Abstract | ||
---|---|---|
We developed a system which performs 3D motion tracking of human's hand and fingers from images of a single high-frame-rate camera and that recognizes his/her typing motion in the air. Our template-matching-based method using hand textures reduces background effect and enables markerless tracking. In addition, use of a high-frame-rate camera enables recognition of rapid typing motion which is difficult to track using standard cameras. In order to realize real-time recognition, we developed hardware which parallelizes and accelerates image processing. As a result, we achieved real-time recognition of typing motion with the throughput of 138 fps (frames per second) and the latency of 29 ms. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1520340.1520564 | CHI Extended Abstracts |
Keywords | Field | DocType |
markerless tracking,rapid typing motion,motion tracking,in-air typing interface,background effect,single high-frame-rate camera,real-time recognition,typing motion,standard camera,high-frame-rate camera,hand texture,template matching,tracking system,embedded computing,real time,frames per second,image processing | Computer vision,Latency (engineering),Computer science,Finger tracking,Image processing,Tracking system,Typing,Frame rate,Artificial intelligence,Throughput,Match moving | Conference |
Citations | PageRank | References |
11 | 0.62 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kazuhiro Terajima | 1 | 11 | 0.96 |
Takashi Komuro | 2 | 157 | 37.65 |
Masatoshi Ishikawa | 3 | 61 | 9.33 |