Basic Search / Detailed Display

Author: 葉育書
Yu-shu Yeh
Thesis Title: 用於行動機器人之即時行人的人腿偵測與追蹤技術
Real-time Pedestrian Legs Detection and Tracking Techniques Used for the Autonomous Mobile Robots
Advisor: 范欽雄
Chin-Shyurng Fahn
Committee: 林啟芳
Chi-Fang Lin
駱榮欽
Rong-Chin Lo
古鴻炎
Hung-Yan Gu
Degree: 碩士
Master
Department: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
Thesis Publication Year: 2012
Graduation Academic Year: 100
Language: 英文
Pages: 88
Keywords (in Chinese): 行人偵測行人人腿偵測行人人腿追蹤倒傳遞類神經網路支持向量機粒子濾波器
Keywords (in other languages): Pedestrian detection, pedestrian legs detection, pedestrian legs tracking, Back-Propagation Neural Network, Support Vector Machine, particle filter.
Reference times: Clicks: 356Downloads: 2
Share:
School Collection Retrieve National Library Collection Retrieve Error Report

行人偵測是電腦視覺中的一個重要議題,包含行動機器人、監控系統與行車安全的幾個應用中;尤其是行動機器人的行人偵測。這是一個富有挑戰性的題目,因為部分的行動機器人機身較矮或架設的攝影機擷取角度過低,而無法得到完整的人形影像。本論文提出了一個行人人腿偵測系統來取代整個行人的偵測。我們系統的最終目的是在一個行動機器人所錄製的影片中去偵測與追蹤行人的人腿。我們的系統只使用了一支簡單的攝影機即可完成行人人腿的偵測,且執行速度快、準確率高。
在人腿偵測的程序中,我們結合一些知名的演算法來做影像前處理,並評估了兩種不同分類器的偵測效能,分別為:倒傳遞類神經網路(Back-Propagation Neural Network)和支持向量機(Support Vector Machine);使用此兩種不同的分類器來偵測行人人腿的區域。
在人腿追蹤的程序中,我們利用粒子濾波器(Particle filter)技術來動態追蹤人腿。我們以邊緣及顏色等資訊當作特徵,使在追蹤的過程中盡可能讓背景的影像達到最低。
根據實驗結果顯示, 我們的系統可以快速偵測與追蹤多位行人的人腿;而且,可以在複雜環境下獲得很高的偵測率。我們所提方法的人腿偵測率在室內環境下超過 95%.,而在室外的環境下,仍有91.3%以上的表現;我們實驗了人腿走動的八個方向,平均偵測率能達到90%。 另外, 人腿偵測的效率達到每秒9 到 10 張畫面. 這結果表示,此方法是可行且有效的偵測人腿。


Pedestrian detection is a key issue in computer vision, with several applications including robotics, surveillance and automotive safety, especially in autonomous mobile robots. However, it is difficult to detect pedestrians because the height of some autonomous mobile robots is not tall enough and the angle of the camera on the robot is limited so that it is hard to capture complete image of pedestrian. In this thesis, we propose a pedestrian legs detection system to replace complete pedestrian body detection. The ultimate goal of the system is detecting and tracking pedestrian legs in video sequences recorded by a moving autonomous mobile robot. In the proposed system, we only use single webcam in our practice yet we can achieve fast and accurate detection.
In the procedure of pedestrian legs detection, we combined many well-known methods to do image pre-processing and we evaluate two machine learning methods: back-propagation neural network (BP-NN) and support vector machine (SVM) to detection pedestrian legs.
In the procedure of pedestrian legs tracking, we propose an improved particle filter to dynamically locate a human leg. We further utilize the edge and color information as the features to make the influence of the background as little as possible.
After experiments, our system can quickly detect multi-pedestrian legs. Moreover, high accuracy detection rate can be accomplished even under cluttering backgrounds. The detect rate of pedestrian legs is more than 95.0% in indoor background and still reaches 91.3% in outdoor background. Moreover, the detection rate of eight different type of leg’s direction can also achieve 90%. On the other hand, the detection performance is 9 to 10 frames per second. The results reveal that the proposed method is feasible and efficient for detecting pedestrian legs.

誌謝 v 中文摘要 vi Abstract vii Contents ix List of Figures xi List of Tables xiii Chapter 1 Introduction 1 1.1 Overview 1 1.2 Motivation 2 1.3 System Overview 3 1.4 Thesis organization 5 Chapter 2 Related Works 6 2.1 Reviews of Pedestrian detection 7 2.2 Reviews of object Tracking 8 Chapter 3 Legs Detection 11 3.1 Image preprocessing 13 3.1.1 Grey-level transformation 13 3.1.2 Wavelet transformation 14 3.1.3 Image pyramid 18 3.1.4 Gaussian filter 19 3.1.5 Histogram equalized 20 3.2 Multi-layer perceptron 22 3.2.1 The back-propagation 23 3.2.2 The MLP-based classifier 26 3.3 Support vector machine 27 3.3.1 Linear support vector machine 28 3.3.2 Non-linear support vector machine 32 3.3.3 The SVM-based classifier 35 Chapter 4 Legs Tracking 36 4.1 Object description and finding 36 4.2 The Kalman filter 38 4.3 The particle filter 40 4.4 Our proposed method 47 4.4.1 Object representation 48 4.4.2 Similarity measurement of features 49 4.4.3 Particle filtering 50 Chapter 5 Experimental Results 54 5.1 System Interface Description 55 5.2 Training Data Set 56 5.3 Comparison of two different classifiers for legs detection 57 5.4 The result of legs tracking 64 Chapter 6 Conclusions and Feature Works 67 6.1 Conclusions 67 6.2 Future Works 68 References 69

[1] T. Zhao, “Model-based Segmentation and Tracking of Multiple Humans in Complex Situations,” Ph.D. Dissertation, Computer Science Department, University of Southern California, 2003.

