Project title: 3D Pose Recovery of the Human Arm
Student: Daniel Deluca-Cardillo
Supervisor: Dr. Du Huynh
Organisation: The University of Western Australia
School of Computer Science and Software Engineering
Motion capture is the process of digitally recording the movement of a human subject. This technology has useful applications in the areas of computer animation and bio-mechanics. Current commercial systems use markers to track motion and, because of this, are restricted in their use. Markerless systems can potentially facilitate new applications of motion capture due to their ability to capture from standard video footage or without specialized equipment. These include animation, rehabilitation, gesture recognition, sign language recognition, and surveillance.
Markerless motion capture is under intensive research at institutions around the world. Because of the large uncertainty when dealing with a single video sequence or even multiple video sequences, research has focused on advanced computer vision techniques, with particle filtering being the most successful.
The system developed for this project uses a specific filtering technique to recover the 3D pose of a human arm from a single video sequence. This task is extremely challenging due to the difficulty of interpreting the limited depth cues found in a 2D image (video frame). Further research based on this project has already begun and will be extended into full-body and multi-camera motion capture.
Daniel Deluca-Cardillo is a student at The University of Western Australia currently completing a combined degree in Bachelor of Computer and Mathematical Science (BCM) / Bachelor of Engineering (BE). This research project was conducted as a requirement for Daniel's BCM honours degree but also contributes preliminary work towards an ARC (Australian Research Council) Discovery Project commencing in 2007. The Chief investigators of this project are Assoc. Prof. Mohammed Bennamoun, Dr. Du Huynh, and Prof. Robyn Owens.
|
