Understanding Mechanical Motion: From Images To Behaviors

Tzachi Dar, Leo Joskowicz, and Ehud Rivlin.
Understanding Mechanical Motion: From Images to Behaviors.
Artif. Intell., 112(1-2):147-179, 1999

Online Version

A pdf version is available for download.

Abstract

We present an algorithm for producing behavior descriptions of planar fixed axes mechanical motions from image sequences using a formal behavior language. The language, which covers the most important class of mechanical motions, symbolically captures the qualitative aspects of objects that translate and rotate along axes that are fixed in space. The algorithm exploits the structure of these motions to robustly recover the objects behaviors. It starts by identifying the independently moving objects, their motion parameters, and their variation with respect to time using normal optical flow analysis, iterative motion segmentation, and motion parameter estimation. It then produces a formal description of their behavior by identifying individual uniform motion events and simultaneous motion changes, and parsing them with a motion grammar. We demonstrate the algorithm on three sets of image sequences: mechanisms, everyday situations, and a robot manipulation scenario.

Keywords

Co-authors

Bibtex Entry

@article{DarJR99a,
  title = {Understanding Mechanical Motion: From Images to Behaviors.},
  author = {Tzachi Dar and Leo Joskowicz and Ehud Rivlin},
  year = {1999},
  journal = {Artif. Intell.},
  volume = {112},
  number = {1-2},
  pages = {147-179},
  keywords = {Image sequence analysis; Function-based analysis; Qualitative reasoning; Mechanical motion; Mechanical devices},
  abstract = {We present an algorithm for producing behavior descriptions of planar fixed axes mechanical motions from image sequences using a formal behavior language. The language, which covers the most important class of mechanical motions, symbolically captures the qualitative aspects of objects that translate and rotate along axes that are fixed in space. The algorithm exploits the structure of these motions to robustly recover the objects behaviors. It starts by identifying the independently moving objects, their motion parameters, and their variation with respect to time using normal optical flow analysis, iterative motion segmentation, and motion parameter estimation. It then produces a formal description of their behavior by identifying individual uniform motion events and simultaneous motion changes, and parsing them with a motion grammar. We demonstrate the algorithm on three sets of image sequences: mechanisms, everyday situations, and a robot manipulation scenario.}
}