Acquiring in situ training data for context-aware ubiquitous computing applications
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Using dynamic time warping for online temporal fusion in multisensor systems
Information Fusion
An automatic segmentation technique in body sensor networks based on signal energy
BodyNets '09 Proceedings of the Fourth International Conference on Body Area Networks
Reconfigurable natural interaction in smart environments: approach and prototype implementation
Personal and Ubiquitous Computing
Hi-index | 0.00 |
We present results on the recognition of intentional humangestures for video annotation and retrieval. We definea gesture as a particular, repeatable, human movementhaving a predefined meaning. An obvious application ofthe work is in sports video annotation where umpire gesturesindicate specific events. Our approach is to augmentvideo with data obtained from accelerometers worn as wristbands by one or more officials. We present the recognitionperformance using a Hidden Markov Model approach forgesture modeling with both isolated gestures and gesturessegmented from a stream.