自调节图卷积UNet的三维人体姿态估计方法
Self-adjusting graph convolution UNet method for 3D human pose estimation
马金林 1崔琦磊 2马自萍 3武江涛 2曹浩杰2
作者信息
- 1. 北方民族大学计算机科学与工程学院,银川 750021;图像图形智能信息处理国家民委重点实验室,银川 750021
- 2. 北方民族大学计算机科学与工程学院,银川 750021
- 3. 北方民族大学数学与信息科学学院,银川 750021
- 折叠
摘要
基于图卷积网络的三维人体姿态估计方法无法提取关节点的多尺度特征和未充分利用相邻节点的拓扑关系问题,提出自调节图卷积UNet的三维人体姿态估计方法M-Joint-UNet.M-Joint-UNet方法由Joint-UNet、自调节图卷积和融合损失 3部分组成:Joint-UNet通过关节点池化与去池化改变特征图大小,以提取关节点的不同尺度特征;自调节图卷积通过可学习矩阵自动调节相邻节点或人体骨架结构的关系;使用L1 和L2 融合的损失缓解梯度爆炸.对比实验表明:所提方法在参数量和估计性能方面均获得了最优的结果,以Human3.6M的二维真实关节点作为输入的参数量仅为0.54×106,MPJPE和P-MPJPE值分别为37.81 mm和30.21 mm.
Abstract
A few issues with the graph convolutional network-based 3D human pose estimation technique include the shared weight of all nodes,the incapacity to extract the multi-scale properties of the nodes,and the failure to take advantage of the topological relationships between neighboring nodes.In this paper,self-adjusting graph convolution UNet method for 3D human pose estimation(M-Joint-UNet)is proposed.M-Joint-UNet is composed of three parts:Joint-UNet,self-adjusting graph convolution,and fusion loss.Joint-UNet changes the size of the feature map through node pooling and unpooling to extract features of different scales of nodes.Self-adjusting graph convolution uses L1 and L2 fusion to mitigate gradient explosions and automatically modifies the relationship between neighboring nodes or the human skeletal structure using a learnable matrix.Comparative experiments show that the proposed method obtains optimal results in terms of the number of parameters and the estimation performance.With the 2D ground truth of Human3.6M as the input,the number of parameters is only 0.54×106,and the MPJPE and P-MPJPE values are 37.81 mm and 30.21 mm,respectively.
关键词
三维人体姿态估计/图卷积/Graph-UNet/关节点池化/权重矩阵Key words
3D human pose estimation/graph convolution/Graph-UNet/joint pool/weight matrix引用本文复制引用
出版年
2025
国家科技期刊平台
NSTL
维普
万方数据