CS-565 Computer Vision Nazar Khan Lecture 15.

Slides:



Advertisements
Similar presentations
Image Segmentation Image segmentation (segmentace obrazu) –division or separation of the image into segments (connected regions) of similar properties.
Advertisements

Lecture 07 Segmentation Lecture 07 Segmentation Mata kuliah: T Computer Vision Tahun: 2010.
Segmentation (2): edge detection
Hough Transform Jeremy Wyatt. The story so far We know how to find edges by convolving with the derivative of a Gaussian filter in two directions We then.
Lecture 5 Hough transform and RANSAC
Thresholding Otsu’s Thresholding Method Threshold Detection Methods Optimal Thresholding Multi-Spectral Thresholding 6.2. Edge-based.
CS 376b Introduction to Computer Vision 04 / 11 / 2008 Instructor: Michael Eckmann.
Error Propagation. Uncertainty Uncertainty reflects the knowledge that a measured value is related to the mean. Probable error is the range from the mean.
Canny Edge Detector1 1)Smooth image with a Gaussian optimizes the trade-off between noise filtering and edge localization 2)Compute the Gradient magnitude.
Image segmentation based on edge and corner detectors Joachim Stahl 04/21/2005.
CS 223B Assignment 1 Help Session Dan Maynes-Aminzade.
Fitting a Model to Data Reading: 15.1,
CS 376b Introduction to Computer Vision 04 / 14 / 2008 Instructor: Michael Eckmann.
Lecture 4: Edge Based Vision Dr Carole Twining Thursday 18th March 2:00pm – 2:50pm.
Searching for pulsars using the Hough transform Badri Krishnan AEI, Golm (for the pulsar group) LSC meeting, Hanford November 2003 LIGO-G Z.
Robust estimation Problem: we want to determine the displacement (u,v) between pairs of images. We are given 100 points with a correlation score computed.
October 8, 2013Computer Vision Lecture 11: The Hough Transform 1 Fitting Curve Models to Edges Most contours can be well described by combining several.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
October 14, 2014Computer Vision Lecture 11: Image Segmentation I 1Contours How should we represent contours? A good contour representation should meet.
Computer Vision Lecture 5. Clustering: Why and How.
Edge Linking & Boundary Detection
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Image Segmentation and Morphological Processing Digital Image Processing in Life- Science Aviad Baram
Chapter 10 Image Segmentation.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
CS654: Digital Image Analysis
Jack Pinches INFO410 & INFO350 S INFORMATION SCIENCE Computer Vision I.
October 16, 2014Computer Vision Lecture 12: Image Segmentation II 1 Hough Transform The Hough transform is a very general technique for feature detection.
Edge Based Segmentation Xinyu Chang. Outline Introduction Canny Edge detector Edge Relaxation Border Tracing.
October 1, 2013Computer Vision Lecture 9: From Edges to Contours 1 Canny Edge Detector However, usually there will still be noise in the array E[i, j],
November 5, 2013Computer Vision Lecture 15: Region Detection 1 Basic Steps for Filtering in the Frequency Domain.
Digital Image Processing Lecture 17: Segmentation: Canny Edge Detector & Hough Transform Prof. Charlene Tsai.
Machine Vision Edge Detection Techniques ENT 273 Lecture 6 Hema C.R.
Instructor: Mircea Nicolescu Lecture 10 CS 485 / 685 Computer Vision.
Detecting Image Features: Corner. Corners Given an image, denote the image gradient. C is symmetric with two positive eigenvalues. The eigenvalues give.
Mark Dorman Separation Of Charged Current And Neutral Current Events In The MINOS Far Detector Using The Hough Transform Mark Dorman 16/12/04.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Statistical Inference for the Mean Objectives: (Chapter 8&9, DeCoursey) -To understand the terms variance and standard error of a sample mean, Null Hypothesis,
Level Set Segmentation ~ 9.37 Ki-Chang Kwak.
Grouping and Segmentation. Sometimes edge detectors find the boundary pretty well.
April 21, 2016Introduction to Artificial Intelligence Lecture 22: Computer Vision II 1 Canny Edge Detector The Canny edge detector is a good approximation.
Course : T Computer Vision
Machine Vision ENT 273 Lecture 4 Hema C.R.
A 2 veto for Continuous Wave Searches
Searching for pulsars using the Hough transform
Fitting: Voting and the Hough Transform
Detection of discontinuity using
Computer Vision Lecture 13: Image Segmentation III
Image Segmentation – Edge Detection
CS-565 Computer Vision Nazar Khan Lecture 4.
Computer Vision Lecture 12: Image Segmentation II
Fourier Transform: Real-World Images
Fitting Curve Models to Edges
IMAGE PROCESSING AKSHAY P S3 EC ROLL NO. 9.
Computer Vision Lecture 9: Edge Detection II
11.6 Geometric Probability
ECE 692 – Advanced Topics in Computer Vision
CS654: Digital Image Analysis
CS Digital Image Processing Lecture 5
Image Segmentation Image analysis: First step:
Section 11.6 Geometric Probability
Digital Image Processing
CS 565 Computer Vision Nazar Khan Lecture 11.
Outline Announcement Perceptual organization, grouping, and segmentation Hough transform Read Chapter 17 of the textbook File: week14-m.ppt.
CS 565 Computer Vision Nazar Khan Lecture 9.
A Block Based MAP Segmentation for Image Compression
Region-Based Segmentation
Morphological Operators
Introduction to Artificial Intelligence Lecture 22: Computer Vision II
CS5760: Computer Vision Lecture 9: RANSAC Noah Snavely
Presentation transcript:

