跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.91) 您好!臺灣時間:2025/02/11 19:25
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:徐志明
研究生(外文):Chih-Ming Hsu
論文名稱:在公路監測環境下的事件偵測
論文名稱(外文):Event Detection in Highway Surveillance Environment
指導教授:許秋婷許秋婷引用關係
指導教授(外文):Chiou-Ting Hsu
學位類別:碩士
校院名稱:國立清華大學
系所名稱:資訊工程學系
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:2006
畢業學年度:95
語文別:英文
論文頁數:77
中文關鍵詞:區塊對應兩階段投票車道重建車道跨越事件偵測
外文關鍵詞:blob correspondence matchingtwo-stage votinglane reconstructionlane-crossingevent detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:148
  • 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
  一個自動化的監測系統應該協助使用者尋找他所感興趣的事件。因為在公路監測環境下拍攝的影片存在獨特的性質,使得事件偵測較為容易。因此在此篇論文中,我們提出一個公路監測環境下事件偵測的方法。
首先針對每一個像素以高斯混合模型(GMM)建立背景模型並偵測前景區塊。而物體追蹤的問題即可轉換為區塊對應的問題。我們採納二階段投票的方式進行區塊對應,並修改其中投票機制以符合公路交通影片的特性。並且針對每一組對應的區塊進行阻擋偵測,修正因為前景偵測錯誤所造成的物體對應問題。
 從累積的追蹤資訊可以建立區塊中心統計圖(blob center histogram)來偵測車輛主要行進軌跡。我們將統計圖切割成較小的影像,以霍氏轉換(Hough Transform)找到初始位置,再使用二次最小平方法尋找近似曲線,進而重建車道資訊。有了車道資訊,我們修改原先的阻擋修正方法並且偵測車道跨越事件。實驗結果顯示修改後的阻擋修正方法可以為阻擋物體找到更為精確的最小邊界方塊位置以獲得更正確的追蹤結果。
  An automatic surveillance system should be able to detect events in which users are interested in. Due to the unique characteristics of highway environment, event detection becomes much easier. In this thesis, we propose an approach to detect events in highway surveillance environment.
  First, for each pixel, we adopt GMM to construct background model and detect foreground. Then, we adopt two-stage voting approach for blob matching and modify the voting conditions based on video properties. Besides, we also conduct occlusion detection and correct those occluded blobs caused by segmentation error.
  From accumulative tracking data, blob center histogram is constructed to detect trajectory curves. We divide the histogram into sub-images, use Hough transform to find the initial position, apply second-order least-square for curve approximation, and reconstruct lanes. With lane information, we modify the occlusion correction method and detect lane-crossing event. The experiment results show that the modified occlusion correction method can retrieve more precious minimum bounding box position for the occluded blobs and get better tracking results.
誌謝  i
中文摘要  ii
Abstract  iii
List of Comtents iv
List of Tables and Figures vi

1. INTRODUCTION  1
2. REALATED WORKS 4
2.1 Background Modeling and Foreground Detection  4
2.1.1 Parametric  Model              4
2.1.2 Nonparametric Model              7
2.1.3 Codebook  Model 9
2.2 Blob Correspondence Matching 13
2.2.1 Model-Based 13
2.2.2 Bounding Box-Based 14
2.3 Event Detection 15
2.3.1 Finite State Machine 16
2.3.2 Hidden Markov Model 17
2.3.3 Rule-Based 18
3. PROPOSED METHOD 22
3.1 Foreground Extraction 22
3.2 Blob Correspondence Matching 26
3.2.1 Object Feature Extraction 27
3.2.2 Object Matching 28
3.2.3 Matching Correction 33
3.3 Event Detection 36
3.3.1 Simple Characteristics Calculation 36
3.3.2 Lane-Making Reconstruction 37
3.3.3 Modified Occlusion Correction 42
3.3.4 Lane-Crossing Event Detection 44
4. EXPERIMENTAL RESULTS 54
4.1 Test Data Set 54
4.2 Results of Our Proposed Method 55
4.2.1 Background Modeling and Foreground Detection 55
4.2.2 Blob Correspondence Matching 56
4.2.3 Traffic Lane Reconstruction 58
4.2.4 Modified Occlusion Correction 59
4.2.5 Lane-Crossing Event Detection 60
5. CONCLUSION 70
6. APPENDIX 71
7. REFERENCES 76
[1]C. Stauffer, W.E.L Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, pp. 22-31, 1998.
