Method for estimating 3D posture of a human body combining densely connecting attention pyramid residual network and equidistance restriction

Abstract

A method for estimating 3D posture of a human body combining densely connecting attention pyramid residual network and equidistance restriction is composed of a discriminative human body 2D posture estimation part and a generative human body 3D posture estimation part. Firstly, a 2D human posture estimation model is constructed. The 2D human posture estimation model includes attention pyramid residual blocks and a funnel sub-network composed of several attention pyramid residuals. The attention pyramid residuals are used for multi-scale image feature extraction, and the funnel sub-network is used to generate human joint thermodynamic map. In order to solve the problem that the environmental context information is not fully utilized, the attention mechanism and multi-scale analysis are combined to capture the environmental context characteristics. In order to solve the problem of gradient disappearance / gradient explosion, the dense connection network is combined with the above attentionmechanism to improve the discrimination of a feature map. Then the loss function is constructed and the equidistant constraint term is introduced to fit the 3D posture of a human body by minimizing the loss function. The method of the invention has obvious advantages in the human body 3D posture estimation task.

Description

technical field [0001] The invention belongs to the technical field of human body posture estimation, and in particular relates to a human body 3D posture estimation method combined with a densely connected attention pyramid residual network and isometric constraints. Background technique [0002] Human 3D pose estimation recovers the 3D positions of human joint points in a given image or video. This work is the basis for many important applications, such as video surveillance, behavior recognition, human interaction, virtual reality, game animation, medical care, and more. [0003] The current human pose estimation methods can be roughly divided into the following categories: 1) Regression iterative method, initialization to get the initial pose prediction, and then iterative estimation to improve the prediction accuracy; 2) Method based on structured learning, using Markov random field mining Human body structure information to obtain the mutual relationship of human body...

AI Technical Summary

Problems solved by technology

[0004] At present, the research on human 3D pose estimation based on deep convolutional neural network has achieved certain results, but there are some bottlenecks in performance: 1) This problem is essentially a pathological problem; 2) The mapping from image feature space to 3D pose space is wrong. Linear multimodal; 3) Deeper networks are easy to learn this nonlinear mapping relationship, but deeper networks are prone to gradient disappearance or gradient explosion problems

Images