Three-dimensional gesture recognition method and system

Abstract

The invention provides a 3D (Three-dimensional) gesture recognition method and system. The 3D gesture recognition system comprises a feature extracting unit, a matching unit and a support vector machine (SVM) classifier, wherein the feature extracting unit is used for extracting a grid depth feature (GDF) from a present frame of an input video sequence, and extracting level setup moment (LSM) features and/or curvature histogram (HOC) features; the matching unit is used for matching the GDF feature extracted by the feature extracting unit with GDF features of a plurality of clustering templates obtained from off-line view clustering, thus obtaining orientation information of a gesture in the present frame; and the SVM classifier is used for recognizing the gesture in the present frame based on the LSM features extracted by the feature extracting unit and/or the HOC features and the orientation information obtained by the matching unit. According to the 3D gesture recognition method and system, the orientation of a hand is not limited, and the problem that the hand of an actor may be shielded by the actor is solved successfully.

Description

technical field [0001] The invention relates to the field of intelligent recognition, in particular to a three-dimensional (3D) gesture recognition method and system. Background technique [0002] Immersive large displays based on virtual reality require people to interact in traditional ways. However, most of the current computer / user interactions are simple interaction methods, and there are interaction barriers, so consumers prefer to interact through multimedia or virtual reality. For example, a computer keyboard provides keyboard interaction performance, but the keyboard interaction is not intuitive, while a TV remote control may make users feel more intuitive, but the TV remote control provides limited interactive performance. Additionally, some flexible interfaces (eg, instrument suits) are bulky and expensive. [0003] Currently, most existing gesture recognition systems only recognize two-dimensional (2D) gestures and are limited to some specific viewing angles. I...

AI Technical Summary

Problems solved by technology

However, the current computer / user interaction mostly adopts simple interaction methods, and there are interaction barriers, so consumers prefer to interact through multimedia or virtual reality

For example, a computer keyboard provides keyboard interactivity, but the keyboard interaction is not intuitive, while a TV remote may feel more intuitive to the user, but the TV remote provides limited interactivity

Also, some flexible interfaces (e.g., instrument suits) are bulky and expensive

[0003] At present, most of the existing gesture recognition systems are only two-dimensional (2D) gesture recognition, and are limited to some specific viewing angles. In addition, it is difficult to perceive gestures in different orientations.

Images