Chamfer Matching & Hausdorff Distance Presented by Ankur Datta Slides Courtesy Mark Bouts Arasanathan Thayananthan.

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints
Advertisements

Shape Context and Chamfer Matching in Cluttered Scenes
A Multi-Resolution Technique for Comparing Images Using the Hausdorff Distance Daniel P. Huttenlocher and William J. Rucklidge Nov Presented by.
Chamfer Distance for Handshape Detection and Recognition CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
Medical Image Registration Kumar Rajamani. Registration Spatial transform that maps points from one image to corresponding points in another image.
Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Document Image Processing
MASKS © 2004 Invitation to 3D vision Lecture 7 Step-by-Step Model Buidling.
Announcements Final Exam May 13th, 8 am (not my idea).
Database-Based Hand Pose Estimation CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
University of Pennsylvania 1 GRASP CIS 580 Machine Perception Fall 2004 Jianbo Shi Object recognition.
Forward-Backward Correlation for Template-Based Tracking Xiao Wang ECE Dept. Clemson University.
Digital Image Processing Lecture 12: Image Topology
Each pixel is 0 or 1, background or foreground Image processing to
1 EFFICIENT BITMAP RESEMBLENCE UNDER TRANSLATION Klara Kedem & Daniel Cohen This presentation will probably involve audience discussion, which will create.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Computer Vision Optical Flow
Comparing Images Using the Hausdorff Distance Mark Bouts 6th April 2006.
Announcements Final Exam May 16 th, 8 am (not my idea). Practice quiz handout 5/8. Review session: think about good times. PS5: For challenge problems,
1 Model Fitting Hao Jiang Computer Science Department Oct 6, 2009.
(1) Feature-point matching by D.J.Duff for CompVis Online: Feature Point Matching Detection,
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
Segmentation Divide the image into segments. Each segment:
Uncalibrated Geometry & Stratification Sastry and Yang
Objective of Computer Vision
Curve Analogies Aaron Hertzmann Nuria Oliver Brain Curless Steven M. Seitz University of Washington Microsoft Research Thirteenth Eurographics.
Computing motion between images
Pores and Ridges: High- Resolution Fingerprint Matching Using Level 3 Features Anil K. Jain Yi Chen Meltem Demirkus.
Announcements Take home quiz given out Thursday 10/23 –Due 10/30.
Fitting a Model to Data Reading: 15.1,
Objective of Computer Vision
Presenter: Stefan Zickler
Optical flow (motion vector) computation Course: Computer Graphics and Image Processing Semester:Fall 2002 Presenter:Nilesh Ghubade
DVMM Lab, Columbia UniversityVideo Event Recognition Video Event Recognition: Multilevel Pyramid Matching Dong Xu and Shih-Fu Chang Digital Video and Multimedia.
VEHICLE NUMBER PLATE RECOGNITION SYSTEM. Information and constraints Character recognition using moments. Character recognition using OCR. Signature.
06 - Boundary Models Overview Edge Tracking Active Contours Conclusion.
Efficient Algorithms for Robust Feature Matching Mount, Netanyahu and Le Moigne November 7, 2000 Presented by Doe-Wan Kim.
1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.
1 TEMPLATE MATCHING  The Goal: Given a set of reference patterns known as TEMPLATES, find to which one an unknown pattern matches best. That is, each.
MESA LAB Multi-view image stitching Guimei Zhang MESA LAB MESA (Mechatronics, Embedded Systems and Automation) LAB School of Engineering, University of.
EFFICIENT ROAD MAPPING VIA INTERACTIVE IMAGE SEGMENTATION Presenter: Alexander Velizhev CMRT’09 ISPRS Workshop O. Barinova, R. Shapovalov, S. Sudakov,
Scientific Writing Abstract Writing. Why ? Most important part of the paper Number of Readers ! Make people read your work. Sell your work. Make your.
Course 13 Curves and Surfaces. Course 13 Curves and Surface Surface Representation Representation Interpolation Approximation Surface Segmentation.
Data Extraction using Image Similarity CIS 601 Image Processing Ajay Kumar Yadav.
Vehicle Segmentation and Tracking From a Low-Angle Off-Axis Camera Neeraj K. Kanhere Committee members Dr. Stanley Birchfield Dr. Robert Schalkoff Dr.
1 Embedding and Similarity Search for Point Sets under Translation Minkyoung Cho and David M. Mount University of Maryland SoCG 2008.
A B C D E F A ABSTRACT A novel, efficient, robust, feature-based algorithm is presented for intramodality and multimodality medical image registration.
Looking at people and Image-based Localisation Roberto Cipolla Department of Engineering Research team
2D Texture Synthesis Instructor: Yizhou Yu. Texture synthesis Goal: increase texture resolution yet keep local texture variation.
Pictorial Structures and Distance Transforms Computer Vision CS 543 / ECE 549 University of Illinois Ian Endres 03/31/11.
Visual Computing Computer Vision 2 INFO410 & INFO350 S2 2015
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
How to tell the differences between a Cat and a Dog Masoud Alipour Ali Farhadi IPM – Scientific Computing Center Vision.
By Pushpita Biswas Under the guidance of Prof. S.Mukhopadhyay and Prof. P.K.Biswas.
Dynamic Programming (DP), Shortest Paths (SP)
Occlusion Tracking Using Logical Models Summary. A Variational Partial Differential Equations based model is used for tracking objects under occlusions.
Image matching using the Hausdorff Distance with CUDA
Chapter 6 Skeleton & Morphological Operation. Image Processing for Pattern Recognition Feature Extraction Acquisition Preprocessing Classification Post.
Tracking Hands with Distance Transforms Dave Bargeron Noah Snavely.
CSCI 631 – Foundations of Computer Vision March 15, 2016 Ashwini Imran Image Stitching.
Lecture 26 Hand Pose Estimation Using a Database of Hand Images
Investigating the Hausdorff Distance
Paper Presentation: Shape and Matching
Vehicle Segmentation and Tracking in the Presence of Occlusions
Image Segmentation Techniques
Kiera Henning, Jiwon Kim,
Paper Reading Dalong Du April.08, 2011.
Comparing Images Using Hausdorff Distance
Image Registration  Mapping of Evolution
Presentation transcript:

Chamfer Matching & Hausdorff Distance Presented by Ankur Datta Slides Courtesy Mark Bouts Arasanathan Thayananthan

Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm (HCMA)

Motivation Matching is a key problem in vision –Edge matching is robust. HCMA is a mid-level features - edges –robust

Types of matching Direct use of pixel –Correlation Use low-level features –Edges or corners High-level matchers –Use identified parts of objects –Relations between features.

HCMA Chamfer Matching - minimize a generalized distance between two sets of edge points. –Parametric transformations HCMA is embedded in a resolution pyramid.

DT : Sequential Algorithm –Start with zero-infinity image : set each edge pixel to 0 and each non-edge pixel to infinity. –Make 2 passes over the image with a mask: 1. Forward, from left to right and top to bottom 2. Backward, from right to left and from bottom to top. Forward Mask Backward Mask d1 and d2, are added to the pixel values in the distance map and the new value of the zero pixel is the minimum of the five sums.

DT Parallel Algorithm For each position of mask on image, V i,j = minimum(v i-1,j-1 +d2,v i-1,j +d1,v i-,j+1 +d2, v i,j-1 +d1,v i,j )

Distance Transform  Distance image gives the distance to the nearest edge at every pixel in the image  Calculated only once for each frame (x,y) d d

Chamfer Matching Edge-model translated over Distance Image. At each translation, edge model superimposed on distance image. Average of distance values that edge model hits gives Chamfer Distance. R.M.S. Chamfer Distance = V i = distance value, n = number of points Chamfer Distance = 1.12

Chamfer Matching  Chamfer score is average nearest distance from template points to image points  Nearest distances are readily obtained from the distance image  Computationally inexpensive

Chamfer Matching  Distance image provides a smooth cost function  Efficient searching techniques can be used to find correct template

Chamfer Matching

Applications: Hand Detection  Initializing a hand model for tracking –Locate the hand in the image –Adapt model parameters –No skin color information used –Hand is open and roughly fronto-parallel

Results: Hand Detection Original Shape Context Shape Context with Continuity Constraint Chamfer Matching

Results: Hand Detection Original Shape Context Shape Context with Continuity Constraint Chamfer Matching

Discussion  Chamfer Matching –Variant to scale and rotation –Sensitive to small shape changes –Need large number of template shapes But –Robust to clutter –Computationally cheap

Comparing Images Using the Hausdorff Distance

Introduction Matching a model to an image. Main topic of the paper: Computing the Hausdorff Distance under translation Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Hausdorff distance set A = {a 1,….,a p } and B = {b 1,….,b q } –Hausdorff distance –Directed Hausdorff distance h(A,B) ranks each point of A based on its nearest point of B and uses the most mismatched point Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Minimal Hausdorff distance Considers the mismatch between all possible relative positions of two sets Matching Criteria: –Minimal Hausdorff Distance M G Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Voronoi surface It is a distance transform It defines the distance from any point x to the nearest of source points of the set A or B Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

How to compute the M T Again the HD definition –We define Interested in the graph of d(x) which gives the distance from any point x to the nearest point in a set of source points in B Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Computing the HD T Can be rewritten as: is the maximum of translated copies of d(x) and d’(x) Define: the upper envelope (pointwise maximum) of p copies of the function d(-t), which have been translated to each other by each Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Comparing Portions of Shapes Extend the case to Finding the best partial distance between a model set B and an image set A Ranking based distance measure K= Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Comparing Portions of Shapes Target is to find the K points of the model set which are closest to the points of the image set. ‘Automatically’ select the K ‘best matching’ points of B –It identifies subsets of the model of size K that minimizes the Hausdorff distance –Don’t need to pre-specify which part of the model is being compared Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Min HD for Grid Points Now we consider the sets A and B to be binary arrays A[k,l] and B[k,l] F[x,y] is small at some translation when every point of the translated model array is near some point of the image array Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Min HD for Grid Points Rasterization introduces a small error compared to the true distance –Claim: F[x,y] differs from f(t) by at most 1 unit of quantization The translation minimizing F[x,y] is not necessarily close to translation of f(t) –So there may be more translation having the same minimum Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Computing HD array F[x,y] can be viewed as the maximization of D’[x,y] shifted by each location where B[k,l] takes a nonzero value Expensive computation! –Constantly computing the new upper envelope Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Computing HD array F[x,y] Probing the Voronoi surface of the image Looks similar to binary correlation –Due to no proximity notion is binary correlation more sensitive to pixel perturbation Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

HD under Rigid motion Extent the transformation set with rotation –Minimum value of the HD under rigid (Euclidean) motion Ensure that each consecutive rotation moves each point by at most 1 pixel –So Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Example translation Imagemodeloverlaid Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples Images Huttenlocher D. Comparing images using the Hausdorff distance

Example Rigid motion Imagemodel overlaid Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples Images Huttenlocher D. Comparing images using the Hausdorff distance

Summary Hausdorff Distance Minimal Hausdorff as a function of translation –Computation using Voronoi surfaces Compared portions of shapes and models The minimal HD for grid points –Computed the distance transform –The minimal HD as a function of translation –Comparing portions of shapes and models The Hausdorff distance under rigid (euclidean) motion Examples Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

END

Hausdorff distance Focus on 2D case Measure the Hausdorff Distance for point sets and not for segments HD is a metric over the set of all closed and bounded sets –Restriction to finite point sets (all that is necessary for raster sensing devices) Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

HD under Rigid motion Computation Limitations –Only from the model B to the image A –Complete shapes Method –For each translation Create an array Q in which each element = –For each point in B »For each rotation we probe the distance transform and maximize it with values already in the array Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Distance Transform DT’s are global transformations. Reduce computational complexity : consider edge-pixels in immediate neighbourhood of edge pixels (local transform). DT at a pixel can be deduced from the values at its neighbors.

Matching portions of shapes Matching portions of the image and a model –Partial distance formulation is not ideal! Consider portion of the image to the model More wise to only consider those points of the image that are ‘underneath’ the model Introduction Hausdorff distance Comparing portionsHD grid pointsHD rigid motionHD translation examples

Conclusion Chamfer matching is better when –There is substantial clutter –All expected shape variations are well- represented by the shape templates –Robustness and speed are more important