[2] D. M. Gavrila, “Pedestrian Detection from a Moving Vehicle,” in Proceedings of the European Conference on Computer Vision, pp. 37-49, 2000.

[3] N. Bellotto and H. Hu, “Multisensor-based human detection and tracking for mobile service robots,” IEEE Transactions on Systems, Man, and Cybernetics, Part B, Vol.39, No.1, pp. 167-181, 2009.

[4] C. H. Wu, “A Visual Search with Pick-up Balls Robot through Path Planning in Known Environment,” Master Thesis, Department of Computer Science Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2009.

[5] P. Viola, M. Jones, and D. Snow, “Detecting Pedestrians Using Patterns of Motion and Appearance,” in International Journal of Computer Vision, vol. 63, no. 2, pp. 153-161, 2005.

[6] N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” in Proceeding of IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 878-885, 2005.

[7] D.M. Gavrila and S. Munder, “Multi-Cue Pedestrian Detection and Tracking from a Moving Vehicle,” in International Journal of Computer Vision, vol. 73, no. 1, pp. 41-59, 2007.

[8] K. Mikolajczyk, C. Schmid and A. Zisserman, “Human detection based on a probabilistic assembly of robust part detectors,” in Proceedings of the European Conference on Computer Vision, pp. 69-82, 2004.

[9] K. C. Fan, Y. K. Wang, and B. F. Chen, “Introduction of tracking algorithms,” Image and Recognition, vol. 8, No. 4, pp. 17-30, 2002.

[10] G. L. Foresti, C. Micheloni, L. Snidaro, and C. Marchiol, “Face detection for visual surveillance,” in Proceedings of the 12th IEEE International Conference on Image Analysis and Processing, pp.115-120, 2003.

[11] K. H. An, D. H. Yoo, S. U. Jung, and M. J. Chung, “Robust multi-view face tracking,” in Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, pp. 1905-1910, 2005.

[12] K. Y. Wang, “A real-time face tracking and recognition system based on particle filtering and AdaBoosting techniques,” Master Thesis, Department of Computer Science Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2006.

[13] S. Birchfield, “Elliptical head tracking using intensity gradients and color histograms,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 232-237, 1998.

[14] P. Fieguth and D. Terzopoulos. “Color-based tracking of heads and other mobile objects at video frame rates,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 21-27, 1997.

[15] C. Y. Tang, Y. P. Hung, and Z. Chen, “Automatic detection and tracking of human head using an active stereo vision system,” in Proceedings of Asian Conference on Computer Vision, vol. 1, pp. 632-639, 1998.

[16] N. Herodotou, K. N. Plataniotis, and A. N. Venetsanopoulos, “Automatic location and tracking of the facial region in color video sequences,” Signal Processing and Image Communication, pp. 359-388, 1999.

[17] W.S. Lee, H.J. Lee, and J.H. Chung, “Wavelet-based FLD for face recognition,” in Proceedings of the IEEE Midwest Symposium on Circuits and Systems, Lansing MI, pp. 734-737, 2000.

[18] C. Liu and H. Wechsler, “Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition,” IEEE Transactions on Image Processing, vol.11, pp.467- 476, 2002.

[19] 王進德,蕭大全,類神經網路與模糊控制理論入門,全華科技股份有限公司,台北市,民國90年

[20] S. Theodoridis and K. Koutroumbas, Pattern Recognition, 3rd Ed., Elsevier, Academic Press, San Diego, California, 2006.

[21] Z. Tang, Z. Miao, “Fast background subtraction and shadow elimination using improved Gaussian mixture model,” in Proceedings of the IEEE International Workshop on Haptic Audio Visual Environments and their Applications Ottawa, pp. 38-41, 2007.

[22] Y. H. Ching, “Visual tracking for a moving object using optical flow technique,” Master Thesis, Department of Mechanical and Electro- Mechanical Engineering, National Sun Yat Sen University, Kaohsiung, 2003.

[23] G. Welch and G. Bishop, “An introduction to the Kalman filter,” Technical Report TR95-041, Department of Computer Science, University of North Carolina at Chapel Hill, NC, 2004.

[24] S. Caifeng, W. Yucheng, T. Tieniu, and F. Ojardias, “Real time hand tracking by combining particle filtering and mean shift,” in Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 669-674, 2004.

[25] G. Welch and G. Bishop, “An introduction to the Kalman filter,” Technical Report TR95-041, Department of Computer Science, University of North Carolina, Chapel Hill, United States, April 2004.

[26] G. L. Foresti, C. Micheloni, L. Snidaro, and C. Marchiol, “Face detection for visual surveillance,” in Proceedings of the 12th IEEE International Conference on Image Analysis and Processing, Mantova, Italy, pp. 115-120, September 2003.

[27] K. T. Song and W. J. Chen, “Face recognition and tracking for human-robot interaction,” in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Hauge, Netherlands, pp. 2877-2882, Octorber 2004.

[28] M. Montemerlo, S. Thrun, and W. Whittaker, “Conditional particle filters for simultaneous mobile robot localization and people-tracking,” in Proceedings of the IEEE International Conference on Robotics and Automation, vol. 1, pp. 695-701, 2002.

[29] K. Nummiaro, E. Koller-Meier, and L. Van Gool, “An adaptive color-based particle filter,” Image and Vision Computing, vol. 21, no. 1, pp. 99-110, 2003.

[30] M. Mason, Z. Duric, “Using Histograms to Detect and Track Objects in Color Video,” Proceedings of Applied Imagery Pattern Recognition, pp. 154–162, 2001.

QR CODE