LOW-LATENCY GESTURE DETECTION

摘要

Low-latency gesture detection is described, for example, to compute a gesture class from a live stream of image frames of a user making a gesture, for example, as part of a natural user interface controlling a game system or other system. In examples, machine learning components are trained to learn gesture primitives and at test time, are able to detect gestures using the learned primitives, in a fast, accurate manner. For example, a gesture primitive is a latent (unobserved) variable describing features of a subset of frames from a sequence of frames depicting a gesture. For example, the subset of frames has many fewer frames than a sequence of frames depicting a complete gesture. In various examples gesture primitives are learnt from instance level features computed by aggregating frame level features to capture temporal structure. In examples frame level features comprise body position and body part articulation state features.

主权项

1. A gesture recognition method comprising:
receiving, at a processor, an input stream of image frames depicting an articulating entity; computing features from individual ones of the image frames and sending the computed features to a trained machine learning system; and receiving in response at least one gesture class from a plurality of possible gesture classes; wherein the individual ones of the image frames are fewer than a number of the image frames depicting a complete gesture of the gesture class made by the articulated entity.