Main / Research




Projects

Current

Synchronous Sonification of Human Motion

We have an on-going interest in turning human motion into sound for feedback to athletes.





In Situ Motion Capture of High-Speed Athletics

The advent of the Kinect depth imager has opened the door to motion capture applications that would have been much more costly with previous technologies. In part, the Kinect achieves this by focusing on a very specific application domain, thus narrowing the requirement for the motion capture system. Specifically, Kinect motion capture works best within a small physical space while the camera is stationary. We seek to extend Kinect motion capture for use in athletic training -- speed skating in particular -- by placing the Kinect on a mobile, robotic platform to capture motion in situ. Athletes move over large distances, so the mobile platform addresses the limited viewing area of the Kinect. As the platform moves, we must also account for the now dynamic background against which the athlete performs. The result is a novel, visually-guided robotic platform that follows athletes, allowing us to capture motion and images that would not be possible with a treadmill.

Examples



Video Interaction with Motion Swarms

We wanted an audience at a sporting event to be able to interact with Swarm Art. It is not feasible to track or recognize gestures in this scenario. This is how we solved the problem.

Download the quicktime movie.


We've created mechanisms to add more finesse to motion swarm interaction by building GUI-style widgets from constrained particle motions.

Download the quicktime movie.


Video games is a potential application of motion swarm interaction. This example shows Poetry Pong, a pong game that produced Markov Model poems (rained with Coleridge in this case). A motion swarm particle acts as a start button in the upper left. Another particle provides a slider for the human-controlled player at the top.



Cooperative Robots for Surveillance

We're building a fleet of small surveillance robots built on a Superdroid platform. The goal is to test and demonstrate a multi-agent system for harbor surveillance and security. The fleet is now operational. The demo video shows four of our ten Superdroids operating simultaneously.


This video shows Mark 0 following some way points around the courtyard outside the ICT building at U of Calgary, 16 July 2009.



Interactive Art and Swarm Art

Jerry Hushlak, Christian Jacob, and I have collaborated to create a number of interactive art installations. We are still working to create more. The image on the right is the cover of the June 2007 edition of Leonardo featuring one of us playing with our first Swarm Art installation in the lab shortly before moving it to the Nickle Art Gallery.

See some of our installations.



Old Stuff

Video Information Servers

A video information server is a device that provides information about scene. The information is either video images, or data extracted from video images. Information extracted from the video images can include descriptions of moving objects, their trajectories, and camera properties. Our servers use CaML (Camera Markup Language), an XML-based language for interaction with video cameras. CaML shares some features with MPEG-7, but it is simpler, designed for bi-direction interaction with a camera, and tailored for use in real-time systems that operate as events occur. The client acquires data from a CaML server, and uses the data in any way that is desired.

Examples

Some examples of things we built with Video Information Servers.



Phase Analysis of Running Gaits

This project was done by Nathan Kendrick, graduate of the lab. Nathan examined the phase signatures of running gaits for athletes and non-athletes.



Binary Restoration of Thin Objects

Detection of concealed objects, such as explosives or illegal drugs, using X-rays is confounded when the object is formed into a thin sheet. We have explored the potential of binary image restoration to detect such thin objects in two- and three-dimensional images. The use of a weighted mean-square error estimate to perform the restoration optimizes the restoration to place emphasis on the infrequent, but significant local structure of the thin objects. Experimental results show the restoration of thin lines and curves in two-dimensional data, and thin sheets in three-dimensional tomographic data.



Shape of Motion

We have developed a novel vision system that can recognize people by the way they walk. The system computes optical flow for an image sequence of a person walking, and then characterizes the shape of the motion with a set of sinusoidally-varying scalars. Feature vectors composed of the phases of the sinusoids are able to discriminate among people.




Publications

Journal Papers

Book Chapters

  • J. Boyd, I. A. T. Popa, M. Ritter, F. Sallis, The creative potential of digital technology for music education in the twenty-first century, Ed. Paolo Somigli, La musica del Novecento: una risorsa per la scuola, Strumenti, proposte, riflessioni, FrancoAngeli, Milano, in press.
  • J. E. Boyd and J. J. Little, Silhouette-based gait recognition, in Encyclopedia of Biometrics, S. Z. Li (ed.), Springer, p646-652, 2009.
  • J. Boyd and J. Little, Biometric Gait Recognition, in Advanced Studies in Biometrics: Summer School on Biometrics , Alghero Italy, June 2-6, 2003. Revised Selected Lectures and Papers, Editors:Massimo Tistarelli, Josef Bigun, Enrico Grosso, Lecture Notes in Computer Science, Vol. 3161/2005, Springer, 2005, p 19-42.
  • J. Boyd and J. Little, Shape of Motion and the Perception of Human Gaits, Proceedings of IEEE Workshop on Empirical Evaluation Methods in Computer Vision, CVPR 98, Santa Barbara, CA, June 1998, p155-171.

Conference Proceedings

Page last modified on April 25, 2019, at 01:40 PM