Space-time gestures
Trevor Jackson Darrell, Alex Pentland · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2002
A method for learning, tracking, and recognizing human gestures using a view-based approach to model articulated objects is presented. Objects are represented using sets of view models, rather than single templates. Stereotypical space-time patterns, i.e., gestures, are then matched to stored gesture patterns using dynamic time warping. Real-time performance is achieved by using special purpose correlation hardware and view prediction to prune as much of the search space as possible. Both view models and view predictions are learned from examples. Results showing tracking and recognition of human hand gestures at over 10 Hz are presented.>
Cited by 353 works. doi:10.1109/cvpr.1993.341109
Authors
References
- Dynamic programming algorithm optimization for spoken word recognition
- Recognition by linear combinations of models
- Vector quantization in speech coding
- A network that learns to recognize three-dimensional objects
- Intelligible encoding of ASL image sequences at extremely low information rates
- Real-Time Detection of Pointing Actions for a Glove-Free Interface.
- Qualitative visual interpretation of 3D hand gestures using motion parallax
- Real time hand shape recognition using pipe-line image processor
- Human-interface by recognition of human gesture with image processing-recognition of gesture to specify moving direction
- VIEW-BASED RECOGNITION