Title page for 100522085


[Back to Results | New Search]

Student Number 100522085
Author Yu-Ying Yang (楊鈺瀅)
Author's Email Address No Public.
Statistics This thesis had been viewed 279 times. Download 17 times.
Department Department of Computer Science & Information Engineering
Year 2012
Semester 2
Degree Master
Type of Document Master's Thesis
Language zh-TW.Big5 Chinese
Title Automatic Region of Interest Segmentation and Trajectory analysis in Far Distance Traffic Surveillance
Date of Defense 2013-06-21
Page Count 80
Keyword
  • Trajectory Clustering
  • Trajectory reconstruction
  • transaction exposure
  • Abstract For traffic safety and efficiency, the surveillance system based on image analysis has become popular research project in recent years. Intelligent surveillance system using pattern recognition and image processing technologies have been developed and improved intensively in this decade. In the thesis, we propose a method to automatically segment the regions of interest in the surveillance videos via analysis of vehicle trajectories. The system aims at dealing with wide-range surveillance, which is an important complement to ground-plane surveillance. The traffic scenes in experimental videos are taken from high buildings. Therefore, the vehicles in the scene are not stereoscopic. The pedestrians are just like black spots, and there are many noises in the scenes.
    First, we do inter-frame differencing and dilation to get the motion region. Then, we perform tracking using the ORB feature, HOG and the color histogram in the motion region. And the tracking results are stored as the trajectories. Afterwards, we use spectral method to automatically determine the number of clusters, and use K-means with modified Hausdorff distance to cluster the trajectories. Then the clusters are segmented with the orientations of trajectories. Assuming that most of vehicles move along the lanes, and lane changing seldom appears. We apply the point rotation and projection to get the valley in the distribution range of each cluster. The position of valley implies the position of lane. After the segmentation of lanes, we merge the overlapping cluster. Finally, to get the correct road map, we do connection with neighbor cluster and orientation. We conduct experiments with different challenging surveillance scenes to validate the proposed method.
    Table of Content 摘要  i
    ABSTRACT  ii
    目錄  iii
    圖目錄  v
    表目錄  viii
    第一章 緒論  1
    1.1 研究動機  1
    1.2 文獻探討  2
    1.3 系統流程  6
    1.4 論文架構  7
    第二章 追蹤  8
    2.1 特徵  8
    2.1.1 Oriented FAST and Rotated BRIEF (ORB)  8
    2.1.2 Histograms of oriented gradients (HOG)  11
    2.1.3 Color Histogram  12
    2.2 追蹤  12
    第三章 軌跡分群及主要道路分析  16
    3.1 群聚  16
    3.1.1 距離度量  16
    3.1.2 相似性度量  17
    3.1.3 群聚方法  18
    3.2 群集分割  22
    3.2.1 Segmentation with Orientation  23
    3.2.2 Segmentation with Projection  25
    3.2.3 Cluster Merging  30
    3.3 群集連接  32
    3.3.1 Cluster Connection with Neighbor  32
    3.3.2 Route Connection with Neighbor  36
    第四章 實驗結果  38
    4.1 實驗場景  38
    4.2 實驗結果及數據分析  44
    4.2.1 追蹤  44
    4.2.2 Clustering  45
    4.2.3 Analysis  48
    4.2.4評估指標  54
    4.2.3結果評估 - 感興趣區域(Region of Interest)  55
    4.2.4結果評估 - 路線  57
    第五章 結論與未來工作  62
    參考文獻  63
    Reference [1]  S. Atev, G. Miller, and N. Papanikolopoulos, “Clustering of Vehicle Trajectories,” IEEE Transactions on Intelligent Transportation Systems, 11(3):647–657, Sept. 2010.
    [2]  D. Hamad, P. Biela, “Introduction to Spectral Clustering," Information and Communication Technologies: From Theory to Application, 3rd International Conference on. IEEE, pp. 1-6, April 2008.
    [3]  Andrew Y. Ng, Michael I. Jordan, Yair Weiss, “On Spectral Clustering: Analysis and an Algorithm,” Advances in Neural Information Processing Systems, 849-856, 2001.
    [4]  Lihi Zelnik-manor, Pietro Perona, “Self-Tuning Spectral Clustering,” Advances in Neural Information Processing Systems 17, 1601-1608, 2004.
    [5]  Brendan Tran Morris , Mohan Trivedi, “Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(11):2287-2301, Nov. 2011.
    [6]  Weiming Hu, Dan Xie, and Tieniu Tan, “A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories,” IEEE Transactions on Neural Networks, 15(1):135-144, Jan. 2004.
    [7]  Brendan Morris , Mohan Trivedi, “Unsupervised Learning of Motion Patterns of Rear Surrounding Vehicles,” IEEE Transactions on Vehicular Electronics and Safety, 80-85, Nov. 2009.
    [8]  Weiming Hu, Dan Xie, Tieniu Tan, and Steve Maybank, “Learning Activity Patterns Using Fuzzy Self-Organizing Neural Network,” IEEE Transactions on System, Man, and Cybernetics, 34(3):1618-1626, June 2004.
    [9]  Weiming Hu , Xuejuan Xiao , Zhouyu Fu , Dan Xie , Tieniu Tan , Steve Maybank, “A System for Learning Statistical Motion Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(9):1450-1464, Sept. 2006.
    [10]  Brendan Tran Morris, Mohan Manubhai Trivedi, “Learning, Modeling, and Classification of Vehicle Track Patterns from Live Video,” IEEE Transactions on Intelligent Transportation Systems, 9(3):425-437, Sept. 2008.
    [11]  Chris Stauffer , W. Eric L. Grimson, “Learning Patterns of Activity Using Real-Time Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):747-757, Aug. 2000.
    [12]  Zhouyu Fu, Weiming Hu, Tieniu Tan, “Similarity-Based Vehicle Trajectory Clustering and Anomaly Detection,” IEEE International Conference on Image Processing, 2:602-605, Sept. 2005.
    [13]  Imran N. Junejo, Omar Javed and Mubarak Shah, “Multi feature path modeling for video surveillance,” Proceedings of the 17th International Conference on Pattern Recognition, 2:716-719, Aug. 2004.
    [14]  Brendan T. Morris and Mohan M. Trivedi, “Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis,” IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance, 154-161, Sept. 2008.
    [15]  Eran Swears, Anthony Hoogs and A.G. Amitha Perera, “Learning Motion Patterns in Surveillance Video Using HMM Clustering,” IEEE Workshop on Motion and video Computing, 1-8, Jan. 2008.
    [16]  C. Piciarelli , G. L. Foresti, “On-line Trajectory Clustering for Anomalous Events Detection,” Proceedings of the Pattern Recognition, 1835-1842, Nov. 2006.
    [17]  Fatih Porikli, “Learning Object Trajectory Patterns by Spectral Clustering,” IEEE International Conference on Multimedia and Expo, 2:1171-1174, June 2004.
    [18]  Brendan Morris and Mohan Trivedi, “Learning Trajectory Patterns by Clustering: Experimental Studies and Comparative Evaluation,” IEEE Conference on Computer Vision and Pattern Recognition, 312-319, June 2009.
    [19]  Brendan Tran Morris and Mohan Manubhai Trivedi, “A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance,” IEEE Transactions on Circuits and Systems for Video Technology, 18(8):1114-1127, Aug. 2008.
    [20]  Zhang Zhang, Kaiqi Huang, Tieniu Tan, “Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scenes,” Proceedings of the 17th International Conference on Pattern Recognition, 3:1135-1138, Aug. 2006.
    [21]  Marie-Pierre Dubuisson and Anil K. Jain, “A Modified Hausdorff Distance for Object Matching,” Proceedings of the 12th IAPR International Conference on Computer Vision & Image Processing, 1:566-568, Oct. 1994.
    [22]  Daniel P. Huttenlocher, Gregory A. Klanderman, and William J. Rucklidge, “Comparing Images Using the Hausdorff Distance,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):850-863, Sep. 1993.
