跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/01 20:01
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

我願授權國圖
: 
twitterline
研究生:宋昭蓉
研究生(外文):Chao-Jung Song
論文名稱:循序權重取樣粒子濾波法實現全方位相機之多目標物影像追蹤
論文名稱(外文):Human Tracking Using Sequential Importance Sampling Particle Filter by Omnidirectional Camera
指導教授:傅立成傅立成引用關係
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電機工程學研究所
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:2007
畢業學年度:95
語文別:英文
論文頁數:73
中文關鍵詞:影像追蹤多目標物追蹤全方位攝影機粒子濾波器
外文關鍵詞:Visual TrackingHuman TrackingOmnidirectional CameraParticle Filter
相關次數:
  • 被引用被引用:2
  • 點閱點閱:268
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在電腦視覺與機器人領域中,影像追蹤是一個很重要的議題。全方位攝影機提供了較寬廣的視野,但是利用全方位攝影機進行影像追蹤,必須克服變形及低解析度的問題。這篇論文利用循序權重取樣粒子濾波器(Sequential Importance Sampling Particle Filter)提出了一個使用全方位攝影機追蹤多目標物的方法,為了快速偵測到目標物的分布,我們提出以前景偵測為基礎的權重取樣演算法(Foreground-Based Importance Sampling Mechanism),使粒子能快速有效的散佈在目標物附近,此外融合顏色與輪廓的資訊估測影像相似度(Likelihood Measurement),此方法可以更準確追蹤目標物,並藉由整合兩個空間的影像相似度增強系統的穩定性,克服全方位攝影機造成的變形問題。最後,透過實驗來驗證此系統整體的效能及可靠性。
Visual tracking is an important topic in computer vision and robotics fields. The omnidirectional cameras provide a wider filed of view, but tracking with an omnidirectional camera must overcome the warping and low resolution drawback. This thesis presents an approach based on the sequential importance sampling particle filter framework to track multiple humans using an omnidirectional camera. In order to efficiently converge to the target distribution, a foreground-based importance sampling mechanism using foreground segmentation algorithm is proposed to draw particles from currently observed image. The fusion of color and contour features to evaluate the likelihood measurement makes human tracking more accurate. Likelihood evaluation by integrating two-space enhances the robustness of the system to the warping effect. The overall performance is validated using several videos in the experiments.
摘要………………………………………………………………………………………………………… I
ABSTRACT…………………………………………………………………………………………… III
TABLE OF CONTENTS……………………………………………………………………………….. V
LIST OF FIGURES…………………………………………………………………………………… VII
LIST OF TABLE……………………………………………………………………………………….. IX
CHAPTER 1 INTRODUCTION……………………………………………………………………… 1
1.1 MOTIVATION 1
1.2 RELATED WORKS 1
1.3 SYSTEM OVERVIEW 8
1.4 THESE ORGANIZATION 9
CHAPTER 2 PRELIMINARIES…………………………………………………………………….. 11
2.1 OMNIDIRECTIONAL CAMERA 11
2.1.1 Omnidirectional Camera Type 11
2.1.2 Omnidirectional Camera Property 12
2.2 BAYESIAN FILTER 13
2.2.1 Bayes’ Theorem 14
2.2.2 Generic Stochastic Filter from Bayesian Perspective 15
2.3 PARTICLE FILTER 17
2.4 SEQUENTIAL IMPORTANCE SAMPLING(SIS)PARTICLE FILTER 19
2.5 SAMPLES CLUSTERING 21
CHAPTER 3 FOREGROUND-BASED IMPORTANCE SAMPLING MECHANISM…………. 25
3.1 PROBLEM DESCRIPTION 26
3.2 SINGLE HUMAN TRACKING FRAMEWORK 27
3.3 MULTIPLE HUMAN TRACKING FRAMEWORK 30
3.4 DATA-DRIVEN MECHANISM 32
3.4.1 Foreground Segmentation 34
3.4.2 Sampling Distribution 37
CHAPTER 4 MULTIPLE CUE FUSION…………………………………………………………… 42
4.1 CONTOUR LIKELIHOOD 43
4.1.1 Implementation of Contour Likelihood 47
4.2 COLOR LIKELIHOOD 48
CHAPTER 5 TWO-SPACE INTEGRATION………………………………………………………. 50
5.1 TWO-SPACE DESCRIPTION 50
5.2 COLOR AND CONTOUR PROPERTIES ON TWO-SPACE 51
5.3 LOCAL UNWARPING TRANSFORMATION 52
5.4 LIKELIHOOD EVALUATION REDEFINE 56
CHAPTER 6 EXPERIMENT RESULTS…………………………………………………………… 58
6.1 ENVIRONMENT DESCRIPTION 58
6.2 TRACKING RESULTS 61
6.2.1 Color Likelihood 61
6.2.2 Contour Likelihood 63
6.2.3 Color and Contour Likelihood 64
6.2.4 Two-Space Integration 66
CHAPTER 7 CONCLUSION………………………………………………………………………... 70
7.1 CONCLUSION 69
REFERENCES………………………………………………………………………………………….. 72
[1]Y. Yagi, K. Imai, K. Tsuji, and M. Yachida, "Iconic memory-based omnidirectional route panorama navigation," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 27, pp. 78-87, 2005.