[2]L. Li, W. Huang, I. Y. Gu and Q. Tian, ”Statistical Modeling of Complex Backgrounds for Foreground Object Detection,” IEEE Trans. Image Processing., vol. 13, no. 11, Nov. 2004.
[3]K. Kim, T.H. Chalidabhongse, D. Harwood, and L. Davis, “Background Modeling and Subtraction by Codebook Construction,” IEEE Conf .Image Processing, pp.3061-3064, Oct. 2004.
[4]C. Beleznai, B.Fruhstuck and H. Bischof, ”Human Detection in Groups Using a Fast Mean Shift Procedure,” IEEE Conf .Image Processing, pp.349-352,Oct. 2004.
[5]T. Zhao, and R. Nevatia, ”Tracking Multiple Humans in Complex Situations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 9, Nov. 2004.
[6]A. Amer, “Voting-Based Simultaneous Tracking of Multiple Video Objects,” IEEE Trans. Circuits and Systems for Video Technology, vol. 15, no. 11, Nov. 2005.
[7]“The Next Generation Simulation (NGSIM) project,”
http://www.ngsim.fhwa.dot.gov/
[8]A. Elgammal, D. Harwood, and L. Davis, “Nonparametric Model for Background Subtraction,” 6th European Conference on Computer Vision, vol. 2, P.751-767, Dublin, Ireland, 2000.
[9]R. Cucchiara, A. Prati, and R. Vezzani, ”An Intelligent Surveillance System for Dangerous Situation Detection in Home Environments,” Intelligenza Artificiale, pp.11-15, vol. 1, no,1, 2004.
[10]W. Lu and Y.P. Tan, ”A Vision-Based Approach to Early Detection of Drowning Incidents in Swimming Pools,” IEEE Trans. Circuits and Systems for Video Technology, pp.159-178, vol.14, no.2, Feb 2004.
[11]P. Kumar, S. Ranganath, H. Weimin, and K. Sengupta, “Framework for Real-Time Behavior Interpretation from Traffic Video,” IEEE Trans. Intelligent Transportation Systems, pp.43-53, vol.6, no.1, March 2005.
[12]Q. Zang, R. Klette, “Robust Background Subtraction and Maintenance,” IEEE Proc. ICPR, 2004.
[13]Z. Zivkovic, “Improved Adaptive Gaussian Mixture Model for Background Subtraction,” IEEE Proc. ICPR, 2004.
[14]Y. Sheikh and M. Shah, “Bayesian Modeling of Dynamic Scenes for Object Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 11, Nov. 2005, pp. 1778-1792.
[15]L. Qin, Y. Zhuang, Y. Pan, and F. Wu, ”Segmenting Layer in Automated Visual Surveillance,” IEEE Proc. ICME, 2005.
[16]C.C.C. Pang, W.W.L. Lam, and N.H.C. Yung, “A Novel Method for Resolving Vehicle Occlusion in a Monocular Traffic-Image Sequence,” IEEE Trans. Intelligent Transportation Systems, pp.129-141, vol.5, no.3, September 2004.
[17]J.H, Hwang, I. Karliga, and H.Y. Cheng, “An Automatic Three-Dimensional Human Behavior Analysis System for Video Surveillance Applications”, IEEE Int.Conf. ISCAS, 2006.
[18]F. Porikli, and X. Li, “Traffic Congestion Estimation Using HMM Models Without Vehicle Tracking,” IEEE Intelligent Vehicles Symposium, pp. 188-193, June 2004.
[19]S. Kamijo, Y. Matsushita, K. Ikeuchi, and M. Sakauchi, “Traffic Monitoring and Accident Detection at intersection,” IEEE Trans. Intelligent Transportation Systems, pp.108-117, vol.1, no.2, June 2000.
[20]Rafael C. Gonzalez, and Richard E. Woods, “Digital Image Processing,” Prentice Hall, 2002.
[21]L. Carminati, and J. Benois-Pineau, “Gaussian Mixture Classification for Moving Object Detection in Video Surveillance Environment,” IEEE Conf .Image Processing, pp.113-116, Sept. 2005.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top