#$%^&*AU2018250385B220201015.pdf#####ABSTRACT Video processing for motor task analysis is described. In various examples, a video of a person carrying out a motor task, such as placing the forefinger on the nose, is input to a trained machine learning system to classify the motor task into one of a plurality of classes. In an example, motion descriptors such as optical flow are computed from pairs of frames of the video and the motion descriptors are input to the machine learning system. The motor task analysis may be used to assess or evaluate neurological conditions such as multiple sclerosis and/or Parkinson's.WO 2016/038516 PCT/IB2015/056719 1/12 102 106 112 114 108 ---- -- ----- -- -VIDEO CAPTURE10 1111 IGE STREAM11 P RE-PROCES SINGPR-ROCESSED 120E,! TRAINED MACHINE LEARNING -/122 SYSTEM MOTOR TASK -. 124 S DA FIG. 1
展开▼