Gesture recognition method based on vision

Abstract

The invention discloses a gesture recognition method based on vision, comprising the following steps: step 1, capturing a video stream through a Kinect sensor, and getting depth image data and bone data; step 2, preprocessing the obtained depth image data through use of a median filtering method; step 3, extracting a hand region according to the depth image data and the bone data to get a hand region binary map; step 4, binarizing the edge image of the hand region binary map through edge detection, and extracting palm contour information; step 5, resetting the center of palm according to the hand region binary map; step 6, calculating out convex hull vertices and a circum circle according to the palm contour information; and step 7, performing matching to recognize gestures using a classification decision tree and a variety of gestures in a gesture library according to the center-of-palm resetting and the convex hull vertices and the circum circle calculated.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a gesture recognition method based on vision-based acquisition and processing of depth graphic data. Background technique [0002] It is said that with the rapid development of computers, the mode of human-computer interaction is constantly changing. Real-life experience is available. Body language is also very important in the process of interaction between people. Using hands to realize human-computer interaction is more natural and smooth than using media such as keyboards and mice. One of the reasons for becoming mainstream. [0003] The principle of using hands to realize human-computer interaction is the interpretation of the machine opponent, such as the shape of the hand, the spatial position of the hand, the posture of the hand, and the spatial position of the hand. There are many recognition methods, some of which use supporting equipment, such as acceleration sensors,...

AI Technical Summary

Problems solved by technology

[0005] The vision-based gesture recognition method generally uses a network camera as an image extraction device, but it is very susceptible to the influence of light changes and the interference of skin color, and the recognition effect is not as expected. With the emergence of the high-tech product Kinect depth camera, A new development direction has appeared in the human-computer interaction mode, but how to realize gesture recognition on the basis of Kinect has become a hot spot for exploration

Images