[2]F. Wallhoff, M. Zobl, G. Rigoll, and I. Potucek, "Face tracking in meeting room scenarios using omnidirectional views," in Proceedings of the 17th International Conference on Pattern Recognitio, 2004, pp. 933-936.
[3]T. E. Boult, R. J. Micheals, G. Xiang, and M. Eckmann, "Into the woods: visual surveillance of noncooperative and camouflaged targets in complex outdoor settings," Proceedings of the IEEE, vol. 89, pp. 1382-1402, 2001.
[4]K. Ikeuchi, M. Sakauchi, H. Kawasaki, and I. Sato, "Constructing Virtual Cities by Using Panoramic Images " International Journal of Computer Vision, 2004.
[5]G. Scotti, L. Marcenaro, C. Coelho, F. Selvaggi, and C. S. Regazzoni, "Dual camera intelligent sensor for high definition 360 degrees surveillance," Vision, Image and Signal Processing, IEE Proceedings-, vol. 152, pp. 250-257, 2005.
[6]G. Scotti, L. Marcenaro, C. Coelho, F. Selvaggi, and C. S. Regazzoni, "A novel dual camera intelligent sensor for high definition 360 degrees surveillance," 2004, pp. 26-30.
[7]Y. Yagi and M. Yachida, "Omnidirectional sensing for human interaction," in Proceedings. Third Workshop on Omnidirectional Vision., 2002, pp. 121-127.
[8]M.-L. Wang, C.-C. Huang, and H.-Y. Lin, "An Intelligent Surveillance System Based on an Omnidirectional Vision Sensor," in IEEE Conference on Cybernetics and Intelligent Systems, 2006, pp. 1-6.
[9]A. Matsumura, Y. Iwai, and M. Yachida, "Tracking people by using color information from omnidirectional images," in Proceedings of the 41st SICE Annual Conference, 2002, pp. 1772-1777.
[10]J. Ortegon-Aguilar and E. Bayro-Corrochano, "Omnidirectional Vision Tracking with Particle Filter," in 18th International Conference on Pattern Recognition, 2006, pp. 1115-1118.
[11]G. Cielniak, M. Miladinovic, D. Hammarin, L. Goranson, A. Lilienthal, and T. Duckett, "Appearance-based tracking of persons with an omnidirectional vision sensor," in Omnivis Workshop with ECCV: Omnidirectional Vision and Camera Networks, 2003.
[12]C. Cauchois, F. de Chaumont, B. Marhic, L. Delahoche, and M. Delafosse, "Robotic assistance: an automatic wheelchair tracking and following functionality by omnidirectional vision," in IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2005), 2005, pp. 2560-2565.
[13]Z. Chen, "Bayesian filtering: From kalman filters to particle filters, and beyond," on line: http://soma.crl.mcmaster.ca/#zhechen/homepage.htm, 2003.
[14]R. T. Bayes, "Essay toward solving a problem in the doctrine of chances," Philosophical Transactions of the Royal Society London, vol. 53, 1763.
[15]S. Ghahramani, Fundamentals of Probability, 2 ed: Prentice-Hall, Inc., 2000.
[16]F. Daum, "Nonlinear filters: beyond the Kalman filter," Aerospace and Electronic Systems Magazine, IEEE, vol. 20, pp. 57-69, 2005.
[17]M. Isard and A. Blake, "CONDENSATION - Conditional density propagation for visual tracking," International Journal of Computer Vision, vol. 29, 1998.
[18]J. Carpenter, P. Clifford, and P. Fearnhead, "Improved particle filter for nonlinear problems," Radar, Sonar and Navigation, IEE Proceedings -, vol. 146, pp. 2-7, 1999.
[19]Y. Boers and J. N. Driessen, "Interacting multiple model particle filter," Radar, Sonar and Navigation, IEE Proceedings -, vol. 150, pp. 344-349, 2003.
[20]M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," Signal Processing, IEEE Transactions on [see also Acoustics, Speech, and Signal Processing, IEEE Transactions on], vol. 50, pp. 174-188, 2002.
[21]S. Theodoridis and K. Koutroumbas, Sequential Clustering Algorithm: Pattern Recognition, 2003.
[22]R. Adams and L. Bischof, "Seeded region growing," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 16, pp. 641-647, 1994.
[23]S.-S. Huang, "Segmentation and Pose Estimation,Ph.D Thesis," 2007.
[24]"http://www.intel.com/technology/computing/opencv/."
[25]"http://www.eerise.com.tw/cpy.htm."
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top