Harris detector Convert image to greyscale

Slides:



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

Object Recognition from Local Scale-Invariant Features David G. Lowe Presented by Ashley L. Kapron.
Automatic Color Gamut Calibration Cristobal Alvarez-Russell Michael Novitzky Phillip Marks.
Group Meeting Presented by Wyman 10/14/2006
Spatial Filtering (Chapter 3)
CSE 473/573 Computer Vision and Image Processing (CVIP)
Interest points CSE P 576 Ali Farhadi Many slides from Steve Seitz, Larry Zitnick.
Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.
TP14 - Local features: detection and description Computer Vision, FCUP, 2014 Miguel Coimbra Slides by Prof. Kristen Grauman.
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 6: Feature matching CS4670: Computer Vision Noah Snavely.
1 Interest Operators Find “interesting” pieces of the image –e.g. corners, salient regions –Focus attention of algorithms –Speed up computation Many possible.
CSCE 641 Computer Graphics: Image Filtering & Feature Detection Jinxiang Chai.
Lecture 4: Feature matching
Scale Invariant Feature Transform (SIFT)
Lecture 3a: Feature detection and matching CS6670: Computer Vision Noah Snavely.
CS4670: Computer Vision Kavita Bala Lecture 7: Harris Corner Detection.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
Image Filtering. Problem! Noise is a problem, even in images! Gaussian NoiseSalt and Pepper Noise.
CS448f: Image Processing For Photography and Vision Denoising.
Overview Introduction to local features
Harris detector Convert image to greyscale Apply Gaussian convolution to blur the image and remove noise Calculate gradient of image in x and y direction.
CSCE 441: Computer Graphics Image Filtering Jinxiang Chai.
National Center for Supercomputing Applications University of Illinois at Urbana-Champaign Image Features Kenton McHenry, Ph.D. Research Scientist.
05 - Feature Detection Overview Feature Detection –Intensity Extrema –Blob Detection –Corner Detection Feature Descriptors Feature Matching Conclusion.
1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.
Local invariant features Cordelia Schmid INRIA, Grenoble.
UCF REU: Weeks 1 & 2. Gradient Code Gradient Direction of the Gradient: Calculating theta.
CSCE 643 Computer Vision: Extractions of Image Features Jinxiang Chai.
Soccer Video Analysis EE 368: Spring 2012 Kevin Cheng.
Local invariant features 1 Thursday October 3 rd 2013 Neelima Chavali Virginia Tech.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Machine Vision ENT 273 Image Filters Hema C.R. Lecture 5.
Harris Corner Detector & Scale Invariant Feature Transform (SIFT)
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.
Intelligent Vision Systems ENT 496 Image Filtering and Enhancement Hema C.R. Lecture 4.
A Tutorial on using SIFT Presented by Jimmy Huff (Slightly modified by Josiah Yoder for Winter )
Sejong Univ. CH3. Area Processes Convolutions Blurring Sharpening Averaging vs. Median Filtering.
Homework 2 (Due: 3/26) A. Given a grayscale image I,
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Filtering the Images.  Filtering images using low-pass filters  Filtering images using a median filter  Applying directional filters to detect edges.
More sliding window detection: Discriminative part-based models
Midterm Review. Tuesday, November 3 7:15 – 9:15 p.m. in room 113 Psychology Closed book One 8.5” x 11” sheet of notes on both sides allowed Bring a calculator.
Instructor: Mircea Nicolescu Lecture 10 CS 485 / 685 Computer Vision.
REU Week 1 Presented by Christina Peterson. Edge Detection Sobel ◦ Convolve image with derivative masks:  x:  y: ◦ Calculate gradient magnitude ◦ Apply.
0 Assignment 1 (Due: 10/2) Input/Output an image: (i) Design a program to input and output a color image. (ii) Transform the output color image C(R,G,B)
Visual homing using PCA-SIFT
CS262: Computer Vision Lect 09: SIFT Descriptors
Interest Points EE/CSE 576 Linda Shapiro.
Distinctive Image Features from Scale-Invariant Keypoints
CS 4501: Introduction to Computer Vision Sparse Feature Detectors: Harris Corner, Difference of Gaussian Connelly Barnes Slides from Jason Lawrence, Fei.
SIFT paper.
TP12 - Local features: detection and description
Feature description and matching
EE 596 Machine Vision HW 6 Assigned: Nov 20, 2013
CAP 5415 Computer Vision Fall 2012 Dr. Mubarak Shah Lecture-5
CSE 455 – Guest Lectures 3 lectures Contact Interest points 1
From a presentation by Jimmy Huff Modified by Josiah Yoder
What I learned in the first 2 weeks
The SIFT (Scale Invariant Feature Transform) Detector and Descriptor
REU Week 1 Ivette Carreras UCF.
Histogram Probability distribution of the different grays in an image.
Img1 img3 img5.
Feature descriptors and matching
SIFT SIFT is an carefully designed procedure with empirically determined parameters for the invariant and distinctive features.
Image Filtering with GLSL
Presentation transcript:

Harris detector Convert image to greyscale Apply Gaussian convolution to blur the image and remove noise Calculate gradient of image in x and y direction for every pixel For each point in the image, consider a 3x3 square window of pixels around that point. Compute the Harris matrix H for that point,   Compute the corner strength function Choose points whose c(H) is above threshold and c(H) is local maxima in a 10x10 neighborhood. These points will be called the feature points

My simple descriptor For each feature points Take a 45x45 window centered at the feature point Normalise the color of each pixels in the window Make a 9x9 window  feature descriptor by applying linear weights to every 5 points and summing up the RGB values separately.   The feature descriptor will contain the RGB value of the points, hence in total our feature descriptor has 9x9x3 dimensions   

Simple descriptor – Bike 1

Simple descriptor – Bike 2

Simple descriptor – bike 3

Simple descriptor – bike 4

Simple descriptor – bike 5

Simple descriptor – bike 6

My simple feature descriptor: bikes 1 – bikes 2 – matching with ratio

My simple feature descriptor : bikes 1 –bikes 3 – matching with ratio

Simple descriptor numbers (testMatch results) The total error is the average Euclidean distance between a (correctly) transformed feature point in the first image and its matched feature point in the second image. My descriptor SIFT Img1-img2 43.651483 7.281360 Img1-img3 64.347448 13.653063 Img1-img4 112.002063 19.995964 Img1-img5 320.155898 34.570192

Your error number will be slightly different: (nInliers/nMatches) My evaluation: for (unsigned int i=0; i<f1.size(); i++) { applyHomography(f1[i].x, f1[i].y, xNew, yNew, h); if (matches[i].id > 0) { d += sqrt(pow(xNew-f2[matches[i].id-1].x,2)+pow(yNew-f2[matches[i].id-1].y,2)); n++; } return d / n; Your evaluation in skeleton code: for (unsigned int i=0; i<f1.size(); i++) { applyHomography(f1[i].x, f1[i].y, xNew, yNew, h); if (matches[i].id > 0) { d = sqrt(pow(xNew-f2[matches[i].id-1].x,2)+pow(yNew-f2[matches[i].id-1].y,2)); if (d < epsilon) nInliers++; nMatches++; } return (nInliers / (float)nMatches);