Skip to main content

4 Result(s)

within Jun-Sik Kim Remove this filter Image Processing and Computer Vision Remove this filter

and

  1. No Access

    Article

    Online Approximate Model Representation Based on Scale-Normalized and Fronto-Parallel Appearance

    Various object representations have been widely used for many tasks such as object detection, recognition, and tracking. Most of them requires an intensive training process on large database which is collected...

    Kiho Kwak, Jun-Sik Kim, Daniel F. Huber… in International Journal of Computer Vision (2016)

  2. No Access

    Article

    Degeneracy of the Linear Seventeen-Point Algorithm for Generalized Essential Matrix

    In estimating motions of multi-centered optical systems using the generalized camera model, one can use the linear seventeen-point algorithm for obtaining a generalized essential matrix, the counterpart of the...

    Jun-Sik Kim, Takeo Kanade in Journal of Mathematical Imaging and Vision (2010)

  3. No Access

    Chapter and Conference Paper

    Semi-metric Space: A New Approach to Treat Orthogonality and Parallelism

    We propose a new method to recover 3D structures of artificial objects from scene pictures using orthogonality and parallelism. A new transformation group, “semi-metric space,” is defined to describe the scene...

    Jun-Sik Kim, In So Kweon in Computer Vision – ACCV 2006 (2006)

  4. No Access

    Chapter and Conference Paper

    Infinite Homography Estimation Using Two Arbitrary Planar Rectangles

    In this paper, we propose a new method to estimate an infinite homography between two views containing two arbitrary planar rectangles. The proposed method does not require metric measurements, such as rectang...

    Jun-Sik Kim, In So Kweon in Computer Vision – ACCV 2006 (2006)