Learning Motion Analysis

    •  William T. Freeman, John A. Haddon, Egon C. Pasztor, "Learning Motion Analysis", Tech. Rep. TR2000-32, Mitsubishi Electric Research Laboratories, Cambridge, MA, September 2000.
      BibTeX TR2000-32 PDF
      • @techreport{MERL_TR2000-32,
      • author = {William T. Freeman, John A. Haddon, Egon C. Pasztor},
      • title = {Learning Motion Analysis},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2000-32},
      • month = sep,
      • year = 2000,
      • url = {}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning


We seek a learning-based algorithm that applies to various low-level vision problems. For a given problem, we want to find the scene interpretation that best explains image data. Specializing to the optical flow problem, we may want to infer the projected velocities (scene) which best explain two consecutive image frames (image). We first present the results of this method for a toy world of irregularly shaped blobs. Then we extend the technique to function on more realistic images, showing reasonable results.