基于注意力机制的改进残差网络的人体行为识别方法  

Human Action Recognition Method based on Attention Mechanism and Improved ResNeXt Network

作　　者：王昊飞 李俊峰[1] WANG Haofei;LI Junfeng(Faculty of Mechanical Engineering&Automation,Zhejiang Sci-Tech University,Hangzhou 310018,China)

机构地区：[1]浙江理工大学机械与自动控制学院,浙江杭州310018

出　　处：《软件工程》2021年第11期51-54,46,共5页Software Engineering

摘　　要：针对ResNeXt网络(残差网络)中存在的对特征提取不充分,以及数据集中背景信息干扰的问题,将ResNeXt网络和注意力机制相结合,提出了一种基于注意力机制的ResNeXt模型。首先,在ResNeXt网络的基础上,将浅层和深层的特征融合生成新型网络结构。其次,将全连接层由全局平均池化层替代,然后在通道空间注意力机制中添加一个条件因子,同时将改进后的注意力机制嵌入上述网络中。最后,在UCF101和HMDB51上分别进行实验,得到了95.2%和65.6%的准确率。研究表明,本文提出的模型可以有效地提取关键特征,充分利用不同层次的特征信息获得较好的准确率。Aiming at problems of insufficient feature extraction in ResNeXt network and background information interference in the dataset,this paper proposes a ResNeXt model based on attention mechanism,which combines the ResNeXt network and attention mechanism.First,based on ResNeXt network,shallow and deep features are merged to generate a new network structure.Second,the fully connected layer is replaced by a global average pooling layer.Then channel attention mechanism is improved by adding a condition factor.At the same time,the improved attention mechanism is embedded in the above-mentioned network.Finally,experiments are performed on UCF101 and HMDB51 respectively,and the accuracy rates of 95.2% and 65.6% are obtained.Experiments show that the proposed model can effectively extract key features,and make full use of feature information of different layers to achieve better accuracy.

关 键 词：人体行为识别 注意力机制 ResNeXt 全局平均池化 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]