Personal Info:

I have graduated from the Computer Vision Lab at the University of Maryland and am now a post-doctoral researcher in the Real-time Vision and Modeling Group at Siemens Corporate Research in Princeton, NJ. There I currently work on pedestrian detection in far-infrared images captured from a moving car.

You can contact me at my new place under the phone number 609 734 3653 or by email firstname.lastname@siemens.com.

Doctoral Research (Research statement):

I am interested in the geometry and statistics of visual space-time, i.e. representations of 3D shape and movement that can be extracted from images. This work has applications in many areas of computer vision and graphics, for example it lead to

•  a better understanding of the geometric structure of the space of light rays ,
•  the design of novel image sensors, and the development of new vision algorithms that utilize the special properties of these new sensors (example 3D structure from motion),
•  new approaches to capture and analyze the 3D shape and motion of non-rigidly moving humans and objects,
•  and methods rooted in geometry and statistics to track independently moving objects in videos.

More detailed information about my research can be found on my research overview page, my research statement and in my publications.

Selected publications that best represent my work

    1. Plenoptic video geometry.

      Jan Neumann and Cornelia Fermüller. Visual Computer, Volume 19, Number 6, Pages 395-404, October 2003.
      (Link to published paper) (Link to preprint)

    2. Eye Design in the Plenoptic Space of Light Rays

      Jan Neumann, Cornelia Fermüller, and Yiannis Aloimonos. Ninth IEEE International Conference on Computer Vision, Volume 2, pages 1160-1167, Nice, France, October 13-16 2003.
      (Link to published paper) (Link to preprint)

    3. Polydioptric Camera Design and 3D Motion Estimation

      Jan Neumann, Cornelia Fermüller, and Yiannis Aloimonos. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, pages 294-301, Madison, Wisconsin, June 16-22, 2003.
      (Link to published paper) (Link to preprint)

    4. Spatio-temporal stereo using multi-resolution subdivision surfaces.

      Jan Neumann and Yiannis Aloimonos.
      International Journal of Computer Vision, 47(1/2/3):181-193, 2002.
      (Link to published paper) (Link to preprint)

  • A link to my other publications

 

PhD Thesis: "COMPUTER VISION IN THE SPACE OF LIGHT RAYS : PLENOPTIC VIDEO GEOMETRY AND POLYDIOPTRIC CAMERA DESIGN"

Abstract: Most of the cameras used in computer vision, computer graphics, and image processing applications are designed to capture images that are similar to the images we see with our eyes. This enables an easy interpretation of the visual information by a human observer. Nowadays though, more and more processing of visual information is done by computers. Thus, it is worth questioning if these human inspired ``eyes'' are the optimal choice for processing visual information using a machine. In this thesis I describe how one can study problems in computer vision without reference to a specific camera model by studying the geometry and statistics of the space of light rays that surrounds us. The study of the geometry will allow us to determine all the possible constraints that exist in the visual input and could be utilized if we had a perfect sensor. Since no perfect sensor exists we use signal processing techniques to examine how well the constraints between different sets of light rays can be exploited given a specific camera model. A camera is modeled as a spatio-temporal filter in the space of light rays which lets us express the image formation process in a function approximation framework. This framework then allows us to relate the geometry of the imaging camera to the performance of the vision system with regard to the given task. In this thesis I apply this framework to problem of camera motion estimation. I show how by choosing the right camera design we can solve for the camera motion using linear, scene-independent constraints that allow for robust solutions. This is compared to motion estimation using conventional cameras. In addition we show how we can extract spatio-temporal models from multiple video sequences using multi-resolution subdivison surfaces. (Thesis in PDF format, 11.5MB).

Teaching:

In Fall 2002 I cotaught the class CMSC828Z - 3D Photography and Inverse Rendering. In this class we talked about how computer vision and computer graphics can mutually benefit from eachother since one can be interpreted as the inverse problem of the other. Specifically, I talked about how computer graphics transforms our models of the world into images (Rendering and Animation), and how computer vision allows us to infer models of the world based on these images (3D Photography and Motion Capture). More information about my teaching philosophy can be found in my teaching statement.

"The reasonable man adapts himself to the world; the unreasonable one persists in trying to adapt the world to himself. Therefore all progress depends on the unreasonable man." G.B. Shaw