In this thesis, we present an automatic and accurate pedestrian segmentation algorithm by incorporating pedestrian shape prior into random walks segmentation from a static image. The Random Walks algorithm requires user-specified labels to produce segmentation with each pixel assigned to a label. This algorithm can provide satisfactory segmentation result with suitable input labeled seeds. Therefore, for taking advantage of this interactive segmentation algorithm, we improve the random walks segmentation algorithm by using prior shape information, which provides appropriate seeds for the pedestrian segmentation from the input image. By using the human shape prior information, we develop a fully automatic pedestrian image segmentation algorithm. The experimental results demonstrate improved segmentation results on some real images by using the proposed algorithm.

Contents
Chapter 1 Introduction 3
1.1 Problem Description and Motivation 6
1.2 Image Segmentation 6
1.3 Human Segmentation 8
1.4 Main Contribution 9
1.5 Thesis Organization 9
Chapter 2 Previous Works 11
Chapter 3 Proposed Method 16
3.1 System overview 16
3.2 Pedestrian Data 17
3.3 Shape Prior Model 18
3.4 Generative Model for Pedestrian Segmentation 20
3.4.1 Graphical Model 20
3.4.2 Edge Weights 21
3.4.3 Likelihood Estimation 22
3.4.4 Convex Optimization 25
3.4.5 Prior Model Decision 28
3.5 Human Detection and Refinement 29
3.6 Seeds Initialization 31
Chapter 4 Experimental results 32
4.1 Affinity Propagation Clustering 33
4.2 Human Detection 34
4.3 Pedestrian location refinement 35
4.4 Pedestrian segmentation performance 36
4.4.1 Results on MIT Pedestrian Set 37
4.4.2 Results on INRIA Dataset 39
4.4.3 Results on ViSOR Video 41
4.5 Results on multi-human segmentation 43
4.6 Parameter Setting 44
Chapter 5 Conclusion 45
Reference 46

References
[1] C.-F. Juan, C.-M. Chang, J.-R. Wu, and D. Lee, “Computer vision based human body segmentation and posture estimation,” IEEE Trans. Syst., Man, Cybern. A, Syst., Humans, vol. 39, no. 1, pp. 119–133, Jan. 2009.
[2] R. Cucchiara, C. Grana, A. Prati, and R. Vezzani, “Probabilities posture classification for human-behavior analysis,” IEEE Trans. Syst., Man, Cybern. A, Syst., Humans, vol. 35, no. 1, pp. 42–54, Jan. 2005.
[3] J. Shi and J. Malik, “Normalized cuts and image segmentation,” IEEE Trans. on PAMI, 22(8):888–905, 2000.
[4] D. Comaniciu and P. Meer, “Mean shift: A robust approach toward feature space analysis,” IEEE Trans. on PAMI, 24:603–619, 2002.
[5] D. Martin, C. Fowlkes, and J. Malik, “Learning to detect natural image boundaries using local brightness, color, and texture cues,” IEEE Trans. on PAMI, 26(5):530–549, 2004.
[6] Y. Boykov and M.-P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images,” In ICCV, 2001.
[7] X. Bai and G. Sapiro, “A geodesic framework for fast interactive image and video segemntation and matting,” In ICCV, 2007.
[8] L. Grady, “Random walks for image segmentation,” PAMI, 28(11):1768–1783, 2006.
[9] T. H. Kim, K. M. Lee and S. U. Lee, “Nonparametric Higher-Order Learning for Interactive Segmentation, ” In CVPR, 2010.
[10] Inmar E. Givoni and Brendan J. Frey, “A Binary Variable Model for Affinity Propagation,” Neural Computation, Vol. 21, issue 6, pp 1589-1600, June 2009.
[11] S. Maji, Alexander C. Berg, J. Malik, “Classification using Intersection Kernel SVMs is Efficient,” In CVPR, 2008.
[12] Shapiro, Linda G.; Stockman, George C. Computer Vision. Upper Saddle River, NJ: Prentice Hall. ISBN 0130307963, 2001.
[13] C. Carson, P. H. Torr, H. Greenspan, and J. Malik, “Blob world: Image Segmentation Using EM and Its Application to Image Querying,” IEEE Trans. PAMI, 24(8): 1026-1038, 2002.
[14] Olsen, O. and Nielsen, M. ”Multi-scale gradient magnitude watershed segmentation,” Proc. of ICIAP 97, Florence, Italy, Lecture Notes in Computer Science, pages 6–13. Springer Verlag, September 1997.
[15] S. Osher and N. Paragios. “Geometric Level Set Methods in Imaging Vision and Graphics, “Springer Verlag, ISBN 0387954880, 2003.
[16] Y. Boykov and M.-P. Jolly, “Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images,” In ICCV, 2001.
[17] C. Rother, V. Kolmogorov, and A. Blake, “Grabcut-interactive foreground extraction using iterated graph cuts,” In SIGGRAPH, 2004.
[18] A. Criminisi, T. Sharp, and A. Blake, “GeoS: Geodesic image segmentation,” In ECCV, 2008.
[19] T. H. Kim, K. M. Lee, and S. U. Lee, “Nonparametric Higher-Order Learning for Interactive Segmentation,” In CVPR, 2010.
[20] Z. Lin, and L.S. Davis, “Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching,” IEEE Trans. PAMI, 32(4): 0162-8828, 2010.
[21] Z. Lin, L.S. Davis, D. Doermann, and D. DeMenthon, “Hierarchical Part-Template Matching for Human Detection and Segmentation,” Proc. IEEE ICCV, pp. 1-8, 2007.
[22] W. Gao, H. Ai, and S. Lao, “Adaptive Contour Features in Oriented Granular Space for Human Detection and Segmentation,” In CVPR, 2009.
[23] P. Viola, M. Jones, and D. Snow, “Detecting pedestrians using pattern of motion and appearance,” In ICCV, 2003.
[24] R. Schapire and Y. Singer, “Improved boosting algorithms using confidence-rated predictions,” Machine Learning, 37: 0885-6125, 2004.
[25] Z. Lin, L. S. Davis, D. Doermann, and D. DeMenthon, “An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans,” In ICCV, 2007.
[26] L. Zhao and L. S. Davis, “Iterative Figure-Ground Discrimination,” In ICPR, 2004.
[27] R. Courant and D. Hilbert, “Methods of Math. Physics,” vol. 2. John Wiley and Sons, 1989.
[28] R. Merris, Laplacian matrices of graphs: A survey. Linear Algebra and its Applications, 197, 198:143–176, 1994.
[29] MIT-CBCL Pedestrian Dataset http://cbcl.mit.edu/cbcl/software-datasets/ PedestrianData .html.
[30] INRIA Person Dataset, http://pascal.inrialpes.fr/data/human/.
[31] ViSOR Video Surveillance Online Repository, http://www.openvisor.org/.
[32] USC Pedestrian Detection Test Set, http://iris.usc.edu/Vision-Users/OldUsers/ bowu/ DatasetWebpage/dataset.html.
[33] Affinity Propagation Clustering, http://www.psi.toronto.edu/index.php?q= affinity%20propagation.
[34] J. Shotton, J. Winn, C. Rother, and A. Criminisi, “TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation,” in ECCV 2006.
[35] B. Wu and R. Nevatia, “Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier,” in CVPR 2007.