Tracking the path shape qualities of human motion

Kai Tu, Harvey Thornburg, Matthew Fulmer, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We propose a probabilistic generative model for extracting intended path shape qualities of an object moving under human control in real time. At each instant, we decide whether the object is moving in a straight, curved, or random path, or whether it has stopped moving. Our model incorporates sensor noise as well as human imperfections in the intended motion. As well as tracking the object's position, velocity, and motion direction, we compute the posterior probability of each shape quality hypothesis given all sensed-data in the horizon [t -N + 1, t]; the hypothesis maximizing this posterior is taken as the decision. The posterior is computed using the unscented Kaiman filter (UKF), as our model is inherently nonlinear. The path-shape quality tracking is successfully embedded in a hybrid physical-digital interface where the position of an illuminated ball, sensed by a low-cost video camera array, triggers multimodal feedback in a mediated learning environment. We show successful results on a variety of real-world motion paths where the participant is given only verbal descriptions of how to move. Our generative model is further validated by user studies involving a simple color-based interaction, where participants discover shape quality controls as they interact.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
DOIs
StatePublished - 2007
Event2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, United States
Duration: Apr 15 2007Apr 20 2007

Other

Other2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
CountryUnited States
CityHonolulu, HI
Period4/15/074/20/07

Fingerprint

Video cameras
Quality control
quality control
learning
Color
horizon
Feedback
balls
Defects
actuators
cameras
Sensors
color
filters
Costs
sensors
defects
interactions
Statistical Models

Keywords

  • Activity analysis
  • Computer vision
  • Human motion analysis
  • Human-computer interaction
  • Hybrid physical-digital environment
  • Multimedia signal processing
  • Natural information interface
  • Unscented Kalman filter
  • Video sensing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Tu, K., Thornburg, H., Fulmer, M., & Spanias, A. (2007). Tracking the path shape qualities of human motion. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 2). [4217525] https://doi.org/10.1109/ICASSP.2007.366352

Tracking the path shape qualities of human motion. / Tu, Kai; Thornburg, Harvey; Fulmer, Matthew; Spanias, Andreas.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2 2007. 4217525.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tu, K, Thornburg, H, Fulmer, M & Spanias, A 2007, Tracking the path shape qualities of human motion. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 2, 4217525, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, Honolulu, HI, United States, 4/15/07. https://doi.org/10.1109/ICASSP.2007.366352
Tu K, Thornburg H, Fulmer M, Spanias A. Tracking the path shape qualities of human motion. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2. 2007. 4217525 https://doi.org/10.1109/ICASSP.2007.366352
Tu, Kai ; Thornburg, Harvey ; Fulmer, Matthew ; Spanias, Andreas. / Tracking the path shape qualities of human motion. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2 2007.
@inproceedings{6c8b758cdf244685af53d66b1e3e73db,
title = "Tracking the path shape qualities of human motion",
abstract = "We propose a probabilistic generative model for extracting intended path shape qualities of an object moving under human control in real time. At each instant, we decide whether the object is moving in a straight, curved, or random path, or whether it has stopped moving. Our model incorporates sensor noise as well as human imperfections in the intended motion. As well as tracking the object's position, velocity, and motion direction, we compute the posterior probability of each shape quality hypothesis given all sensed-data in the horizon [t -N + 1, t]; the hypothesis maximizing this posterior is taken as the decision. The posterior is computed using the unscented Kaiman filter (UKF), as our model is inherently nonlinear. The path-shape quality tracking is successfully embedded in a hybrid physical-digital interface where the position of an illuminated ball, sensed by a low-cost video camera array, triggers multimodal feedback in a mediated learning environment. We show successful results on a variety of real-world motion paths where the participant is given only verbal descriptions of how to move. Our generative model is further validated by user studies involving a simple color-based interaction, where participants discover shape quality controls as they interact.",
keywords = "Activity analysis, Computer vision, Human motion analysis, Human-computer interaction, Hybrid physical-digital environment, Multimedia signal processing, Natural information interface, Unscented Kalman filter, Video sensing",
author = "Kai Tu and Harvey Thornburg and Matthew Fulmer and Andreas Spanias",
year = "2007",
doi = "10.1109/ICASSP.2007.366352",
language = "English (US)",
isbn = "1424407281",
volume = "2",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Tracking the path shape qualities of human motion

AU - Tu, Kai

AU - Thornburg, Harvey

AU - Fulmer, Matthew

AU - Spanias, Andreas

PY - 2007

Y1 - 2007

N2 - We propose a probabilistic generative model for extracting intended path shape qualities of an object moving under human control in real time. At each instant, we decide whether the object is moving in a straight, curved, or random path, or whether it has stopped moving. Our model incorporates sensor noise as well as human imperfections in the intended motion. As well as tracking the object's position, velocity, and motion direction, we compute the posterior probability of each shape quality hypothesis given all sensed-data in the horizon [t -N + 1, t]; the hypothesis maximizing this posterior is taken as the decision. The posterior is computed using the unscented Kaiman filter (UKF), as our model is inherently nonlinear. The path-shape quality tracking is successfully embedded in a hybrid physical-digital interface where the position of an illuminated ball, sensed by a low-cost video camera array, triggers multimodal feedback in a mediated learning environment. We show successful results on a variety of real-world motion paths where the participant is given only verbal descriptions of how to move. Our generative model is further validated by user studies involving a simple color-based interaction, where participants discover shape quality controls as they interact.

AB - We propose a probabilistic generative model for extracting intended path shape qualities of an object moving under human control in real time. At each instant, we decide whether the object is moving in a straight, curved, or random path, or whether it has stopped moving. Our model incorporates sensor noise as well as human imperfections in the intended motion. As well as tracking the object's position, velocity, and motion direction, we compute the posterior probability of each shape quality hypothesis given all sensed-data in the horizon [t -N + 1, t]; the hypothesis maximizing this posterior is taken as the decision. The posterior is computed using the unscented Kaiman filter (UKF), as our model is inherently nonlinear. The path-shape quality tracking is successfully embedded in a hybrid physical-digital interface where the position of an illuminated ball, sensed by a low-cost video camera array, triggers multimodal feedback in a mediated learning environment. We show successful results on a variety of real-world motion paths where the participant is given only verbal descriptions of how to move. Our generative model is further validated by user studies involving a simple color-based interaction, where participants discover shape quality controls as they interact.

KW - Activity analysis

KW - Computer vision

KW - Human motion analysis

KW - Human-computer interaction

KW - Hybrid physical-digital environment

KW - Multimedia signal processing

KW - Natural information interface

KW - Unscented Kalman filter

KW - Video sensing

UR - http://www.scopus.com/inward/record.url?scp=34547499401&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547499401&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2007.366352

DO - 10.1109/ICASSP.2007.366352

M3 - Conference contribution

SN - 1424407281

SN - 9781424407286

VL - 2

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -