Kiera Henning, Jiwon Kim,

Slides:



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

A Multi-Resolution Technique for Comparing Images Using the Hausdorff Distance Daniel P. Huttenlocher and William J. Rucklidge Nov Presented by.
Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Alignment Visual Recognition “Straighten your paths” Isaiah.
Three things everyone should know to improve object retrieval
TP14 - Local features: detection and description Computer Vision, FCUP, 2014 Miguel Coimbra Slides by Prof. Kristen Grauman.
A NOVEL LOCAL FEATURE DESCRIPTOR FOR IMAGE MATCHING Heng Yang, Qing Wang ICME 2008.
Announcements Final Exam May 13th, 8 am (not my idea).
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Fast High-Dimensional Feature Matching for Object Recognition David Lowe Computer Science Department University of British Columbia.
Patch Descriptors CSE P 576 Larry Zitnick
Dimensionality Reduction Chapter 3 (Duda et al.) – Section 3.8
Iterative closest point algorithms
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
CS 790Q Biometrics Face Recognition Using Dimensionality Reduction PCA and LDA M. Turk, A. Pentland, "Eigenfaces for Recognition", Journal of Cognitive.
Chamfer Matching & Hausdorff Distance Presented by Ankur Datta Slides Courtesy Mark Bouts Arasanathan Thayananthan.
(1) Feature-point matching by D.J.Duff for CompVis Online: Feature Point Matching Detection, Extraction.
Improved Approximation Bounds for Planar Point Pattern Matching (under rigid motions) Minkyoung Cho Department of Computer Science University of Maryland.
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
CS4670: Computer Vision Kavita Bala Lecture 8: Scale invariance.
Lecture 6: Feature matching and alignment CS4670: Computer Vision Noah Snavely.
Presenter: Stefan Zickler
Computer vision.
Alignment Introduction Notes courtesy of Funk et al., SIGGRAPH 2004.
Lecture 4: Feature matching CS4670 / 5670: Computer Vision Noah Snavely.
A Statistical Approach to Speed Up Ranking/Re-Ranking Hong-Ming Chen Advisor: Professor Shih-Fu Chang.
Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao.
Survey of Algorithms to Query Image Databases COMP :Computational Geometry Benjamin Lok 11/2/98 Image from Kodak’s PhotoQuilt.
Object Detection with Discriminatively Trained Part Based Models
Beyond Sliding Windows: Object Localization by Efficient Subwindow Search The best paper prize at CVPR 2008.
Efficient Matching of Pictorial Structures By Pedro Felzenszwalb and Daniel Huttenlocher Presented by John Winn.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
21 June 2009Robust Feature Matching in 2.3μs1 Simon Taylor Edward Rosten Tom Drummond University of Cambridge.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Adaptive Rigid Multi-region Selection for 3D face recognition K. Chang, K. Bowyer, P. Flynn Paper presentation Kin-chung (Ryan) Wong 2006/7/27.
Histograms of Oriented Gradients for Human Detection Navneet Dalal and Bill Triggs CVPR 2005 Another Descriptor.
Discussion of Pictorial Structures Pedro Felzenszwalb Daniel Huttenlocher Sicily Workshop September, 2006.
Pictorial Structures and Distance Transforms Computer Vision CS 543 / ECE 549 University of Illinois Ian Endres 03/31/11.
CSE 185 Introduction to Computer Vision Feature Matching.
Partial Shape Matching. Outline: Motivation Sum of Squared Distances.
CSE554Contouring IISlide 1 CSE 554 Lecture 5: Contouring (faster) Fall 2013.
776 Computer Vision Jan-Michael Frahm Spring 2012.
Image matching using the Hausdorff Distance with CUDA
Tracking Hands with Distance Transforms Dave Bargeron Noah Snavely.
Image Representation and Description – Representation Schemes
CSE 554 Lecture 5: Contouring (faster)
CENG 789 – Digital Geometry Processing 08- Rigid-Body Alignment
Cascade for Fast Detection
Lecture 13: Feature Descriptors and Matching
Lecture 07 13/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.
Nearest-neighbor matching to feature database
TP12 - Local features: detection and description
Lit part of blue dress and shadowed part of white dress are the same color
Investigating the Hausdorff Distance
Feature description and matching
Object detection as supervised classification
A special case of calibration
Spatio-temporal Pattern Queries
Features Readings All is Vanity, by C. Allan Gilbert,
Object recognition Prof. Graeme Bailey
Nearest-neighbor matching to feature database
Aim of the project Take your image Submit it to the search engine
Brief Review of Recognition + Context
Large Scale Image Deduplication
CSE 185 Introduction to Computer Vision
Flexible templates, density estimation, mean shift
Feature descriptors and matching
Calibration and homographies
Presentation transcript:

Kiera Henning, Jiwon Kim, Lost and Found The Distance Transform Kiera Henning, Jiwon Kim,

Pictorial Structures Represent the ‘lost’ item with a tree G = (V, E). V = {parts of the object} E = {deformations between parts} [Felzenszwalb, Huttenlocher 00]

An example template tree

The Problem Given an object, find the best location of the object in the image while respecting the structure of the object defined by the tree.

