Method and device for extracting skeleton line based on random forest

Abstract

The invention discloses a method and device for extracting a skeleton line based on a random forest. The method comprises the following steps of: constructing a random forest according to a training sample of the skeleton line of a human body; acquiring the joint position information of a human body graph to be measured according to the random forest; determining the starting point of a current joint to be measured according to the joint position information; walking on the random forest according to a preset prediction rule from the starting point until a terminating condition is satisfied, and then determining the predicted position of the current joint to be measured according to a specific rule; using the predicted position of the current joint to be measured as the starting point of asub node of the joint; repeating the above walking operation until the predicted positions of all joints in the human body graph to be measured is obtained; and forming the skeleton line of the humanbody graph to be measured according to the predicted positions of all joints. It is short in time consumption and can differentiate respective joints to extract the skeleton line based on the randomforest.

Description

technical field [0001] The invention relates to the technical field of human body recognition, in particular to a random forest-based skeleton line extraction method and a device thereof. Background technique [0002] With the rapid development of artificial intelligence, people's requirements for games are getting higher and higher. Somatosensory games, which have broken through the previous operation method of simply inputting with handle buttons, are a new type of game that is performed (operated) through changes in body movements. This kind of game often obtains the body movement changes of the human body by extracting the skeleton line of the human body. [0003] At present, the algorithms for extracting skeleton lines mainly include: morphological analysis and deep learning. Morphological analysis can obtain the skeleton line of the human body through refinement, but it cannot distinguish each joint; the deep learning algorithm is trained through a large amount of da...

AI Technical Summary

Problems solved by technology

Morphological analysis can obtain the skeleton line of the human body through refinement, but cannot distinguish each joint; the deep learning algorithm, through training with a large amount of data, obtains the skeleton line, but it takes a long time and requires the support of high-end hardware

Images