Part ofAdvances in Neural Information Processing Systems 15 (NIPS 2002)
Jakob Heinzle, Alan Stocker
We report a system that classifies and can learn to classify patterns of visual motion on-line. The complete system is described by the dynam- ics of its physical network architectures. The combination of the fol- lowing properties makes the system novel: Firstly, the front-end of the system consists of an aVLSI optical flow chip that collectively computes 2-D global visual motion in real-time [1]. Secondly, the complexity of the classification task is significantly reduced by mapping the continu- ous motion trajectories to sequences of ’motion events’. And thirdly, all the network structures are simple and with the exception of the optical flow chip based on a Winner-Take-All (WTA) architecture. We demon- strate the application of the proposed generic system for a contactless man-machine interface that allows to write letters by visual motion. Re- garding the low complexity of the system, its robustness and the already existing front-end, a complete aVLSI system-on-chip implementation is realistic, allowing various applications in mobile electronic devices.
Requests for name changes in the electronic proceedings will be accepted with no questions asked. However name changes may cause bibliographic tracking issues. Authors are asked to consider this carefully and discuss it with their co-authors prior to requesting a name change in the electronic proceedings.
Use the "Report an Issue" link to request a name change.