基于几何特征与LSTM网络结合的动作识别算法  

Action recognition algorithm based on LSTM network with geometric features

作　　者：邬倩 吴飞[1] 骆立志 WU Qian;WU Fei;LUO Lizhi(College of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《传感器与微系统》2020年第10期111-114,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61272097);上海市科技学术委员会重点项目(18511101600)。

摘　　要：为进一步提高基于人体骨架动作识别的识别率,打破以往大部分基于深度学习的方法的输入都为人体骨架关节坐标的局限性,提出了一种将骨架几何特征与长短期记忆(LSTM)网络结合的动作识别算法。选择基于关节与选定直线之间距离的骨架几何特征代替骨架关节坐标作为网络的输入,并引入了基于LSTM的网络结构,即时序关注LSTM网络。利用时序关注LSTM网络具有重点关注最具识别性的帧的能力,在SBU Interaction数据集和UT Kinect数据集上分别取得了99.25%和98.79%的识别率。实验结果证明:该方法对基于人体骨架动作识别的有效性。In order to further improve the rate of action recognition based on human skeleton and break the limitation that the inputs of most methods based on deep learning are human joint coordinates,a skeleton-based action recognition algorithm combining geometric features with long short-term memory(LSTM)network is proposed.The geometric features based on the distances between joints and selected lines are selected as the input of the network.Then,a simple network structure based on LSTM,time-concerned LSTM network,is introduced.By utilizing the ability of time-concerned LSTM network to focus on the most recognizable frames,99.25%and 98.79%recognition rates are achieved on SBU Interaction dataset and UT Kinect dataset,respectively.The experimental results show that the method is effective for skeleton-based action recognition.

关 键 词：骨架动作识别 几何特征 长短期记忆(LSTM)网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]