The Problem (cont) Define For a given part, j, if we know the location of our parent, i, then the best location for j is that which minimizes

The Solution Beginning with the leaves and continuing toward the root one depth at a time, determine B. If all nodes at depth at least d have already determined B, then all nodes at depth d-1 can determine B.

Deformation cost Suppose

Transformed Grid Let location , and define , where

Transformed Grid (cont) Then Run DT on grid defined by T.

Match cost Using PCA, can initialize m to measure the distance from space spanned by eigenvectors. Using simple color scheme, m measures how well the area matches the average color and variance of the part. Using sum of squared differences to match a part expected to change very little.

Examples Using PCA Success! Failed…

Examples Using PCA

Example Using Sum Sq Diff

Document Recognition Documents on Desk Document Image

Document Template SIFT features [Lowe 04]

Example

Feature Points

Distance Transform

chamf(A,B) = ∑a∈A minb∈B ||a-b|| Approach 1 L22 distance defined in 2D feature space [px,py] (2D location x, y) Assymetric Chamfer distance chamf(A,B) = ∑a∈A minb∈B ||a-b|| Brute-force search for best matching translation and rotation (x,y,θ) between A and B

Result Sparse document incorrectly matched to more dense document

Approach 2 L22 distance defined in 2D feature space [px,py] (2D location x, y) Symmetric Chamfer distance chamf(A,B) + chamf(B,A) Brute-force search for best matching translation and rotation (x,y,θ) between A and B

Result H = 268.7 H = 239.3 Non-existing document scores only slightly lower than existing document

Approach 3 L22 distance defined in 3D feature space [px,py,αpo] (x, y + edge orientation) Symmetric Chamfer distance chamf(A,B) + chamf(B,A) Brute-force search for best matching translation and rotation (x,y,θ) between A and B  Better at answering existence query

Result H = 673.1 H = 267.0 Non-existing document scores clearly lower than existing document

Approach 4 L2 distance defined in 3D feature space [px,py,αpo] (x, y + edge orientation) Symmetric, partial Hausdorff distance h(A,B) = K-tha∈A minb∈B ||a-b|| H(A,B) = max(h(A,B), h(B,A)) Efficient search for best matching translation, rotation and scale (x,y,θ) between A and B under partial occlusion

Partial Hausdorff Distance h(A,B) = K-tha∈A minb∈B ||a-b|| Rank a’s according to distance to closest b K=|A| equivalent to h(A,B) = max… 1-K/|A| dictates amount of partial occlusion allowed

Fast Hausdorff Search (1) H(A,B) decreases linearly  can compute lower bound for a cell Subdivide and prune in transformation space [tx,ty,sx,sy] [Huttenlocher et al. 92]

Fast Hausdorff Search (2) Additional acceleration tricks Early rejection N = # of points in A whose dtrans value > thresh If |A| > N > K, skip rest of points for the given cell Early acceptance Probe a randomly chosen fraction of A (e.g., 20%) If fraction of points < thresh larger than K/|A|, accept cell Skipping forward [Huttenlocher et al. 92]

Result Speedup Test image: Template: Xform space: 1600x1200 ~10,000 features Template: ~600x500 ~1,000 features Xform space: 36 rotation bins 100 scales between 0.5 and 1.0 (tx,ty,θ) (tx,ty,θ,sx,sy) Exhaustive search > 10 minutes ? Fast Hausdorff search < 1 minute 4-5 minutes

Result Partial occlusion (success, failure) works up to ~20% occlusion

Discussion Comparison w/ SIFT-based recognition Accuracy (error rate, occlusion handling) Inherently lower, because full feature descriptor information not used Efficiency (speed) Fast multi-resolution search performs quite well Potentially could be made faster by using fewer features However, SIFT-based method also has room for speedup

References Daniel Huttenlocher, William Rucklidge. A Multi-Resolution Technique for Comparing Images Using the Hausdorff Distance. Technical Report TR 92-1321, 1992. Pedro Felzenszwalb, Daniel Huttenlocher. Efficient Matching of Pictorial Structures. In CVPR, 2000. Martin Handford. Where’s Waldo Now?