A gesture segmentation recognition method and system for automatically detecting non-gesture patterns

Abstract

The invention discloses a gesture segmentation recognition method capable of detecting non-gesture modes automatically and a gesture segmentation recognition system. The gesture segmentation recognition method includes multiple steps, a first step is that a gesture recognition model is trained based on heterogeneous data acquired by a camera and a sensor, the gesture recognition model is used for constructing a threshold model, and the gesture recognition model and the threshold model constitute a gesture segmentation model; a second step is that the gesture segmentation model is used for automatically detecting non-gesture modes from an input continuous action sequence; a third step is that the non-gesture modes are used for training a non-gesture recognition model; and a fourth step is that the gesture segmentation model is expanded based on the non-gesture recognition model and used for segmentation recognition of the input continuous action sequence. Due to the gesture segmentation recognition method capable of detecting the non-gesture modes automatically, the gesture segmentation recognition system can well represent the non-gesture modes, the probability that the non-gesture modes are misjudged to gesture modes is reduced, and accuracy of a gesture segmentation algorithm is improved.

Description

technical field [0001] The invention belongs to the field of human-computer interaction, in particular to a gesture segmentation and recognition method and system for automatically detecting non-gesture patterns. Background technique [0002] Human-computer interaction is an interdisciplinary subject involving many professional backgrounds such as computer science, behavioral psychology, social ethics, graphic interface design, and industrial design. It takes user experience as the ultimate goal and serves as a bridge connecting humans and computers. With the improvement of computer technology and the continuous expansion of production needs in different fields of society and people's living needs, new intelligent human-computer interaction methods have become inevitable. Among the various ways of human-computer interaction, gestures are one of the most natural, intuitive and easy-to-learn ways. Gesture interaction technology with intelligent perception of action semantics ...

AI Technical Summary

Problems solved by technology

However, only the general threshold model is used as the adaptive likelihood threshold, and those complex non-gesture action sequences are likely to be misjudged as gesture action sequences, because the general threshold model is only a combination of all states of all gesture models in the system. A fully connected traversal model, it can only match the pattern composed of predefined gesture sub-patterns in any order, but cannot match the non-gesture pattern composed of non-predefined gesture sub-patterns, so when a gesture When the likelihood value calculated by the model for the current input action sequence is higher than the general threshold model, it cannot arbitrarily determine that the current input action sequence belongs to a certain gesture mode

Images