Dense Estimation of Motion and Appearance



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding



Fitting Mixture Models to both Motion and Appearance.
Top row: (1) Image sequence, (2) Horizontal, and (3) vertical motion components Middle row: (1) P(A), (2) p(u), and (3) P(v) Bottom row: (1) P(A) with single Gaussian after thresholding (standard background subtraction), (2) P(A).p(u).p(v) after thresholding





[Research]
        [Tracking Vehicles In Airborne Video Imagery]
        [Dense Motion and Appearance Estimation]
        [Implicitization by Matrix Annihilation]
        [Modeling and Measurement Using IPs]
        [Automated Sorting of Remote Controllers ]
        [Shape Assessment by Selective Fixations ]



Related Publications
  • Hulya Yalcin, Michael Black, Ronan Fablet,
    "The Dense Estimation of Motion and Appearance,"
    Second IEEE Workshop on Image and Video Registration (IVR'04) in conjunction with CVPR'04. [Abstract] [pdf]

    • Resume | Research | Main Page
    Carnegie Mellon University, Robotics Institute
    5000 Forbes Av., Pittsburgh, PA, 15213
    hulyayalcin@gmail.com