Now showing items 3-7 of 7

    • An Object Recognition System for Complex Imagery that Models theProbability of a False Positive 

      Olson, Clark F.; Huttenlocher, Daniel P. (Cornell University, 1996-07)
      This paper describes an object recognition system for use in complex imagery that can perform recognition adaptively by setting the matching threshold such that the probability of a false positive is low. In order to ...
    • On Invariants of Sets of Points or Line Segments Under Projection 

      Huttenlocher, Daniel P.; Kleinberg, Jon M. (Cornell University, 1992-07)
      We consider the problem of computing invariant functions of the image of a set of points or line segments in $\Re^3$ under projection. Such functions are in principle useful for machine vision systems, because they allow ...
    • On Planar Point Matching Under Affine Transformation 

      Hopcroft, John E.; Huttenlocher, Daniel P. (Cornell University, 1989-04)
    • Tracking Non-Rigid Objects in Complex Scenes 

      Huttenlocher, Daniel P.; Noh, Jae J.; Rucklidge, William J. (Cornell University, 1992-12)
      We consider the problem of tracking non-rigid objects moving in a complex scene. We describe a model-based tracking method, in which two-dimensional geometric models are used to localize an object in each frame of an ...
    • Visually-Guided Navigation by Comparing Two-Dimensional Edge Images 

      Huttenlocher, Daniel P.; Leventon, Michael E.; Rucklidge, William J. (Cornell University, 1994-01)
      We present a method for navigating a robot from an initial position to a specified landmark in its visual field, using a sequence of monocular images. The location of the landmark with respect to the robot is determined ...