Accession Number : ADA260150


Title :   Recognizing 3D Objects for 2D Images: An Error Analysis


Descriptive Note : Memorandum rept.


Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB


Personal Author(s) : Grimson, W E ; Huttenlocher, Daniel P ; Alter, T D


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a260150.pdf


Report Date : Jul 1992


Pagination or Media Count : 32


Abstract : Many recent object recognition systems use a small number of pairings of data and model features to compute the three-dimensional transformation from a model coordinate frame into the sensor coordinate system. In the case of perfect image data, these systems seem to work well. With uncertain image data, however, the performance of such methods is less well understood. In this paper, the authors examine the effects of two-dimensional sensor uncertainty on the computation of three-dimensional model transformations. They use this analysis to bound the uncertainty in the transformation parameters as well as the uncertainty associated with applying the transformation to map other model features into the image. They also examine the effects of the transformation uncertainty on the effectiveness of recognition methods.


Descriptors :   *IMAGE PROCESSING , *UNCERTAINTY , *TRANSFORMATIONS(MATHEMATICS) , *PATTERN RECOGNITION , *COMPUTER VISION , *ERROR ANALYSIS , MATHEMATICAL MODELS , ARTIFICIAL INTELLIGENCE , CARTESIAN COORDINATES , MAPPING , DETECTORS , APPROXIMATION(MATHEMATICS) , SENSITIVITY , ALIGNMENT , THREE DIMENSIONAL


Subject Categories : Numerical Mathematics
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE