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

Welcome to Scribd!

  • 5 views

    Ee6148 CV

    Uploaded by

    prathima1704g7
    The document is a mid-semester exam for a computer vision course. It contains 3 questions with multiple parts each. Question 1 involves (a) calculating a grey level co-occurrence matrix and analyzing texture descriptors, (b) determining a local binary pattern and designing rotation invariant patterns, and (c) describing a thinning algorithm for skeleton representation. Question 2 involves (a) defining the intrinsic matrix of identical cameras, (b) determining the spatial configuration of a stereo rig from rotation and translation, (c) computing the fundamental matrix, and (d) proving properties of the epipolar plane. Question 3 involves (a) describing B-spline curve interpolation, (b) analyzing snake models for active contour extraction, and

    Copyright:

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

    Ee6148 CV

    Uploaded by

    prathima1704g7
    5 views2 pages
    The document is a mid-semester exam for a computer vision course. It contains 3 questions with multiple parts each. Question 1 involves (a) calculating a grey level co-occurrence matrix and analyzing texture descriptors, (b) determining a local binary pattern and designing rotation invariant patterns, and (c) describing a thinning algorithm for skeleton representation. Question 2 involves (a) defining the intrinsic matrix of identical cameras, (b) determining the spatial configuration of a stereo rig from rotation and translation, (c) computing the fundamental matrix, and (d) proving properties of the epipolar plane. Question 3 involves (a) describing B-spline curve interpolation, (b) analyzing snake models for active contour extraction, and

    Original Description:

    Original Title

    EE6148 CV

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document is a mid-semester exam for a computer vision course. It contains 3 questions with multiple parts each. Question 1 involves (a) calculating a grey level co-occurrence matrix and analyzing texture descriptors, (b) determining a local binary pattern and designing rotation invariant patterns, and (c) describing a thinning algorithm for skeleton representation. Question 2 involves (a) defining the intrinsic matrix of identical cameras, (b) determining the spatial configuration of a stereo rig from rotation and translation, (c) computing the fundamental matrix, and (d) proving properties of the epipolar plane. Question 3 involves (a) describing B-spline curve interpolation, (b) analyzing snake models for active contour extraction, and

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    5 views2 pages

    Ee6148 CV

    Uploaded by

    prathima1704g7
    The document is a mid-semester exam for a computer vision course. It contains 3 questions with multiple parts each. Question 1 involves (a) calculating a grey level co-occurrence matrix and analyzing texture descriptors, (b) determining a local binary pattern and designing rotation invariant patterns, and (c) describing a thinning algorithm for skeleton representation. Question 2 involves (a) defining the intrinsic matrix of identical cameras, (b) determining the spatial configuration of a stereo rig from rotation and translation, (c) computing the fundamental matrix, and (d) proving properties of the epipolar plane. Question 3 involves (a) describing B-spline curve interpolation, (b) analyzing snake models for active contour extraction, and

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    1

    NATIONAL INSTITUTE OF TECHNOLOGY, ROURKELA


    MID-SEMESTER EXAMINATION
    SESSION: 2022-2023 (Spring)
    B.Tech. 8th Semester & M. Tech. 2nd Semester
    Subject code: EE6148 Subject Name: Computer Vision Dept. Code: EE
    No. of pages : 2 Full Marks : 30 Duration: 2 Hours

    Qs. Answer all questions. Marks


    No.
    All parts of the question must be answered in one place.
    1(a) For texture description employed in statistical methods, determine the grey 3
    level co-occurrence matrix (GLCM) P90o,1 for the given image as below. From
    the homogeneity and entropy of texture descriptors of the GLCM, present an
    analysis of the image texture.

    3 1 1 1 0 0
    2 4 1 1 0 0
    0 2 2 1 3 3
    1 2 3 3 4 4
    1 2 4 4 3 2
    1 1 3 4 2 2

    (b) Determine the local binary pattern (LBP) of the following grey level image. 4
    78 135 200

    98 100 128

    105 145 75

    The above image is rotated by 900 anti-clockwise. Design and analyse some
    rotation invariant LBPs which could overcome the limitations of LBP by
    applying the same to both original and rotated images.

    (c) Skeleton representation can be used to analyze the geometric structure of a 3


    region that plays an important role in character recognition. Design a thinning
    algorithm for the above application with detail description of the steps.

    2(a) Consider two identical cameras (such that camera Intrinsic matrices K = K`), 2
    whose optical axis coincides with the z axis, whose focal length is 0.03 m, with
    square pixels, no pinhole point offset and zero skew. What is the expression of
    K?

    (b) Consider the point Xin expressed with respect to the first camera coordinate 3
    system. Suppose the corresponding point with respect to second camera is Xin`
    = RXin + T, where :
    2

    cos 𝜃 −𝑠𝑖𝑛𝜃 0
    rotation 𝑅 = 𝑠𝑖𝑛𝜃 𝑐𝑜𝑠𝜃 0 with Ɵ =60 degree
    0 0 1
    0.3
    And translation T = 0
    0

    What is the spatial configuration of the stereo rig formed by the two cameras?
    What is the position of the second camera with respect to the first one?

    (c) Compute the fundamental matrix F associated to the stereo rig defined both in 3
    (a) and (b).

    (d) In epipolar constraint, the epipolar plane associated with left camera is spanned 2
    by the two vectors T and Pl.

    Prove that T X Pl = A. Pl, where A is a skew symmetric matrix.

    3(a) Describe the concept of B-spline curve interpolation for boundary shape
    description of an object in an image. Consider a cubic B-spline curve with 4
    uniform knot spacing. The control points are (-1,-1), (-1,1), (1,1), and (1,-1).
    What are the end-points of the curve segment? Derive the general function f(t)
    for a cubic B-spline, given it’s 4 control points. Use this to derive the 4x4
    matrix used for uniform cubic B-spline curves.

    (b) In image understanding, snake model is suitable for extraction of active


    contours. Present an elaborate analysis on the above statement based on energy 4
    minimization theory. Show the steps of the snake algorithm for contour
    segment estimation.

    (c) Fourier spectrum based spectral approach plays an important role in texture 2
    analysis. Justify it.

    You might also like