Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. The Smoothest Velocity Field and Token Matching

The Smoothest Velocity Field and Token Matching

Thumbnail Image
Download
Name

AIM-724.pdf

Size

1.03 MB

Format

Adobe PDF

Checksum (MD5)

ea6f241f843e70d81e4c8dc0cb1bf1d6

Thumbnail Image
Download
Name

AIM-724.ps

Size

1.34 MB

Format

PostScript

Checksum (MD5)

17d5083274204137f0b90f7b6431fd91

Author(s)
Yuille, A.L.
Date Issued
August 1, 1983
Series/Report no.
AIM-724
Abstract
This paper presents some mathematical results concerning the measurement of motion of contours. A fundamental problem of motion measurement in general is that the velocity field is not determined uniquely from the changing intensity patterns. Recently Hildreth & Ullman have studied a solution to this problem based on an Extremum Principle [Hildreth (1983), Ullman & Hildreth (1983)]. That is, they formulate the measurement of motion as the computation of the smoothest velocity field consistent with the changing contour. We analyse this Extremum principle and prove that it is closely related to a matching scheme for motion measurement which matches points on the moving contour that have similar tangent vectors. We then derive necessary and sufficient conditions for the principle to yield the correct velocity field. These results have possible implications for the design of computer vision systems, and for the study of human vision.
Subjects
motion measurement
velocity field
optical flow
szero crossings
motion perception
Persistent DSpace Link
http://hdl.handle.net/1721.1/5652
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.