基于循环神经网络的人体运动模型的隐状态初始化方法  

Hidden state initialization method for recurrent neural network-based human motion model

作　　者：李南帆 司文文 杜思远 王志勇 钟重阳 夏时洪[2,3] LI Nanfan;SI Wenwen;DU Siyuan;WANG Zhiyong;ZHONG Chongyang;XIA Shihong(State Grid Beijing Urban Power Supply Company,Beijing 100034,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]国网北京城区供电公司,北京100034 [2]中国科学院计算技术研究所,北京100190 [3]中国科学院大学,北京100049

出　　处：《计算机应用》2023年第3期723-727,共5页journal of Computer Applications

基　　金：国家重点研发计划科技冬奥重点专项(2020YFF0304701);北京市电力公司科技项目(52020220004B)。

摘　　要：针对基于循环神经网络(RNN)的人体运动合成方法存在首帧跳变,进而影响生成运动的质量的问题,提出一种带有隐状态初始化的人体运动合成方法,将初始隐状态作为自变量,利用神经网络的目标函数作为优化目标,并使用梯度下降的方法进行优化求解,以得到一个合适的初始隐状态。相较于编码器-循环-解码器(ERD)、残差门控循环单元(RGRU)模型,所提方法在首帧的预测误差分别减小63.51%和6.90%,10帧的总误差分别减小50.00%和4.89%。实验结果表明,该方法无论是运动合成质量还是运动预测精度都优于不进行初始隐状态估计的方法;它通过准确估计基于RNN的人体运动模型的首帧隐状态可提升运动合成的质量,并且为实时安全监测中的动作识别模型提供可靠的数据支持。Aiming at the problem of the jump existed in the first frame of human motion synthesis method based on Recurrent Neural Network(RNN),which affects the quality of generated motion,a human motion synthesis method with hidden state initialization was proposed.The initial hidden state was used as independent variable,the objective function of the neural network was used as optimization goal,and the gradient descent method was used to optimize and solve the problem to obtain a suitable initial hidden state.Compared with Encoder-Recurrent-Decoder(ERD)model and Residual Gate Recurrent Unit(RGRU)model,the proposed method with initial hidden state estimation reduces the prediction error of the first frame by 63.51%and 6.90%respectively,and decreases the total error of 10 frames by 50.00%and 4.89%respectively.Experimental results show that the proposed method is better than the method without initial hidden state estimation in both motion synthesis quality and motion prediction accuracy.And the proposed method accurately estimates the hidden state of the first frame of RNN-based human motion model,which improves the quality of motion synthesis and provides reliable data support for action recognition model in real-time security monitoring.

关 键 词：人体运动合成 循环神经网络 隐状态估计 动作识别 运动模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]