Mark Moyou, PhD

Mark Moyou, PhD

Melbourne, Florida, United States
16K followers 500+ connections

Join to follow

About

I work with Enterprise teams to get their machine-learning models into production. I also…

Articles by Mark

Contributions

Join now to see all contributions

Activity

Join now to see all activity

Experience

  • NVIDIA Graphic

    NVIDIA

    Melbourne, Florida, United States

  • -

    Atlanta, Georgia, United States

  • -

  • -

  • -

    Melbourne, Florida Area

  • -

    Melbourne, Florida, United States

  • -

  • -

  • -

    Melbourne, Florida Area

  • -

    Melbourne, Florida Area

  • -

    Melbourne, Florida Area

  • -

    Melbourne Fl

  • -

    Melbourne, Florida Area

  • -

    Melbourne, Florida Area

  • -

    Melbourne Fl

  • -

    Melbourne, Florida Area

  • -

    Melbourne Fl

Education

  • Florida Institute of Technology Graphic

    Florida Institute of Technology

    -

    Activities and Societies: Toastmasters International, IEEE, Society of Systems Engineers

    Emphasis on Machine Learning and Intelligent Systems.

    Dissertation: Geometry Driven Probabilistic Models for Shape Registration, Classification and Retrieval.

  • -

  • -

    Activities and Societies: • Tau Beta Pi Engineering Honors Society Spring2010-present • American Institute of Chemical Engineers Aug 2009- Present • President of the Florida Tech Diving Club June 2011-Present • FIT Men’s Varsity Crew Team Aug 2006-Dec 2008 President of the Florida Tech Slacklining Club Florida Tech Surf Club Florida Tech Bouldering Club

Licenses & Certifications

Volunteer Experience

  • K12 Course Instructor

    Viera Charter School

    - 2 months

    Education

    We developed coursework based on Scratch and Blockly to teach 2nd grade kids how to code. This included interactive lab sessions and homework assignments. The students ranged from 6-8 years old and there were 120 students in total. Overall it was a fantastic experience as it challenged you to related foreign concepts to the young students in an interactive way.

  • K12 Course Instructor

    Viera Charter School

    - Present 11 years 2 months

    Education

    The outcome of our effort was to teach programming to students that were 5-7 years old in order to begin filling the gap in tech talent for the future. The courses took place over 4 weeks and were interactive lab sessions.

  • Event Facilitator

    Secretknock.co

    - Present 9 years 8 months

    Economic Empowerment

    The secret knock is an exclusive gathering of people who have made significant contributions to society. The event fosters collaboration and inspires the younger generation to continue forging ground breaking paths.

    http://secretknock.co/

  • Technical Volunteer

    RE•WORK

    - Present 8 years 3 months

    Education

    Volunteering to help coordinate the Deep Learning Summit event.

Publications

  • Bayesian Fusion of Back Projected Probabilities (BFBP): Co-occurrence Descriptors for Tracking in Complex Environments

    Advanced Concepts for Intelligent Vision Systems

    Among the multitude of probabilistic tracking techniques, the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm has been one of the most popular. Though several modifications have been proposed to the original formulation of CAMSHIFT, limitations still exist. In particular the algorithm underperforms when tracking textured and patterned objects. In this paper we generalize CAMSHIFT for the purposes of tracking such objects in non-stationary backgrounds. Our extension introduces a novel…

    Among the multitude of probabilistic tracking techniques, the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm has been one of the most popular. Though several modifications have been proposed to the original formulation of CAMSHIFT, limitations still exist. In particular the algorithm underperforms when tracking textured and patterned objects. In this paper we generalize CAMSHIFT for the purposes of tracking such objects in non-stationary backgrounds. Our extension introduces a novel object modeling technique, while retaining a probabilistic back projection stage similar to the original CAMSHIFT algorithm, but with considerably more discriminative power. The object modeling now evolves beyond a single probability distribution to a more generalized joint density function on localized color patterns. In our framework, multiple co- occurrence density functions are estimated using information from several color channel combinations and these distributions are combined using an intuitive Bayesian approach. We validate our approach on several aerial tracking scenarios and demonstrate its improved performance over the original CAMSHIFT algorithm and one of its most successful variants.

    Other authors

  • A new energy minimization framework and sparse linear system for path planning and shape from shading.

    Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP)

    For over 30 years, the static Hamilton-Jacobi (HJ) equation, specifically its incarnation as the eikonal equation, has been a bedrock for a plethora of computer vision models, including popular applications such as shape-from-shading, medial axis representations, level-set segmentation, and geodesic processing (i.e. path planning). Numerical solutions to this nonlinear partial differential equation have long relied on staples like fast marching and fast sweeping algorithms— approaches which…

    For over 30 years, the static Hamilton-Jacobi (HJ) equation, specifically its incarnation as the eikonal equation, has been a bedrock for a plethora of computer vision models, including popular applications such as shape-from-shading, medial axis representations, level-set segmentation, and geodesic processing (i.e. path planning). Numerical solutions to this nonlinear partial differential equation have long relied on staples like fast marching and fast sweeping algorithms— approaches which rely on intricate convergence analysis, approximations, and specialized implementations. Here, we present a new variational functional on a scalar field comprising a spatially varying quadratic term and a standard regularization term. The Euler-Lagrange equation corresponding to the new functional is a linear differential equation which when discretized results in a linear system of equations. This approach leads to many algorithm choices since there are myriad efficient sparse linear solvers. The limiting behavior, for a particular case, of this linear differential equation can be shown to converge to the nonlinear eikonal. In addition, our approach eliminates the need to explicitly construct viscosity solutions as customary with direct solutions to the eikonal. Though our solution framework is applicable to the general class of eikonal problems, we detail specifics for the popular vision applications of shapefrom-shading, vessel segmentation, and path planning. We showcase experimental results on a variety of images and complex mazes, in which we hold our own against state-ofthe art fast marching and fast sweeping techniques, while retaining the considerable advantages of a linear systems approach.

    Other authors
    See publication

  • LBO-Shape Densities: Efficient 3D Shape Retrieval Using Wavelet Density Estimation

    21st International Conference on Pattern Recognition (ICPR). (Oral Presentation)

    Driven by desirable attributes such as topological characterization and invariance to isometric transformations, the use of the Laplace-Beltrami operator (LBO) and its associated spectrum have been widely adopted among the shape analysis community. Here we demonstrate a novel use of the LBO for shape matching and retrieval by estimating probability densities on its Eigen space, and subsequently using the intrinsic geometry of the density manifold to categorize similar shapes. In our framework…

    Driven by desirable attributes such as topological characterization and invariance to isometric transformations, the use of the Laplace-Beltrami operator (LBO) and its associated spectrum have been widely adopted among the shape analysis community. Here we demonstrate a novel use of the LBO for shape matching and retrieval by estimating probability densities on its Eigen space, and subsequently using the intrinsic geometry of the density manifold to categorize similar shapes. In our framework, each 3D shape's rich geometric structure, as captured by the low order eigenvectors of its LBO, is robustly characterized via a nonparametric density estimated directly on these eigenvectors. By utilizing a probabilistic model where the square root of the density is expanded in a wavelet basis, the space of LBO-shape densities is identifiable with the unit hyper sphere. We leverage this simple geometry for retrieval by computing an intrinsic Karcher mean (on the hyper sphere of LBO-shape densities) for each shape category, and use the closed-form distance between a query shape and the means to classify shapes. Our method alleviates the need for superfluous feature extraction schemes-required for popular bag-of-features approaches-and experiments demonstrate it to be robust and competitive with the state-of-the-art in 3D shape retrieval algorithms.

    Other authors
    See publication

  • Shape Analysis on the Hypersphere of Wavelet Densities

    21st International Conference on Pattern Recognition (ICPR), 2012. (Oral Presentation)

    We present a novel method for shape analysis which represents shapes as probability density functions and then uses the intrinsic geometry of this space to match similar shapes. In our approach, shape densities are estimated by representing the square-root of the density in a wavelet basis. Under this model, each density (of a corresponding shape) is then mapped to a point on a unit hypersphere. For each category of shapes, we find the intrinsic Karcher mean of the class on the hypersphere of…

    We present a novel method for shape analysis which represents shapes as probability density functions and then uses the intrinsic geometry of this space to match similar shapes. In our approach, shape densities are estimated by representing the square-root of the density in a wavelet basis. Under this model, each density (of a corresponding shape) is then mapped to a point on a unit hypersphere. For each category of shapes, we find the intrinsic Karcher mean of the class on the hypersphere of shape densities, and use the minimum spherical distance between a query shape and the means to classify shapes. Our method is adaptable to a variety of applications, does not require burdensome preprocessing like extracting closed curves, and experimental results demonstrate it to be competitive with contemporary shape matching algorithms.

    See publication

Courses

  • Computer Graphics

    -

  • Data Mining

    -

  • Decision and Risk Analysis

    -

  • Digital Image Processing

    -

  • Neural Networks

    -

  • Research Methods

    -

  • Simulation and Modeling

    -

  • Systems Engineering Principles

    -

  • Technology Commercialization Strategy

    -

Languages

  • English

    -

More activity by Mark

View Mark’s full profile

  • See who you know in common
  • Get introduced
  • Contact Mark directly
Join to view full profile

Other similar profiles

Explore more posts

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses

See all courses