Kriegman Research Group

[ Home ]   [ Personnel ]   [ Research Projects ]   [ Publications ]   [ Software ]   [ Links ]  

Structure from Motion

The goal of this work was to derive an algorithm that could be used to reconstruct the 3D geometry of a rigid scene composed of a number of straight line features using the measurements obtained from a set of calibrated cameras at unknown positions. The algorithm we have implemented recovers the positions of the features and the positions of the cameras up to a scale factor.

This package contains two files, SFM.tar.Z and DATA.tar.Z.

SFM.tar.Z (90KB) is a compressed tar file containing the code that was used to implement the 3D structure from motion algorithm described in "Structure and Motion from Line Segments in Multiple Images" (500KB). by Camillo J. Taylor and David J. Kriegman, Center for Systems Science Technical Report No. 9402b, January 1994.

DATA.tar (7.1MB of compressed images) is a tar file containing three data sets of real images and input files that were used to test this program.

Examples of the results of this algorithm.

Homotopy Continuation

Homotopy continuation is a numerical method for solving systems of n polynomial equations in n variables. It finds both real and complex roots of the system, and we have successfully used it to solve systems with up to 2000 roots for a diverse set of applications including geometric modelling, aspect graph construction, stable pose computation, etc. This is a distributed implementation that runs across a network of UNIX machines. A program invokes clients on remote UNIX workstations to solve subproblems. We have run this using Sparc Stations running Solaris and Sun UNIX, and SGI's running IRIX.

Version 1.0 of this package is contained in array-1.0.tar.Z (50KB).

Yale Face Database

The Yale Face Database (size 6.4MB) contains 165 grayscale images in GIF format of 15 individuals. There are 11 images per subject, one per different facial expression or configuration: center-light, w/glasses, happy, left-light, w/no glasses, normal, right-light, sad, sleepy, surprised, and wink.

The database is publically available for non-commercial use. In order for us to track those using it, please fill in the following form. Let us know if you have any problems.

Go to the Yale Face Database.
(NOTE: This works only with Netscape 4.75 (and below) under Windows or Linux/Unix. It will NOT work with Internet Explorer or Netscape 6.)


Updated : Sep 9 2001
Research support