簡易檢索 / 詳目顯示

回結果列表
研究生： 黃克臻
Huang, Ke-Chen
論文名稱： 立體影像行人定位系統
Pedestrian Localization System via Stereo Vision Video
指導教授： 王大中
Wang, Ta-Chung
學位類別： 碩士
Master
系所名稱： 工學院 - 民航研究所
Institute of Civil Aviation
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 78
中文關鍵詞： 行人偵測 、距離量測 、立體視覺
外文關鍵詞： Pedestrian detection, Distance measurement, Stereo Vision.
相關次數： 點閱：103  下載：2 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著快速進步的交通運輸，因疲勞駕駛、喝酒開車或是行車間接聽行動電話導致分心，進而引發與路上行人發生碰撞交通事故時有耳聞。降低駕駛負擔及防撞的方法也愈來愈多。甚至，無人駕駛的技術也有革命性的發展。以上所有的總總不斷凸顯了行人偵測為重要且不可或缺的一環。本論文利用立體視覺來偵測並做行人定位。第一步，先架設在同一水平位置並經校正過後的雙相機系統，並確保兩台相機皆可捕捉到周遭環境。接著將捕捉到的畫面進行切割，依行人距離相機遠近不同，以至於在畫面中出現的範圍區隔出來，不可能出現的範圍便不需進行偵測，藉此可以大幅縮減運算時間。再來利用Support Vector Machine (SVM)支持向量機結合多尺寸的Histogram of Oriented Gradient (HOG)做為行人分類器分類出行人。偵測出的行人將被標記並記錄位置座標，並利用Oriented FAST and Rotated BRIEF (ORB)特徵點演算法來計算出影像中的對應點做立體匹配求得行人與相機的距離訊息。最後搭配權重來計算行人與相機的距離，以減少因匹配錯誤而造成的誤差。本論文的成果可以應用於車輛避撞系統。

    As the rapid development of transportation nowadays, distracting from roads causing pedestrian bumping accidents happened from times to times. New ways of reducing driver’s workload and avoiding collisions are popping up fast. Furthermore, unmanned driving system evolves revolutionary. All of the factors above show that the detection of pedestrians is much more important than ever. This thesis develops a stereo vision system to detect and localize pedestrians. First, a two-camera system is calibrated in order to make sure the alignment of the images took from both cameras. Second, frame segmentation is applied. By segmentation, areas with no pedestrian can be ignored to reduce computational time. Then multi-scale Histogram of Oriented Gradient (HOG) descriptors are extracted to detect pedestrians using Support Vector Machine (SVM) as the classifier. The detected pedestrians are boxed to label their location in the image. The Oriented FAST and Rotated BRIEF (ORB) feature algorithm is then used to estimate the disparity information, which can be used to determine the relative distance between pedestrians and the vehicle. Finally, applying weightings to reduce the errors made by wrong matched points. Several examples are provided to demonstrate that the proposed system could be used to detect pedestrians and have possible applications in traffic collision avoidance systems.

    摘要　I ABSTRACT　II 致謝　III ACKNOWLEDGEMENTS　V TABLE OF CONTENTS　VII LIST OF FIGURES　X LIST OF TABLES　XII NOMENCLATURE　XIII CHAPTER 1 INTRODUCTION　1 1.1 Motivation　1 1.2 Industry System　3 1.3 Literature Review　5 1.4 Outline of This Research　9 CHAPTER 2 COMPUTER VISION　10 2.1 Homogeneous coordinates　11 2.2 Projective Geometry　12 2.3 Camera Coordinate System and Image Coordinate System　15 2.4 Camera Calibration　18 2.5 Stereo Vision　19 2.6 Epipolar Geometry　22 2.7 Fundamental Matrix　24 2.8 Image Rectification　26 CHAPTER 3 PEDESTRIAN DETECTION SYSTEM　29 3.1 Histogram of Oriented Gradient　30 3.1.1 Gradient and Orientation Computation　31 3.1.2 Weighted vote into spatial and orientation cell　32 3.1.3 Normalization and Descriptor Blocks　33 3.1.4 Collect HOGs over detection window　34 3.2 Support Vector Machine　35 3.3 Fast Pedestrian Detection　41 CHAPTER 4 STEREO MATCHING　43 4.1 ORB: Oriented FAST and Rotated BRIEF　44 4.1.1 Oriented FAST key point　45 4.1.2 Rotated BRIEF　47 4.2 Matching the key points　51 4.3 Distance Measurement　52 CHAPTER 5 PROPOSED SYSTEM FRAME　53 5.1 Frame Segmentation　54 5.2 SVM Pedestrian Detection Classifier　57 5.2.1 Pedestrian Dataset 58 5.2.2 Training Step 59 5.2.3 Performance of the Classifier 61 5.3 Modified Distance Measuring System 62 5.4 Pedestrian Localization System 64 CHAPTER 6 EXPERIMENT OF THE SYSTEM 65 6.1 Experiment Hardware 66 6.2 Experiment Setup 68 6.2.1 Choosing System Mounting Place 68 6.2.2 Experiment Environment 69 6.3 Results and Discussion 70 6.3.1 Results Comparison 71 6.3.2 Discussions 72 CHAPTER 7 CONCLUSION AND FUTURE WORK 74 REFERENCES 75

    [1] A. Carullo and M. Parvis. An ultrasonic sensor for distance measurement in automotive applications. IEEE Sensors Journal. 1(2), pp. 143, Aug., 2001.
    [2] J. Wang, F. Gao, S. Shi, and J. Wang, "A New Method for Distance and Relative Velocity Measurement in Vehicle Collision Warning System," in IEEE Sixth International Conference on Intelligent Systems Design and Applications, Jinan, pp. 1142-1147, Oct. 16-18, 2006.
    [3] Wikipedia. Collision Avoidance System, Available: http://en.wikipedia.org/wiki/Collision_avoidance_system
    [4] BMW. BMW 7 series Driver Assistance Systems, Available: http://www.bmw.com/com/en/newvehicles/7series/sedan/2015/showroom/driver_assistance.html
    [5] BMW. BMW Driving Assistant Plus, Available: http://www.bmw.com/com/en/newvehicles/7series/sedan/2015/showroom/driver_assistance.html#drivingassistant
    [6] ARTC. Application of combining vision and radar signals, Available: http://www.artc.org.tw/chinese/03_service/03_02detail.aspx?pid=2461
    [7] ARTC. Combination of sensors and pedestrian detection, Available: http://www.artc.org.tw/chinese/03_service/03_02detail.aspx?pid=2689
    [8] K. C. Ke, "Fast Pedestrian and Motorcycle Detection and Tracking for Embedded Driver Assistance System," NTUT Dept. of Computer Science & Information Engineering, 2014.
    [9] Wikipedia. Pedestrian detection, Available: http://en.wikipedia.org/wiki/Pedestrian_detection#cite_note-1
    [10] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, pp. 886-893, Jun. 25-25, 2005.
    [11] D. M. Gavrila and J. Giebel, "Shape-based pedestrian detection and tracking," in IEEE Intelligent Vehicle Symposium, pp. 8-14, Jun. 17-21, 2002.
    [12] D. M. Gavrila and V. Philomin, "Real-time object detection for "smart" vehicles," in Seventh IEEE International Conference on Computer Vision, pp. 87-93, Sep. 20-27, 1999.
    [13] H. Nanda and L. Davis, "Probabilistic template based pedestrian detection in infrared videos," in IEEE Intelligent Vehicle Symposium, Versailles, France, pp. 15-20, Jun. 17-21, 2002.
    [14] C. Papageorgiou and T. Poggio. A Trainable System for Object Detection. International Journal of Computer Vision. 38(1), pp. 15-33, Jun., 2000.
    [15] P. Viola, M. J. Jones, and D. Snow. Detecting Pedestrians Using Patterns of Motion and Appearance. International Journal of Computer Vision. 63(2), pp. 153-161, Jul., 2005.
    [16] K. Mikolajczyk, C. Schmid, and A. Zisserman, "Human Detection Based on a Probabilistic Assembly of Robust Part Detectors," in Computer Vision - ECCV 2004, T. Pajdla and J. Matas, Eds., ed Berlin, Heidelberg: Springer Berlin Heidelberg, 2004.
    [17] H. Bristow and S. Lucey. Why do linear SVMs trained on HOG features perform so well? arXiv preprint arXiv:1406.2419. pp., Jun., 2014.
    [18] K. A. Rahman, M. S. Hossain, M. A. A. Bhuiyan, T. Zhang, M. Hasanuzzaman, and H. Ueno, "Person to Camera Distance Measurement Based on Eye-Distance," in Third International Conference on Multimedia and Ubiquitous Engineering, Qingdao, pp. 137-141, Jun. 4-6, 2009.
    [19] K. Muljowidodo, M. A. Rasyid, N. SaptoAdi, and A. Budiyono. Vision based distance measurement system using single laser pointer design for underwater vehicle. Indian Journal of Marine Sciences. 38(3), pp. 324-331, Sep., 2009.
    [20] K. Konolige, "Small Vision Systems: Hardware and Implementation," in Robotics Research, P. Y. Shirai and P. S. Hirose, Eds., ed London: Springer London, pp. 203-212, 1998.
    [21] L. Iocchi. (Apr. 6, 1998). Stereo Vision: Triangulation, Available: http://www.dis.uniroma1.it/~iocchi/stereo/triang.html
    [22] A. L. Hou, X. Cui, Y. Geng, W. J. Yuan, and J. Hou, "Measurement of Safe Driving Distance Based on Stereo Vision," in Sixth International Conference on Image and Graphics, pp. 902-907, Aug. 12-15, 2011.
    [23] T. S. Hsu and T. C. Wang. An Improvement Stereo Vision Images Processing for Object Distance Measurement. International Journal of Automation and Smart Technology. 5(2), pp. 85-90, Jun., 2015.
    [24] Y. M. Mustafah, R. Noor, H. Hasbi, and A. W. Azma, "Stereo vision images processing for real-time object distance and size measurements," in Computer and Communication Engineering (ICCCE), Kuala Lumpur, Malaysia, pp. 659-663, Jul. 3-5, 2012.
    [25] J. C. Cheng and S. J. Feng, "A real-time multiresolutional stereo matching algorithm," in IEEE International Conference on Image Processing, pp. III-373-6, Sep., 2005.
    [26] A. Fusiello, V. Roberto, and E. Trucco, "Efficient stereo with multiple windowing," in Computer Vision and Pattern Recognition, San Juan, Puerto Rico, p. 858, Jun 17-19, 1997.
    [27] D. G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision. 60(2), pp. 91-110, 2004.
    [28] E. Rosten and T. Drummond, "Machine Learning for High-Speed Corner Detection," in Computer Vision - ECCV 2006, A. Leonardis, H. Bischof, and A. Pinz, Eds., ed Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 430-443, 2006.
    [29] M. Calonder, V. Lepetit, C. Strecha, and P. Fua, "BRIEF: Binary Robust Independent Elementary Features," in Computer Vision - ECCV 2010, K. Daniilidis, P. Maragos, and N. Paragios, Eds., ed Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 778-792, 2010.
    [30] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in International Conference on Computer Vision, Barcelona, pp. 2564-2571, Nov. 6-13, 2011.
    [31] Y. F. Liao, "Object Geometry Reconstruction by Stereo Image Data," Depart. of Aeronautics and Astronautics, National Cheng Kung University, 2005.
    [32] Y. T. Ho, "Three-Dimensional Target Trajectory Estimation and Interception by Visual Servo Technology," Depart. of Aeronautics and Astronautics, National Cheng Kung University, Jun. 27, 2002.
    [33] R. Tsai. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE Journal on Robotics and Automation. 3(4), pp. 323-344, Aug., 1987.
    [34] Z. Zhang, "Flexible camera calibration by viewing a plane from unknown orientations," in Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, pp. 666-673, Sep. 20-27, 1999.
    [35] G. Xu and Z. Zhang, Epipolar geometry in stereo, motion and object recognition: a unified approach vol. 6: Springer Science & Business Media, 2013.
    [36] Wikipedia. Epipolar geometry, Available: https://en.wikipedia.org/wiki/Epipolar_geometry
    [37] C. Loop and Z. Zhang, "Computing rectifying homographies for stereo vision," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, pp. 1-131, Jun. 23-25, 1999.
    [38] Wikipedia. Image rectification, Available: http://en.wikipedia.org/wiki/Image_rectification
    [39] V. N. Vapnik. An overview of statistical learning theory. IEEE Transactions on Neural Networks. 10(5), pp. 988-999, Sep., 1999.
    [40] Y. S. Abu-Mostafa, "Lecture 14: Support Vector Machines," in Learning From Data, ed. California Institute of Technology, 2012.
    [41] Y. S. Abu-Mostafa, "Lecture 15: Kernel Methods," in Learning From Data, ed. California Institute of Technology, 2012.
    [42] M. Jones and P. Viola, "Fast multi-view face detection," in Proc. of Computer Vision and Pattern Recognition. vol. 3, ed: Mitsubishi Electric Research Lab TR-20003-96 3, p. 14, 2003.
    [43] P. Dollá, S. Belongie, and P. Perona, "The Fastest Pedestrian Detector in the West," in British Machine Vision Conference (BMVC), Aberystwyth, United Kingdom, p. 7, 2010.
    [44] P. L. Rosin. Measuring Corner Properties. Computer Vision and Image Understanding. 73(2), pp. 291-307, Feb., 1999.
    [45] C. C. Chang and C. J. Lin. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST). 2(3), pp. 1-27, Apr., 2011.
    [46] N. Dalal and B. Triggs. INRIA Person Dataset, Available: http://pascal.inrialpes.fr/data/human/

    下載圖示 校內：2018-11-29公開
    校外：2020-11-29公開
    QR CODE