轻量级高分辨率人体姿态估计研究

Lightweight and High-Resolution Human Pose Estimation Method

人体姿态估计通常使用高分辨率表示的方法来实现关键点的检测,但网络参数量较大,运算较为复杂。基于此,提出了一种轻量级高分辨率人体姿态估计算法。首先,使用稠密连接网络(DenseNet)并进行轻量化改进,提出密集连接层,使得各层之间连接更加紧密,从而降低网络的运算参数,优化网络的运算速度;其次,在降低参数且精度保持不变的情况下,在多尺度融合阶段使用上采样和反卷积模块结合的融合方式,使得输出的特征信息更加丰富,检测结果更加准确;最后,利用COCO 2017验证数据集及MPII数据集进行验证。实验结果表明,在保证准确率的情况下与其他人体姿态估计算法相比,所提算法的平均精度为74.8%,运算参数减少了63.8%,网络运算复杂度缩小了8.5%,同时也到达了实时性的效果。

For human pose estimation,a highscore representation method is usually adopted for detecting key points;however,this detection is difficult to achieve because of numerous network parameters and complicated calculations.In this study,to realize a closer connection between layers and achieve an enhanced lightweight nature,the densely connected network(DenseNet)is employed and densely connected layers are proposed.The network calculation parameters are reduced while the detection accuracy is maintained,and the network computing speed is optimized.Second,a fusion method that combines upsampling and deconvolution modules in the multiscale fusion stage is proposed,facilitating more abundant output feature information and more accurate detection results more accurate.Finally,the COCO 2017 and MPII datasets are used for validating the proposed method.Experimental results show that compared with other human pose estimation algorithms,the proposed method achieves an average network accuracy of 74.8%,reduces the number of operating parameters by 63.8%,and decreases the network calculation complexity by 8.5%while ensuring the accuracy of realtime effects.