Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 17 views

    Homework#2 - ECE181B Harris Corner Detector Implementation: Thuyen Ngo, Perm#5773155 January 25, 2012

    Uploaded by

    acsbachkhoa
    This document summarizes an implementation of the Harris corner detection algorithm. The implementation follows 5 main steps: 1) compute derivatives of the image by convolving with the derivative of Gaussian kernels; 2) compute components of the Harris matrix A; 3) blur the components with a Gaussian kernel; 4) compute the corner response function as det(A) - α(trace(A))^2; and 5) detect local maxima after thresholding to find corners. The performance is evaluated by detecting corners on test images and varying parameters like the Gaussian kernel standard deviations σ1 and σ2, threshold γ0, and maximal filter radius r.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd

    Homework#2 - ECE181B Harris Corner Detector Implementation: Thuyen Ngo, Perm#5773155 January 25, 2012

    Uploaded by

    acsbachkhoa
    17 views7 pages
    This document summarizes an implementation of the Harris corner detection algorithm. The implementation follows 5 main steps: 1) compute derivatives of the image by convolving with the derivative of Gaussian kernels; 2) compute components of the Harris matrix A; 3) blur the components with a Gaussian kernel; 4) compute the corner response function as det(A) - α(trace(A))^2; and 5) detect local maxima after thresholding to find corners. The performance is evaluated by detecting corners on test images and varying parameters like the Gaussian kernel standard deviations σ1 and σ2, threshold γ0, and maximal filter radius r.

    Original Description:

    Original Title

    hw2_181b

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes an implementation of the Harris corner detection algorithm. The implementation follows 5 main steps: 1) compute derivatives of the image by convolving with the derivative of Gaussian kernels; 2) compute components of the Harris matrix A; 3) blur the components with a Gaussian kernel; 4) compute the corner response function as det(A) - α(trace(A))^2; and 5) detect local maxima after thresholding to find corners. The performance is evaluated by detecting corners on test images and varying parameters like the Gaussian kernel standard deviations σ1 and σ2, threshold γ0, and maximal filter radius r.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    17 views7 pages

    Homework#2 - ECE181B Harris Corner Detector Implementation: Thuyen Ngo, Perm#5773155 January 25, 2012

    Uploaded by

    acsbachkhoa
    This document summarizes an implementation of the Harris corner detection algorithm. The implementation follows 5 main steps: 1) compute derivatives of the image by convolving with the derivative of Gaussian kernels; 2) compute components of the Harris matrix A; 3) blur the components with a Gaussian kernel; 4) compute the corner response function as det(A) - α(trace(A))^2; and 5) detect local maxima after thresholding to find corners. The performance is evaluated by detecting corners on test images and varying parameters like the Gaussian kernel standard deviations σ1 and σ2, threshold γ0, and maximal filter radius r.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    Homework#2 - ECE181B Harris Corner Detector Implementation

    Thuyen Ngo, Perm#5773155 January 25, 2012

    Algorithm

    Basically, the implementation follows 5 steps discussed in class:

    1.1

    Compute Derivatives

    In this case, we will also have to blur the original image along with (before) taking the derivative, which results in a quite simple way of approximating derivatives by noticing two following facts: i) Derivative of a convolution: For simplication, let consider the scalar case:

    g(x) = f (x) h(x) =


    f (t)h(x t)dt

    g (x) =

    f (t)h (x t)dt = f (x) h (x)

    The above expression implies that we could compute the derivative of a convolution by convole the derivative of the kernel with the original function. This fact still holds true for higher dimentions - in our case, 2 dimentions. ii) Seperable convolution: From the text, we know that the two-dimentional kernel K corresponding to sucessive convolution with a horizontal kernel h and a vertical kernal v is the outer product of the 2 kernels . K = vhT Based on two above statements, in order to calculate Ix and Iy , instead of smoothing in both 2 directions then taking the derivatives of the resulting image, we now take derivative of the kernel and build new lter kernels to compute Ix and Iy . Gaussian kernal: h(x) = x h (x) = 2

    1
    2 21

    x2
    1

    1
    2 21

    x2
    1

    Chosing the radius of the kernels N 31 , we calculate two one-dimentional kernels u for h(x) and v for h (x) (x [NN])

    Ix is the resulting image after smoothing along y coordinate and taking derivatve (dirence) along x coordinate. Then the kernel for Ix : Fx = uv T Ix = Fx I (I is the original image) In the same way, Iy is the resulting image after smoothing along x coordinate and taking derivatve (dirence) along y coordinate and the kernel for Iy :
    T Fy = vuT = Fx Iy = Fy I;

    1.2

    Compute 3 components of matrix A


    2 Ix2 = Ix 2 Iy2 = Iy Ixy = Ix Iy

    1.3

    Blur the 3 images with a Gaussian kernel


    1
    x2
    2 2

    Gaussian Kernel: h(x) =

    e 2 22 Now we smooth the image in both direction and the lter for that: F = uuT

    1.4

    Compute Corner Response Funtion (CRF)


    CRF = det(A) (trace(A))2

    Find det and trace of A and then:

    1.5

    Find local maxima and perform thersholding

    - Using a maximal lter (with radius r) to nd local maxima max crf - Normalize local maxima = - Detect corners: > 0 (threshold) - Display detected corners. 2 max crf max(max crf )

    Performance

    Figure 1: 1 = 1, 2 = 3, = 0.04, r(maximal lter radius) = 1, 0(threshold) = 0.01

    Figure 2: 1 = 1.5, 2 = 3, = 0.04, r = 1, 0 = 0.01 3

    Figure 3: 1 = 1, 2 = 3, = 0.04, r = 1, 0 = 0.01

    Figure 4: 1 = 1, 2 = 3, = 0.04, r = 1, 0 = 0.09 4

    Figure 5: 1 = 1, 2 = 5, = 0.04, r = 1, 0 = 0.01

    Figure 6: 1 = 1, 2 = 3, = 0.04, r = 10, 0 = 0.01 5

    Figure 7: 1 = 1, 2 = 3, = 0.06, r = 1, 0 = 0.01 Notess: - When increase 1,2 , the lters blur the image more, and less corners detected (Fig1 vs Fig2; Fig3 vs Fig5) - Obviously, when increase 0 , less corners detected (Fig3 vs Fig4) - When increase the maximal lter radius r, we reduce the number of local maxima and therefore the ruduce the number of corners detected (Fig3 vs Fig6) - Finally increase , the detector becomes less senstive (Fig3 vs Fig7)

    You might also like