Palm position determination method and device, electronic equipment and storage medium

Abstract

The invention provides a palm position determination method and device, electronic equipment and a storage medium. The method comprises the following steps: firstly, detecting key points of a target palm, performing linear fitting on the key points of the palm root of the target palm and a plurality of key points belonging to the same finger to obtain linear fitting straight lines corresponding to a plurality of fingers, determining the gradient of the target palm according to the plurality of linear fitting straight lines, and determining the gradient of the target palm according to the positions of the key points. A position frame covering all key points of the target palm is obtained and can indicate the size and the position of the target palm. The gradient of the palm is analyzed based on the key points obtained through preliminary detection, the position frame is obtained based on the gradient and by combining all the obtained key points, it can be ensured that the gradient and the size of the generated position frame are basically consistent with those of the target palm, positioning is more accurate, and when gesture recognition and continuous tracking of the target palm are carried out based on the position frame subsequently, the accuracy is higher. Interference of the background environment in the image or missing key points can be reduced, and it is ensured that feature extraction is more accurate.

Description

technical field [0001] The invention relates to the field of human-computer interaction, in particular to a palm position determination method, device, electronic equipment and storage medium. Background technique [0002] Due to the development of computer vision technology, gesture control based on computer vision has become a widely used interaction method in the field of human-computer interaction. Gesture control usually uses a camera to track human body movements, and sends control to devices through human gestures. instruction. In this way, there is no need for control equipment such as a remote control, or traditional input and output equipment such as a mouse and keyboard, and the device can be remotely controlled by hand within a certain distance. However, many gesture recognition scenarios are very dependent on the exact position and size of the framed hand, and the currently commonly used target detection algorithms based on deep learning usually only approximat...

AI Technical Summary

Problems solved by technology

However, many gesture recognition scenarios are very dependent on the exact position and size of the framed hand, and the currently commonly used target detection algorithms based on deep learning usually only approximate the position and size of the framed hand, and its accuracy is not high. Affect the accuracy of subsequent gesture recognition

Images