Rapid Finger Motion Tracking on Low-Power Mobile Environments for Large Screen Interaction
Motion and gesture are garnering significant interest as the sizes of screens are getting larger. To provide lightweight finger motion tracking on low-power mobile environments, we propose an approach that breaks down the stereotypes of camera view points. By directing the camera view angle towards the ceiling, the proposed approach can reduce the problem complexity incurred by complicated background environments. Though this change incurs poor lighting conditions for image processing, by clustering and tracking the fragmented motion blobs from the motion image of the saturation channel, rapid finger motion can be tracked efficiently with low computational load. We successfully implemented and tested the proposed approach on a low-power mobile device with a 1.5 GHz mobile processor and a low specification camera with a capture rate of under 15 fps.
KeywordsMotion tracking Mobile environment Remote interface
- 1.Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. In: TPAMI (2001)Google Scholar
- 2.de La Gorce, M., Fleet, D.J., Paragios, N.: Model-based 3D hand pose estimation from monocular video. In: TPAMI (2011)Google Scholar
- 3.Sharp, T., Keskin, C., Robertson, D., Taylor, J., Shotton, J.: Accurate, robust, and flexible real-time hand tracking. In: CHI (2015)Google Scholar
- 4.Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)Google Scholar
- 5.Stenger, B., Thayananthan, A., Torr, P.H., Cipolla, R.: Model-based hand tracking using a hierarchical Bayesian filter. In: TPAMI (2006)Google Scholar