A continuous character gesture trajectory recognition method based on stdw

Abstract

Aiming at the problems existing in the prior art, the present invention proposes a continuous character gesture trajectory recognition method based on a structured dynamic time domain warping algorithm, through automatic segmentation of continuous gesture trajectory, extraction of new corner features and STDW recognition and character The included processing between gesture trajectories realizes natural, real-time and accurate recognition of continuous character gesture trajectories. Compared with the prior art, the interactive mode of the present invention is more natural, less restrictive to users and meets the requirements of human-computer interaction. Compared with the traditional several gesture action categories, which are more diverse, under the condition of both accuracy and real-time performance, the present invention combines the structure of the character gesture trajectory with the dynamic time warping algorithm to form a structured dynamic time warping algorithm to improve the original The recognition effect of the algorithm increases the recognition rate. At the same time, it has a higher accuracy rate, a better human-computer interaction experience and can meet real-time requirements.

Description

technical field [0001] The invention belongs to the technical field of computer vision and human-computer interaction, and more specifically relates to a method for recognizing continuous character gesture tracks based on STDW (Structured Dynamic Time Warping, structured dynamic time domain warping algorithm). Background technique [0002] Human-computer interaction technology realizes the information input and output between the computer and the human, the human inputs instructions to the computer, and the computer outputs calculation results to the human. Today, with the rapid development of information technology, the emergence of various smart devices is changing people's daily life. With the emergence of new smart devices, new human-computer interaction methods are subverting traditional human-computer interaction models. [0003] The commercialization of depth cameras (such as Kinect, Leap Motion) has made gesture recognition more and more attention in the field of 3D...

AI Technical Summary

Problems solved by technology

This method finally takes the upper, lower, left, right and other trajectories and simple characters such as 10 Arabic numerals as the recognition results, and assumes that the start and end points of the trajectories are known, and does not involve automatic trajectory segmentation algorithm design

Images