CS-565 Computer Vision Nazar Khan Lecture 15

Line Segment Detection Edge detector gives potential edge pixels. Hough transform gives potential infinite lines. But we see line segments. In this lecture, we study a Line Segment Detector. Rafael Grompone von Gioi, Jeremie Jakubowicz, Jean-Michel Morel, Gregory Randall , LSD: a Line Segment Detector, Image Processing On Line, 2 (2012), pp. 35{55. http://dx.doi.org/10.5201/ipol.2012.gjmr-lsd

LSD Aimed at detecting line segments locally straight contours on images. Contours – zones of the image where the gray level is changing fast.

Line Support Regions Compute the level-line angle at each pixel to produce a level-line field. Segment level-line field into connected regions of pixels that share the same level-line angle up to a certain tolerance . These connected regions are called line support regions.

Region Growing

Line Support Rectangles Each line support region is a candidate for a line segment. Associate a rectangle with each region. The principal inertial axis of the line support region is used as main rectangle direction The size of the rectangle is chosen to cover the full region.

Aligned Points For the line support rectangle, count the number of aligned points Level-line angle within  radians of rectangle angle.

Validation The total number of pixels in the rectangle, n, and its number of aligned points, k, are counted and used to validate the rectangle as a detected line segment.

Helmholtz Principle The so-called Helmholtz principle states that no perception (or detection) should be produced on an image of noise.

The a contrario Approach Rough idea: if a random level-line field can produce more alignments than in the observed image rectangle, then the rectangle does not represent a line segment. In other words, accept a line segment only if it can’t occur by chance. More formally, lines are outliers in a random level-line model H0.

The a contrario Approach The noise model H0 has the following properties {LLA(j) }jPixels is composed of independent random variables. LLA(j) is uniformly distributed over [0; 2] where LLA(j)=level-line angle for pixel j. Under hypothesis H0, the probability that a pixel on the a contrario model is an aligned point is p=/. (Why?)

The a contrario Approach Let i=input image, I=random image. Let r be a rectangle with n(r) pixels. Let k(r,i) be the number of aligned points within r in observed image i Let k(r,I) be the number of aligned points within r in a random image I P(k(r,I)>= k(r,i)) represents the probability of the event that number of aligned pixels in observed rectangle is less than random alignments. If this probability is high then the rectangle does not represent a valid line segment in input image i.

The a contrario Approach k(r,I) = # aligned points in r in random image I Probability of j random alignments in rectangle r Probability of more random alignments than observed Expected number of rectangles under random model that are as good as observed rectangle. These are all false alarms!

The a contrario Approach

LSD Grow line support regions based on seed pixels with large gradients Form line support rectangles Validate each rectangle if the number of aligned points within the rectangle cannot be due to chance.

LSD

Weaknesses Lines can still be broken because of the region growing process. Intersections are missed. Requires post-processing.