Stereoscopic hand 3D skeleton model real-time reconstruction method and apparatus based on binocular color imaging system

Abstract

The invention discloses a stereoscopic hand 3D skeleton model real-time reconstruction method based on a binocular color imaging system. The binocular color imaging system is used for shooting a handto obtain two color images of the same hand in different viewing angles. The method includes: S1, detecting the position of the hand; S2, detecting plane key points of the hand; S3, recovering three-dimensional coordinates according to the plane positions of the key points in a binocular image; and S4, performing fitting to form a three-dimensional hand skeleton by employing the three-dimensionalcoordinates of the key points. According to the method, 3D reconstruction of the hand is performed only by employing the binocular color image without any extra special equipment. The invention also provides an apparatus based on the method.

Description

technical field [0001] The invention relates to the technical field of human hand recognition, in particular to a method and device for real-time reconstruction of a three-dimensional human hand 3D skeleton model based on a binocular color imaging system. Background technique [0002] Gesture recognition technology plays an important role in human-computer interaction. Gesture recognition in a natural way can save people from using wearable devices to control machines with gesture information. Gesture recognition can be divided into three levels: two-dimensional hand recognition, two-dimensional gesture recognition, three-dimensional gesture recognition. Among them, two-dimensional hand recognition is to classify the gestures of two-dimensional pictures, and can distinguish simple gestures such as fisting and OK. Compared with two-dimensional hand recognition, two-dimensional gesture recognition can calculate more complex continuous gestures, such as waving, but it still s...

AI Technical Summary

Problems solved by technology

Compared with two-dimensional hand recognition, two-dimensional gesture recognition can calculate more complex continuous gestures, such as waving, but it still stays at the level of two-dimensional information without depth information

Three-dimensional gesture recognition is the most ideal form in gesture recognition, but it is also the most complex task

Two-dimensional gesture information collection only requires a single ordinary camera, while the current three-dimensional gesture recognition requires special hardware to obtain hand depth information

However, this method needs to wear a solid-color glove when it is applied. It is not a natural gesture recognition, and it can only recognize dozens of specific gestures, and cannot reconstruct the 3D information of the whole hand.

[0006] In the same method [6] using a binocular color camera, only the position of one finger of the index finger can be detected, and only a simple click action can be recognized, and the information of the entire hand cannot be obtained.

Images