Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introductory Techniques for 3-D Computer Vision
Introductory Techniques for 3-D Computer Vision
Vision-based tracking and interpretation of human leg movement for virtual reality applications
IEEE Transactions on Circuits and Systems for Video Technology
Innovative geometric pose reconstruction for marker-based single camera tracking
Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications
Multimedia Tools and Applications
| Hi-index | 0.00 |
One of the obstacles to the proliferation the VR technology to digital contents is theexpensive, intrusive, cumbersome and brittle nature of the sensors that are required to detectuser's intent. While optical tracking, being wireless with respect to the user's body, has beenregarded as one solution to this usability aspect, the traditional problems of establishingmarker correspondence and resolving their occlusions in real time still remain. One avenueof efforts to address these problems is to simply add more and more hardware (or processingpower), making the tracking system too expensive for general usage, while another majoreffort looks to directly track human body parts, but usually suffers from the inability to trackpoint features. In this paper, we present a relatively inexpensive (e.g. runs on a high-end PC),but reasonably accurate real time optical motion tracking system, called the "POSTRACK",that can still find a wide range of applications for VR. POSTRACK uses four cheap 8-bitgrayscale cameras attached with infrared LED's, and the user wears several (1~5) highlyreflective markers. The markers are "designed" to be very easy to wear (snap-on), and evenfashionable. The four cameras are calibrated using well known algorithms, and the initialmarker assignments are found by a simple heuristic based on the normal human posture,while the fundamental matrices are used to find blob correspondence and compute the 3Dpositions of the markers. Since the snap-on markers are rather large and their positions arecomputed from their image centroids (which constantly change), the computed 3D positiondata are jittery, more so than other trackers that use much smaller marker sizes, or comparedto magnetic trackers. While the technology is old (i.e. uses standard vision and stereoalgorithms), the engineering of the POSTRACK strikes a good balance between cost and itscapability, and we demonstrate this through results from using it for gesture motionrecognition and orientation tracking for 3D pointing.