The schematic of cwCST-image based gesture recognition method. (IMAGE)
Caption
The recorded HD-sEMG are decomposed into channel-wise CSTs, transformed into cwCST-image according to the channel distribution, and decoded to different gestures by CNN-based model. The CSTs in each channel comprise the discharges of motor units adjacent to the corresponding electrode, represented by bars and circles in different colors.
Credit
Yang Yu, Shanghai Jiao Tong University.
Usage Restrictions
News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.
License
Licensed content