摘要
在3D人体姿态估计中,遮挡会导致人体关节点提取不准确,针对该问题,本文提出一种结合时空注意力和通道注意力的3D人体姿态估计算法。首先,提出一种特征筛选模块,该模块通过引入位置嵌入模块,以进一步捕获人体关节点的特征信息;其次,提出一种移动视觉Transformer时间注意力模块,该模块通过引入SiLU激活函数,以获取更多姿态特征细节;最后,提出一种通道注意力模块,该模块通过引入并行分支处理架构及增加归一化层,以调整输出通道的特征权重,达到算法对人体姿态特征的关注和弱化其背景特征的目的。在Human3.6M数据集上进行实验,相较于基准模型Strided Transformer,将级联金字塔网络提取的2D关节点作为输入时,每关节位置误差的平均值和进行普罗克鲁斯对齐后的每关节位置误差的平均值分别下降2.5%和2.3%;将Human3.6M数据集标注的2D关节点作为输入时,每关节位置误差的平均值下降6.7%。实验结果表明,本文提出的算法准确性较高。
In the field of 3D human pose estimation,occlusion leads to inaccurate extraction of human joint points.To address this problem,this paper proposes a 3D human pose estimation algorithm that combines spatio-temporal attention and channel attention.Firstly,a feature filtering module is proposed,which further captures the feature information of human joint points by introducing the position embedding module.Then,a mobile vision transformer temporal attention module is proposed,which can obtain more details of pose features by introducing the SiLU activation function.Finally,a channel attention module is proposed,which adjusts the weights of the output channel features by introducing a parallel branch processing architecture and adding normalization layers,so that the algorithm can focus on human pose features while reducing the influence of background features.Experiments are conducted on the Human3.6M dataset.Compared with the baseline model Strided Transformer,the mean per joint position error(MPJPE)and the procrustes-aligned mean per joint position error(P-MPJPE)decrease by 2.5% and 2.3%,respectively,when the 2D joint points extracted from the cascaded pyramid network(CPN)are used as input.The MPJPE decrease by 6.7% when the annotated 2D joint points of the Human3.6M dataset are used as input.Experimental results show that the proposed algorithm has high accuracy.
作者
易见兵
张裕贤
曹锋
李俊
彭鑫
陈鑫
YI Jianbing;ZHANG Yuxian;CAO Feng;LI Jun;PENG Xin;CHEN Xin(College of Information Engineering,Jiangxi University of Science and Technology,Ganzhou Jiangxi 341000,China;Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control(Jiangxi University of Science and Technology),Ganzhou Jiangxi 341000,China)
出处
《广西师范大学学报(自然科学版)》
北大核心
2025年第5期130-144,共15页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金(62066018,62366017)
江西省自然科学基金(20181BAB202004)
江西省研究生创新专项资金(YC2023-S662)。
作者简介
通信作者:易见兵(1980-),男,江西宜春人,江西理工大学副教授,博士。E-mail:yijianbing8@jxust.edu.cn。
