Human Pose Estimation Method Based on Dynamic Lightweight High-Resolution Network

Abstract

The present invention provides a human body posture estimation method based on a dynamic lightweight high-resolution network. The method proposes a dynamic lightweight high-resolution network Dite-HRNet, which can efficiently extract the key point features of the human body under multiple scales and Capture the spatial context information between different human body key points; through the dynamic pyramid convolution and adaptive context modeling methods, respectively solve the problem that the network module in the existing high-resolution network is too static and the spatial context is insufficiently captured, and use The two specially designed two dynamic context modules for high-resolution networks, namely dynamic multi-scale context modules and dynamic global context modules, and finally make full use of the parallel multi-branch structure characteristics of high-resolution networks, which will have different hyperparameter configurations The dynamic context module of the method is applied to different branches of a lightweight high-resolution network to construct an efficient lightweight high-resolution network.

Description

technical field [0001] The invention relates to the technical fields of deep learning and computer vision, in particular to a method for estimating human body posture based on a dynamic lightweight high-resolution network. Background technique [0002] Human pose estimation, which is to detect the positions of important human joints or parts in images or videos, is a pre-task for many downstream applications in the field of computer vision technology (such as behavior recognition, human-computer interaction, video surveillance, etc.). In the application of human pose estimation, especially in real-time applications under limited computing resources and equipment conditions, we must not only pursue higher detection accuracy, but also ensure high computing efficiency. At this stage, most of the methods research on human pose estimation use convolutional neural networks to extract and detect the feature information of human key points. Such convolutional neural networks can be ...

AI Technical Summary

Problems solved by technology

The calculation efficiency of various operations in the network module on different input data is high or low, and is affected by factors such as the resolution of the data and the number of feature channels. However, the high-resolution network contains many feature data at different scales. Therefore, the static network module cannot make good use of the multi-scale characteristics of its parallel multi-resolution network branch structure, making it difficult to achieve optimal computational efficiency.

[0004] In addition, the traditional human pose estimation network only extracts the key point features of the human body in the image through a single repeated convolution operation. Due to the limitation of the size of the convolution receptive field, the feature map extracted in this way only uses the local part of the image. Pixel information, while ignoring the contextual relationship between distant pixels

This kind of network can only learn the pixel distribution pattern of human body parts in the local area of ​​the image. Because of the lack of global information assistance, it cannot grasp the spatial context relationship between all human body parts well, resulting in the deviation of image feature extraction.

Increasing the size of the convolution kernel used by the convolution layer can expand the receptive field range of each operation on the image, thereby capturing more image space context information, but blindly increasing the size of the convolution kernel will cause the network The computational complexity is gradually increasing, which is not conducive to the lightweight design of the network

Images