. Bertozzi and A. Broggi, "GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection," Image Processing, IEEE Transactions on, Vol. 7 1, Jan. 1998, pp. 62-81.
[2] T. N. Tan, K. D. Baker, and G. D. Sullivan, "Model-independent recovery of object orientations," Robotics and Automation, IEEE Transactions on, Vol. 13 4 , Aug. 1997, pp. 602-606.
[3] T. N. Tan, G. D. Sullivan, and K. D. Baker, "Efficient image gradient-based object localisation and recognition," Computer Vision and Pattern Recognition, 1996. Proceedings CVPR ''96, 1996 IEEE Computer Society Conference on, 1996, pp. 397-402.
[4] D. Willersinn and W. Enkelmann, "Robust obstacle detection and tracking by motion analysis," Intelligent Transportation System, 1997. ITSC ''97, IEEE Conference on, 1997, pp. 717-722.
[5] N. D. Matthews, P. E. An, and C. J. Harris, "Vehicle detection and recognition for autonomous intelligent cruise control," Image, Speech and Intelligent Systems, 1995/6 Research Journal.
[6] http://millemiglia.ce.unipr.it/ARGO/english/techdet/vd.html, Vehicle Detection in ARGO System
[7] A. Broggi, M. Bertozzi, A. Fascioli, and M. Sechi, "Shape-based pedestrian detection," Intelligent Vehicles Symposium, 2000. IV 2000. Proceedings of the IEEE, 2000, pp. 215-220.
[8] Q.-T. Luong, J. Weber, D. Koller, and J. Malik, "An integrated stereo-based approach to automatic vehicle guidance," Computer Vision, 1995. Proceedings, Fifth International Conference on, 1995, pp. 52-57.
[9] H. Mori, N. M. Charkari, and T. Matsushita, "On-line vehicle and pedestrian detections based on sign pattern," Industrial Electronics, IEEE Transactions on, Vol. 41 4, Aug. 1994, pp. 384-391.
[10] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas, and W. v. Seelen, "Walking pedestrian recognition," Intelligent Transportation Systems, IEEE Transactions on, Vol. 1 3 , Sept. 2000, pp. 155-163.
[11] L. Zhao and C. Thorpe, "Stereo- and Neural Network-Based Pedestrian Detection," Intelligent Transportation Systems, IEEE Transactions on , Vol. 1, Sept. 2000, pp. 148 -154.
[12] K. Konolige, "Small Vision System: Hardware and Implementation," Proc. ISSR, Hayama, 1997.
[13] C. Papageorgiou, T. Poggio, "Trainable Pedestrian Detection," Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on, Vol. 4, 1999, pp. 35 -39 vol.4.
[14] A. Mohan, "Object detection in images by components," A.I. Memo 1664, Center for Biological and Computational Learning, M.I.T., Cambridge, MA, 1999.
[15] D. M. Gavrila, and V. Philomin, "Real-time object detection for "smart" vehicles," Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, Vol. 1, 1999, pp. 87 -93 vol.1.
[16] Liu, C.-Y. and L.-C. Fu, "Computer Vision Based Movable Obstacle Detection and Recognition for Vehicle Driving," Department of Computer Science and Information Engineering, National Taiwan University, Master Paper.
[17] U. Franke and I. Kutzbach, "Fast stereo based object detection for Stop&Go traffic," Intelligent Vehicles Symposium, 1996, Proceedings of the 1996 IEEE, 1996, pp. 339-344
[18] J. C. Rojas and J. D. Crisman, "Vehicle detection in color images," Intelligent Transportation System, 1997. ITSC ''97., IEEE Conference on, 1997, pp. 403-408.
[19] J. Yang and A. Waibel, "A real-time face tracker," The Proceedings of the Third IEEE Workshop on Applications of Computer Vision, 1996.
[20] H. Mori, K. Kobayashi, N. Ohtuki, and S. Kotani, "Color impression factor: an image understanding method for outdoor mobile robots," Intelligent Robots and Systems, 1997. IROS ''97, Proceedings of the 1997 IEEE/RSJ International Conference on, Vol. 1, 1997, pp. 380 -387.
[21] J. D. Crisman and C. E. Thorpe, "SCARF: a color vision system that tracks roads and intersections," Robotics and Automation, IEEE Transactions on, Vol. 9 1, Feb. 1993, pp. 49-58.
[22] M. P. Dubuisson and A. K. Jain, ŖD matching of 3D Moving objects in color outdoor scenes," Computer Vision and Pattern Recognition, 1994. Proceedings CVPR ''94, 1994 IEEE Computer Society Conference on, 1994, pp. 887-891.
[23] I. Masaki, "Machine-vision systems for intelligent transportation systems," IEEE Intelligent Systems, Vol. 13 6, Nov.-Dec. 1998, pp. 24 -31.
[24] J. M. Ferryman, S. J. Maybank, and A. D. Worrall, "Visual surveillance for moving vehicles," Visual Surveillance, 1998. Proceedings, 1998 IEEE Workshop on, 1997, pp. 73-80.
[25] D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge, "Comparing images using the Hausdorff distance," Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 15 9, Sept. 1993, pp. 850 -863.
[26] R. Azencott, F. Durbin, and J. Paumard, "Multiscale identification of building in compressed large aerial scenes," in Proc. 13th Int. Conf. Pattern Recognition, Vienna, Austria, Aug. 1996, Vol. 2, pp. 974-978.
[27] M. -P. Dubuisson and A. K. Jain, "A modified Hausdorff distance for object matching," in Proc.12th Int. Conf. Pattern Recognition, Jerusalem, Israel, Oct. 1994, pp.566-568.
[28] Dong-Gyu Sim, Oh-Kyu Kwon, and Rae-Hong Park, "Object matching algorithms using robust Hausdorff distance measures," Image Processing, IEEE Transactions on, Vol. 8 3, March 1999, pp. 425 -429.
[29] M. J. Swain and D. H. Ballard, "Color Indexing," Int. Journal of Computer Vision, 7(1):11-32,1991.
[30] http://www.phy.ntnu.edu.tw/class/demolab/, 台灣師大 物理教學/示範實驗 教室 - 反應時間與行車安全距離
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