    [23]  Jiangung Lou, Qifeng Liu, Tieniu Tan and Weirning Hu,”Semantic Interpretation of Object Activities in a Surveillance System,” Proceedings of the 16th International Conference on Pattern Recognition, 3:777-780, 2002.
    [24]  Stefan Atev, Osama Masoud, and Nikos Papanikolopoulos, “Learning Traffic Patterns at Intersections by Spectral Clustering of Motion Trajectories,” IEEE/RSJ International Conference on Intelligent Robots and Systems, 4851-4856 Oct. 2006.
    [25]  Yuanfeng Yang, Zhiming Cui, Jian Wu, Guangming Zhang, Xuefeng Xian, “Trajectory Analysis Using Spectral Clustering and Sequence Pattern Mining,” Journal of Computational Information Systems, 8(6):2637-2645, March 2012.
    [26]  Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski, “ORB: an efficient alternative to SIFT or SURF,” IEEE International Conference on Computer Vision, 2564-2571, Nov. 2011.
    [27]  Herbert Bay, Tinne Tuytelaars, Luc Van Gool, “SURF: Speeded Up Robust Features,” Journal of Computer Vision and Image Understanding, 110(3):346-359, June 2008.
    [28]  Michael Calonder, Vincent Lepetit, Pascal Fua, “BRIEF: Binary Robust Independent Elementary Features,” Proceedings of the 11th European conference on Computer vision, 778-792, 2010.
    [29]  Chris Harris , Mike Stephens, “A Combined Corner and Edge Detector,” Proceedings of the Fourth Alvey Vision Conference, 147-151, 1988.
    [30]  Paul L. Rosin, “Measuring Corner Properties,” Journal of Computer Vision and Image Understanding, 73(2):291-307, Feb. 1999.
    [31]  Edward Rosten , Tom Drummond, “Machine Learning for High-Speed Corner Detection,” Proceedings of the 9th European conference on Computer Vision, 430-443, 2006.
    [32]  Marius Muja and David G. Lowe, “Fast Matching of Binary Features,” Proceedings of the Ninth Conference on Computer and Robot Vision, 404-410, 2012
    [33]  Marina Meila, “Comparing clusterings--an information based distance,” Journal of Multivariate Analysis, 98(5):873-895, 2007.
    [34]  Ondrej Miksik, Krystian Mikolajczyk, “Evaluation of Local Detectors and Descriptors for Fast Feature Matching,” International Conference on Pattern Recognition, 2681-2684, Nov. 2012.
    [35]  Navneet Dalal and Bill Triggs, “Histograms of Oriented Gradients for Human Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:886-893, June 2005.
    [36]  Stefan Emilov Atev, Using Asymmetry in the Spectral Clustering of Trajectories, University of Minnesota Minneapolis, USA, 2011.
    [37]  Jia Wen, Chao Li, Zhang Xiong, “Behavior pattern extraction by trajectory analysis,” Journal of Frontiers of Computer Science in China, 5(1):37-44, March 2011.
    [38]  Tianzhu Zhang, Hanqing Lu, Stan Z. Li, “Learning Semantic Scene Models by Object Classification and Trajectory Clustering,” IEEE Conference on Computer Vision and Pattern Recognition, 1940-1947, June 2009.
    [39]  Nadeem Anjum and Andrea Cavallaro, “Multifeature Object Trajectory Clustering for Video Analysis,” IEEE Transactions on Circuits and Systems for Video Technology, 18(11):1555-1564, Nov. 2008.
    [40]  Ko-Cheung Hui and Wan-Chi Siu, “Extended Analysis of Motion-Compensated Frame Difference for Block-Based Motion Prediction Error,” IEEE Conference on Image Processing, 1232-1245, 2007.
    Advisor
  • Hsu-Yung Cheng(鄭旭詠)
  • Files Link new system User-defined authorizations: 2016-07-15
    Date of Submission 2013-06-28

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have dissertation-related questions, please contact with the NCU library extension service section.
    Our service phone is (03)422-7151 Ext. 57407,E-mail is also welcomed.