Three-dimensional human body posture estimation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a three-dimensional human body posture estimation method and device, equipment and a storage medium, and the method comprises: obtaining a to-be-estimated image; inputting the to-be-estimated image into a target three-dimensional human body posture estimation model for three-dimensional human body posture estimation, wherein the target three-dimensional human body posture estimation model is a model obtained by adversarial training based on a to-be-trained generative network, a to-be-trained discrimination network and a human body posture strong geometric constraint model; and obtaining target three-dimensional human body posture data corresponding to the to-be-estimated image according to the three-dimensional human body posture data output by the target three-dimensional human body posture estimation model. The problem of few training samples is effectively solved through adversarial training, the prediction performance of the model obtained through training on interference shielding is improved by introducing the human body posture strong geometric constraint model, and the probability of occurrence of abnormal posture prediction is reduced.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a method, device, equipment and storage medium for estimating a three-dimensional human body pose. Background technique [0002] 3D human pose detection is an important research field in the field of computer vision. This research field has important application value and practical significance for human action discrimination, intention recognition, behavior detection, and sports teaching. [0003] At present, there are two main methods for 3D human body posture detection: one method is to perform 3D depth joint point regression prediction on the basis of 2D joint point prediction by first performing 2D joint point prediction, but this method is used from When the 2D prediction results are used for 3D regression, there is a general problem of insufficient use of spatial information extraction, resulting in low performance of the 3D prediction part; anoth...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of this application is to provide a method, device, device, and storage medium for estimating a three-dimensional human body posture, aiming at solving the problem that the three-dimensional human body posture detection in the prior art cannot correctly predict the human body joint points when there is interference occlusion, and often occurs Technical Issues in the Prediction Results of Abnormal Postures

Images