Unsual Behavior Analysis and Its Application to Surveillance Systems Yung-Tai Hsu( 許詠泰 ) Jun-Wei Hsieh( 謝君偉 ) Hong-Yuan Mark Liao( 廖弘源 )

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

電腦視覺 Computer and Robot Vision I
Extended Gaussian Images
Laboratoire d'InfoRmatique en Image et Systèmes d'information FRE 2672 CNRS/INSA de Lyon/Université Claude Bernard Lyon 1/Université Lumière Lyon 2/Ecole.
3D Shape Histograms for Similarity Search and Classification in Spatial Databases. Mihael Ankerst,Gabi Kastenmuller, Hans-Peter-Kriegel,Thomas Seidl Univ.
Distinctive Image Features from Scale- Invariant Keypoints Mohammad-Amin Ahantab Technische Universität München, Germany.
Automatic Feature Extraction for Multi-view 3D Face Recognition
Instructor: Mircea Nicolescu Lecture 15 CS 485 / 685 Computer Vision.
Each pixel is 0 or 1, background or foreground Image processing to
3D Skeletons Using Graphics Hardware Jonathan Bilodeau Chris Niski.
Image Segmentation some examples Zhiqiang wang
Instructor: Dr. G. Bebis Reza Amayeh Fall 2005
Parametrizing Triangulated Meshes Chalana Bezawada Kernel Group PRISM 3DK – 3DK – September 15, 2000.
CS485/685 Computer Vision Prof. George Bebis
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
Good quality Fingerprint Image Minutiae Feature Extraction
Math 310 Sections Isometry. Transformations Def A transformation is a map from the plane to itself that takes each point in the plane to exactly.
A Real-Time for Classification of Moving Objects
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Shape Classification Using the Inner-Distance Haibin Ling David W. Jacobs IEEE TRANSACTION ON PATTERN ANAYSIS AND MACHINE INTELLIGENCE FEBRUARY 2007.
E.G.M. PetrakisBinary Image Processing1 Binary Image Analysis Segmentation produces homogenous regions –each region has uniform gray-level –each region.
Junjun Pan 1, Xiaosong Yang 1, Xin Xie 1, Philip Willis 2, Jian J Zhang 1
Digital Image Processing
7.1 Scalars and vectors Scalar: a quantity specified by its magnitude, for example: temperature, time, mass, and density Chapter 7 Vector algebra Vector:
Machine Vision for Robots
2D Shape Matching (and Object Recognition)
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
Digital Image Processing Lecture 20: Representation & Description
CS 551/651 Advanced Computer Graphics Warping and Morphing Spring 2002.
Ajay Kumar, Member, IEEE, and David Zhang, Senior Member, IEEE.
ENT 273 Object Recognition and Feature Detection Hema C.R.
Marching Cubes: A High Resolution 3D Surface Construction Algorithm William E. Lorenson Harvey E. Cline General Electric Company Corporate Research and.
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Warm Up Worksheet .
Digital Image Processing CCS331 Relationships of Pixel 1.
3D polygonal meshes watermarking using normal vector distributions Suk-Hawn Lee, Tae-su Kim, Byung-Ju Kim, Seong-Geun Kwon.
Wenqi Zhu 3D Reconstruction From Multiple Views Based on Scale-Invariant Feature Transform.
A survey of different shape analysis techniques 1 A Survey of Different Shape Analysis Techniques -- Huang Nan.
Fourier Descriptors For Shape Recognition Applied to Tree Leaf Identification By Tyler Karrels.
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
CS654: Digital Image Analysis Lecture 36: Feature Extraction and Analysis.
Rendering Pipeline Fall, D Polygon Rendering Many applications use rendering of 3D polygons with direct illumination.
CSSE463: Image Recognition Day 9 Lab 3 (edges) due Weds, 3:25 pm Lab 3 (edges) due Weds, 3:25 pm Take home quiz due Friday, 4:00 pm. Take home quiz due.
Robotics Chapter 6 – Machine Vision Dr. Amit Goradia.
Course 3 Binary Image Binary Images have only two gray levels: “1” and “0”, i.e., black / white. —— save memory —— fast processing —— many features of.
Chapter 6 Skeleton & Morphological Operation. Image Processing for Pattern Recognition Feature Extraction Acquisition Preprocessing Classification Post.
3D mesh watermarking Wu Dan Introduction Spatial domain (00 EG) Transformed domain (02 EG) K=D-A; (D ii is a degree of vertex v i, A is an.
Morphological Image Processing (Chapter 9) CSC 446 Lecturer: Nada ALZaben.
TRANSFORMATIONS. DEFINITION  A TRANSFORMATION is a change in a figure’s position or size.  An Image is the resulting figure of a translation, rotation,
Dilations A dilation is a transformation that produces an image that is the same shape as the original, but is a different size. A dilation stretches or.
Image Sampling and Quantization
Image Representation and Description – Representation Schemes
Digital Image Processing Lecture 20: Representation & Description
Reflections.
PRESENTED BY Yang Jiao Timo Ahonen, Matti Pietikainen
Reflections.
Date of download: 11/14/2017 Copyright © ASME. All rights reserved.
Warm Up Worksheet .
Y. Davis Geometry Notes Chapter 9.
Transformations Example Draw the line Draw 1 at , ,
Chapter 3 Vectors.
Extract Object Boundaries in Noisy Images
Measurement of abdominal aortic aneurysms with three-dimensional ultrasound imaging: Preliminary report  Daniel F. Leotta, PhD, Marla Paun, BS, Kirk W.
Finding Direction Angles of Vectors
Binary Image processing بهمن 92
Presented by: Chang Jia As for: Pattern Recognition
Mid – Module Assessment Review
Vocabulary transformation reflection preimage rotation
Presentation transcript:

Unsual Behavior Analysis and Its Application to Surveillance Systems Yung-Tai Hsu( 許詠泰 ) Jun-Wei Hsieh( 謝君偉 ) Hong-Yuan Mark Liao( 廖弘源 )

Introduction Deformable Triangulations Skeleton-based Posture Recognition Posture Recognition Using the Centroid Context Experiment Results

Deformable Triangulations P is a posture extracted in binary form by image subtraction(fig.1) B is the set of boundary points along the contour of P(fig.2) Extract some high curvature points from B(fig.3) α(p) is the angle of a point p in B. It can be determined by two specified points p + and p -.(fig.4) fig.1 fig.2 fig.3 fig.4

Deformable Triangulations D min = |B| / 30, D max = |B| / 20 If α is larger than a threshold T α (here we set it at 150), p is selected as a control point. If two candidates, p 1 and p 2 are close to each other, i.e., ||p 1 – p 2 ||<d min, the candidate with smaller α angle is chosen as a control point.

Deformable Triangulations Vi Vj Vk VaVb

Triangulation-based Skeleton Extraction P is decomposed into a set of triangle meshes Ω p Ω p ={T i } i=0,1,2,…,N TP -1 Each triangle mesh T i in Ω p has a centroid C T i H is defined as the head of P and it is the highest node among all the nodes. All the leaf nodes L i correspond to different limbs of P The branching nodes B i are the key points used to decompose P into different body parts, such as the hands, feet, or torso.

Posture Recognition Using a Skeleton Assume S P and S D are two skeletal images extracted from a posture P and D. Assume DT S P is the distance map of S P. The value of a pixel r in DT S P is its shortest distance to all foreground pixels in S P. d(r, q) is the Euclidian distance between r and q. |DT S P | represents the image size of DT S P. S P and S D must be normalized to a unit size and their centers must be set to the origins of DT S P and DT S D.

Posture Recognition Using a Skeleton a)Shows the original posture. b)It is the result of skeleton extraction. c)Shows the resultant distance map based on (b)

Centroid Context-based Description of Postures Assume all postures are normalized to a unit size. We project a sample onto a log-polar coordinate and label each mesh. Use m to represent the number of shells used to quantize the radial axis and use n to represent the number of sectors that we would like to quantize each shell. The total number of bins used to construct the centroid context is m×n. For each centroid r of a triangle mesh of a posture, we construct a vector histogram h r. h r (k) is the number of triangle mesh centroids in the kth bin by considering r as the origin bin k is the kth bin of the log-polar coordinate.

Centroid Context-based Description of Postures Given two histograms h r i (k) and h r j (k), the distance between them can be measured by a normalized intersection:

Centroid Context-based Description of Postures |V P | is the number of elemetns in V P.

Centroid Context-based Description of Postures Give two postures P and Q, the distance between their centroid contexts is measured by: Where w and w are the area ratios of the ith and jth body parts residing in P and Q.

Centroid Context-based Description of Postures

Posture Recognition Using the Skeleton and the Centroid Context T i is the ith normal behavior with the training threshold. q is the query posture. r i,j is the jth key posture of the ith normal behavior with length N.

Experiment Results