GSCT UVR LAB.
UVR Lab. was formed in Feb. 2001 at GIST to study and develop “Virtual Reality in Smart computing environments” that process multimodal input, perceive user’s intention and emotion, and respond to user’s request through Augmented Reality. Since 2012, UVR Lab moved to KAIST GSCT and restarted with a theme of “FUN in Ubiquitous VR.”
 
작성일 : 12-04-09
Barcode-assisted Planar Object Tracking Method for Mobilde Augmented Reality
 글쓴이 : UVR
조회 : 5,453  


Uploaded by GIST CTI on Nov. 25, 2011
 
We propose a planar target tracking method that exploits a barcode containing information about the target. Our method combines both barcode detection and natural feature tracking methods to track a planar object efficiently on mobile devices. A planar target is detected by recognizing the barcode located near the target, and the target's keypoints are tracked in video sequences. We embed the information related to a planar object into the barcode, and the information is used to limit image regions to perform keypoint matching between consecutive frames. We show how to detect a barcode robustly and what information is embedded for efficient tracking. Our detection method runs at 30 fps on modern mobile devices, and it can be used for mobile augmented reality applications using planar targets.