Skip to content

← ArchivePaper2004

Automated Extraction and Parameterization of Motions in Large Data Sets

Lucas Kovar, Michael Gleicher

Discovers logically similar motion variants in large capture databases and builds continuous parameterized motion families automatically.

Abstract

Large motion data sets often contain many variants of the same kind of motion, but without appropriate tools it is difficult to fully exploit this fact. This paper provides automated methods for identifying logically similar motions in a data set and using them to build a continuous and intuitively parameterized space of motions. To find logically similar motions that are numerically dissimilar, our search method employs a novel distance metric to find "close" motions and then uses them as intermediaries to find more distant motions. Search queries are answered at interactive speeds through a precomputation that compactly represents all possibly similar motion segments. Once a set of related motions has been extracted, we automatically register them and apply blending techniques to create a continuous space of motions. Given a function that defines relevant motion parameters, we present a method for extracting motions from this space that accurately possess new parameters requested by the user. Our algorithm extends previous work by explicitly constraining blend weights to reasonable values and having a run-time cost that is nearly independent of the number of example motions. We present experimental results on a test data set of 37,000 frames, or about ten minutes of motion sampled at 60 Hz.

How to read this

Category
Method: motion-data search and parameterization
Contributions
  • Automated identification of logically similar motions using a novel distance metric plus intermediary motions to bridge numerically dissimilar but related clips
  • Interactive-speed search via a precomputation that compactly represents all possibly similar motion segments
  • Automatic registration and blending into a continuously, intuitively parameterized motion space, with blend weights constrained to reasonable values and run-time cost nearly independent of example count
Context
Extends data-driven motion synthesis built on motion databases (notably Kovar and Gleicher's Motion Graphs) from connecting clips toward extracting and parameterizing families of similar motions.Builds on: Motion Graphs
Correctness
Relies on a distance metric and chained intermediaries to capture logical similarity, and on blending staying valid within the constrained weight range; readers should remember accuracy of requested parameters depends on the example coverage and the user-supplied parameter function.
Clarity
Clearly written; a first pass conveys the search-then-parameterize pipeline, a second pass is needed for the distance metric, precomputation, and registration/blending details.
How to read it
Focus on the distance metric and the intermediary-based search, then on how the parameterized space is built; a second pass pays off if you want interactive query or controllable blending.

Builds on

Built upon by

Nothing yet.

Related work

Keywords

This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →