Name
Abstract | ||
|---|---|---|
Hand gestures are examples of fast and complex motions. Computers fail to track these in fast video, but sleight of hand fools humans as well: what happens too quickly we just cannot see. We show a 3D tracker for these types of motions that relies on the recognition of familiar configurations in 2D images (classification), and fills the gaps in-between (interpolation). We illustrate this idea with experiments on hand motions similar to finger spelling. The penalty for a recognition failure is often small: if two configurations are confused, they are often similar to each other, and the illusion works well enough, for instance, to drive a graphics animation of the moving hand. We contribute advances in both feature design and classifier training: our image features are invariant to image scale, translation, and rotation, and we propose a classification method that combines VQPCA with discrimination trees. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1109/ICCV.2003.1238659 | Nice, France |
Keywords | Field | DocType |
discrimination tree,experimentson hand,complex motion,recognition failure,image feature,fast video,image scale,classification methodthat,hand gesture,classifier training,machine vision,gesture recognition,image classification,object recognition,translation,computer vision,feature extraction,interpolation,image features,human computer interaction,image recognition,rotation,stereo vision | Graphics,Computer vision,Pattern recognition,Feature (computer vision),Computer science,Interpolation,Gesture recognition,Feature extraction,Animation,Artificial intelligence,Contextual image classification,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7695-1950-4 | 41 | 2.35 |
References | Authors | |
14 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Carlo Tomasi | 1 | 8314 | 679.81 |
| Slav Petrov | 2 | 2405 | 107.56 |
| Arvind Sastry | 3 | 41 | 2.35 |