REU Week 1 Presented by Christina Peterson. Edge Detection Sobel ◦ Convolve image with derivative masks:  x:  y: ◦ Calculate gradient magnitude ◦ Apply.

Slides:



Advertisements
Similar presentations
Feature Detection. Description Localization More Points Robust to occlusion Works with less texture More Repeatable Robust detection Precise localization.
Advertisements

SIFT & MatLab Pier Luigi Mazzeo.
Edges and Contours– Chapter 7
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.
1Ellen L. Walker Edges Humans easily understand “line drawings” as pictures.
Edge and Corner Detection Reading: Chapter 8 (skip 8.1) Goal: Identify sudden changes (discontinuities) in an image This is where most shape information.
Lecture 4 Edge Detection
Canny Edge Detector.
Midterm review: Cameras Pinhole cameras Vanishing points, horizon line Perspective projection equation, weak perspective Lenses Human eye Sample question:
Feature extraction: Corners and blobs
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe – IJCV 2004 Brien Flewelling CPSC 643 Presentation 1.
Computer Vision P. Schrater Spring 2003
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Chapter 2. Image Analysis. Image Analysis Domains Frequency Domain Spatial Domain.
Computer vision.
Reporter: Fei-Fei Chen. Wide-baseline matching Object recognition Texture recognition Scene classification Robot wandering Motion tracking.
CAP 5415 Computer Vision Fall 2004
UCF REU: Weeks 1 & 2. Gradient Code Gradient Direction of the Gradient: Calculating theta.
EECS 274 Computer Vision Linear Filters and Edges.
CSC508 What You Should Be Doing Code, code, code –Programming Gaussian Convolution Sobel Edge Operator.
CSCE 643 Computer Vision: Extractions of Image Features Jinxiang Chai.
KRISTIN LAM REU WEEKS 1 & 2. MATERIAL COVERED MATLAB basics Edge Detection Harris Corner Detector Adaboost Face Detection Optical Flow Lucas-Kanade Method.
Lecture 7: Features Part 2 CS4670/5670: Computer Vision Noah Snavely.
CSC508 Convolution Operators. CSC508 Convolution Arguably the most fundamental operation of computer vision It’s a neighborhood operator –Similar to the.
Kylie Gorman WEEK 1-2 REVIEW. CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAY CHANNELS.
Distinctive Image Features from Scale-Invariant Keypoints David Lowe Presented by Tony X. Han March 11, 2008.
WEEK 1-2 ALEJANDRO TORROELLA. CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAYING THE SEPARATE CHANNELS.
Edges.
PRESENTATION REU IN COMPUTER VISION 2014 AMARI LEWIS CRCV UNIVERSITY OF CENTRAL FLORIDA.
CSE 6367 Computer Vision Image Operations and Filtering “You cannot teach a man anything, you can only help him find it within himself.” ― Galileo GalileiGalileo.
Scale Invariant Feature Transform (SIFT)
SIFT DESCRIPTOR K Wasif Mrityunjay
Presented by David Lee 3/20/2006
Course 5 Edge Detection. Image Features: local, meaningful, detectable parts of an image. edge corner texture … Edges: Edges points, or simply edges,
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
1 Edge Operators a kind of filtering that leads to useful features.
Blob detection.
SIFT Scale-Invariant Feature Transform David Lowe
CS262: Computer Vision Lect 09: SIFT Descriptors
Interest Points EE/CSE 576 Linda Shapiro.
Presented by David Lee 3/20/2006
Distinctive Image Features from Scale-Invariant Keypoints
Scale Invariant Feature Transform (SIFT)
SIFT paper.
Image Primitives and Correspondence
Corners and Interest Points
Report 1: Optical Flow and Sift
Levi Smith REU Week 1.
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
Lecture 10 Image sharpening.
From a presentation by Jimmy Huff Modified by Josiah Yoder
a kind of filtering that leads to useful features
What I learned in the first 2 weeks
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
REU Week 1 Ivette Carreras UCF.
a kind of filtering that leads to useful features
Interest Points & Descriptors 3 - SIFT
Canny Edge Detector.
Week 1 Alan Wright - UCF.
Edge detection f(x,y) viewed as a smooth function
Detection of salient points
SIFT SIFT is an carefully designed procedure with empirically determined parameters for the invariant and distinctive features.
Week 1 Emily Hand UNR.
IT472 Digital Image Processing
CAP 5415 Computer Vision Fall 2004
Presentation transcript:

REU Week 1 Presented by Christina Peterson

Edge Detection Sobel ◦ Convolve image with derivative masks:  x:  y: ◦ Calculate gradient magnitude ◦ Apply threshold

Edge Detection Marr Hildreth ◦ Apply Laplacian of Gaussian to an image ◦ Find zero crossings  {+,-}, {+, 0, -}, {-, +}, {-, 0, +} ◦ Mark edges  Apply threshold to slope of zero-crossings

Edge Detection Canny ◦ Convolve image with first derivative of gaussian ◦ Find magnitude of gradient and orientation ◦ Apply non-max suppression  For each pixel, check if it is a local max by comparing it to neighbor pixels along normal direction to an edge ◦ Apply hysteria thresholding

Canny Example Original Image Canny Output

Harris Corner Detector Implemented Harris Corner Detector ◦ 1. x and y derivatives  Ix=conv2(double(I), maskx, ‘same’)  Iy=conv2(double(I), masky, ‘same’) ◦ 2. products of derivatives  Ix2=Ix.*Ix  Iy2=Iy.*Iy  Ixy=Ix.*Iy ◦ 3. sums of products of derivatives  Sx2=gauss_filter(Ix2, sigma, kernel_size)  Sy2=gauss_filter(Iy2, sigma, kernel,size)  Sxy=gauss_filter(Ixy, sigma, kernel_size)

Harris Corner Detector ◦ 4. Define matrix H(x,y):  For j=1:columns,  For i=1:rows,  H{ i, j } = [Sx2(i, j) Sxy(i, j); Sxy(i, j) Sy2(i, j) ◦ 5. Response Detector  For j=1:columns,  For i=1:rows,  R( i, j ) = det(H{ i, j } )– k*(trace(H{ i, j }))^2 ◦ 6. Apply threshold to R  Edge: R <  Corner: R > 10000

Harris Corner Detector

Sift Purpose ◦ To identify features of an image regardless of scale and rotation Scale Space ◦ Resize image to half size (octave) ◦ Blur image by adjusting sigma ◦ 4 octaves and 5 blur levels are recommended

Sift Sift Features ◦ Divide image into 4 x 4 windows ◦ Divide each window into 4 x 4 subwindows Calculate magnitude and gradient for each subwindow ◦ Generate a histogram of 8 bins for each 4 x 4 window Each bin represents a gradient orientation 4 x 4 x 8 = 128 dimensions

Sift using Vl_feat

Match candidates by finding patches that have the most similar SIFT descriptor

Optical Flow Lucas Kanade Optical Flow Does not work for areas of large motion ◦ Resolved by Pyramids

Optical Flow

Bag of Features Implemented a Bag of Word classification Divided image into frames Concatenated sift descriptors for each frame Kmeans2 to cluster features Image represented as histogram Used histograms as training data for SVM

Bag of Features Results for 8 frames and 20 clusters: ◦ 9.5% accuracy on test data Conclusions: ◦ Increase frames and clusters to improve accuracy

Research Topics 1. Survey on Multiple Human Tracking by Detection Methods Afshin Dehghan 2. Data Driven Attributes for Action Detection Rui Hou 3. Subspace Clustering via Graph Regularized Sparse Coding Nasim Souly