Accession Number:

ADA270522

Title:

Why Stereo Vision is Not Always about 3D Reconstruction

Descriptive Note:

Memorandum rept.

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

Report Date:

1993-07-01

Pagination or Media Count:

13.0

Abstract:

A common assumption of stereo vision researchers is that the goal of stereo is to compute explicit 3D information about a scene, to support activities such as navigation, hand-eye coordination and object recognition. This paper suggests reconsidering what is required of a stereo algorithm, in light of the needs of the task that uses its output. We, show that very accurate camera calibration is needed to reconstruct accurate 3D distances, and argue that often it may be difficult to attain and maintain such accuracy. We further argue that for tasks such as object recognition, separating object from background is of central importance. We suggest that stereo can help with this task, without explicitly computing 3D information. We provide a demonstration of a stereo algorithm that supports separating figure from ground through attentive fixation on key features. Stereo vision, Camera calibration, Noise sensitivity

Subject Categories:

  • Cybernetics
  • Navigation and Guidance

Distribution Statement:

APPROVED FOR PUBLIC RELEASE