Tag generation for human activity identification

Abstract

The invention relates to tag generation for human activity recognition. Video data (121, 122, 123) depicting a human body or a body part is obtained. Based on the video data, a time-resolved simplified graphical representation of the human body part is generated (190). Based on the time-resolved simplified graphical representation, a tag associated with the activity of the human body or body part is determined (129). Such tags may be used to populate training datasets that may later be used to train machine learning models based on sensor data observing a human body or body part, such as for gesture classification, fall detection, or other tasks.

Images