Scribd Logo
Upload

Welcome to Scribd!

  • 26 views

    Notes On The Harris Detector: From Rick Szeliski's Lecture Notes, CSE576, Spring 05

    Uploaded by

    ilham
    The Harris corner detector identifies corners in an image by analyzing the intensity change caused by small shifts of a local window. It models the intensity change as a bilinear form using the image derivatives within the window. Corners are detected as points where there is a significant change in intensity in all directions, as indicated by both eigenvalues of the bilinear form matrix being large. The detector computes a corner response measure for each point based on the eigenvalues and thresholds it to identify the strongest corners.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Notes On The Harris Detector: From Rick Szeliski's Lecture Notes, CSE576, Spring 05

    Uploaded by

    ilham
    26 views12 pages
    The Harris corner detector identifies corners in an image by analyzing the intensity change caused by small shifts of a local window. It models the intensity change as a bilinear form using the image derivatives within the window. Corners are detected as points where there is a significant change in intensity in all directions, as indicated by both eigenvalues of the bilinear form matrix being large. The detector computes a corner response measure for each point based on the eigenvalues and thresholds it to identify the strongest corners.

    Original Description:

    fdagfdxd

    Original Title

    Harris Detector

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The Harris corner detector identifies corners in an image by analyzing the intensity change caused by small shifts of a local window. It models the intensity change as a bilinear form using the image derivatives within the window. Corners are detected as points where there is a significant change in intensity in all directions, as indicated by both eigenvalues of the bilinear form matrix being large. The detector computes a corner response measure for each point based on the eigenvalues and thresholds it to identify the strongest corners.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    26 views12 pages

    Notes On The Harris Detector: From Rick Szeliski's Lecture Notes, CSE576, Spring 05

    Uploaded by

    ilham
    The Harris corner detector identifies corners in an image by analyzing the intensity change caused by small shifts of a local window. It models the intensity change as a bilinear form using the image derivatives within the window. Corners are detected as points where there is a significant change in intensity in all directions, as indicated by both eigenvalues of the bilinear form matrix being large. The detector computes a corner response measure for each point based on the eigenvalues and thresholds it to identify the strongest corners.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 12

    Notes on the Harris Detector

    from Rick Szeliski’s lecture notes,


    CSE576, Spring 05

    Harris corner detector


    • C.Harris, M.Stephens. “A Combined
    Corner and Edge Detector”. 1988

    1
    The Basic Idea
    • We should easily recognize the point by
    looking through a small window
    • Shifting a window in any direction should
    give a large change in intensity

    Harris Detector: Basic Idea

    “flat” region: “edge”: “corner”:


    no change in no change along significant change
    all directions the edge direction in all directions

    2
    Harris Detector: Mathematics
    Change of intensity for the shift [u,v]:

    E (u , v) = w( x, y ) [ I ( x + u , y + v) − I ( x, y ) ]
    2

    x, y

    Window function w(x,y) = or

    1 in window, 0 outside Gaussian

    Harris Detector: Mathematics


    For small shifts [u,v] we have a bilinear approximation:

    u
    E (u , v) ≅ [u, v ] M
    v

    where M is a 2×2 matrix computed from image derivatives:

    I x2 IxI y
    M= w( x, y )
    x, y IxI y I y2

    3
    Harris Detector: Mathematics
    Intensity change in shifting window: eigenvalue analysis
    u
    E (u , v) ≅ [u, v ] M λ1, λ2 – eigenvalues of M
    v
    direction of the
    fastest change
    direction of the
    slowest change
    Ellipse E(u,v) = const
    (λmax)-1/2
    (λmin)-1/2

    Harris Detector: Mathematics

    Classification of λ2 “Edge”
    image points using λ2 >> λ1 “Corner”
    eigenvalues of M: λ1 and λ2 are large,
    λ1 ~ λ2 ;
    E increases in all
    directions

    λ1 and λ2 are small;


    E is almost constant “Flat” “Edge”
    in all directions region λ1 >> λ2

    λ1

    4
    Harris Detector: Mathematics
    Measure of corner response:

    R = det M − k ( trace M )
    2

    det M = λ1λ2
    trace M = λ1 + λ2

    (k – empirical constant, k = 0.04-0.06)

    Harris Detector: Mathematics

    λ2 “Edge” “Corner”
    • R depends only on R<0
    eigenvalues of M
    • R is large for a corner R>0
    • R is negative with large
    magnitude for an edge
    • |R| is small for a flat
    region “Flat” “Edge”
    |R| small R<0
    λ1

    5
    Harris Detector
    • The Algorithm:
    – Find points with large corner response
    function R (R > threshold)
    – Take the points of local maxima of R

    Harris Detector: Workflow

    6
    Harris Detector: Workflow
    Compute corner response R

    Harris Detector: Workflow


    Find points with large corner response: R>threshold

    7
    Harris Detector: Workflow
    Take only the points of local maxima of R

    Harris Detector: Workflow

    8
    Harris Detector: Summary

    • Average intensity change in direction [u,v] can be


    expressed as a bilinear form:
    u
    E (u , v) ≅ [u , v ] M
    v

    • Describe a point in terms of eigenvalues of M:


    1λ2 − k ( λ1 + λ2 )
    R = λresponse
    2
    measure of corner

    • A good (corner) point should have a large intensity


    change in all directions, i.e. R should be large
    positive

    Harris Detector: Some


    Properties
    • Rotation invariance

    Ellipse rotates but its shape (i.e. eigenvalues)


    remains the same

    Corner response R is invariant to image rotation

    9
    Harris Detector: Some
    Properties
    • Partial invariance to affine intensity
    change
    Only derivatives are used => invariance
    to intensity shift I → I + b
    Intensity scale: I → a I

    R R
    threshold

    x (image coordinate) x (image coordinate)

    Harris Detector: Some


    Properties
    • But: non-invariant to image scale!

    All points will be Corner !


    classified as edges

    10
    Harris Detector: Some
    Properties
    • Quality of Harris detector for different
    scale changes
    Repeatability rate:
    # correspondences
    # possible correspondences

    C.Schmid et.al. “Evaluation of Interest Point Detectors”. IJCV 2000

    Models of Image Change

    • Geometry
    – Rotation
    – Similarity (rotation + uniform scale)

    – Affine (scale dependent on direction)


    valid for: orthographic camera, locally
    planar object
    • Photometry
    – Affine intensity change (I → a I + b)

    11
    Rotation Invariant Detection
    • Harris Corner Detector

    C.Schmid et.al. “Evaluation of Interest Point Detectors”. IJCV 2000

    12

    You might also like