基于双流卷积与双中心loss的行为识别研究

毛志强; 马翠红; 崔金龙; 王毅

Chinese

您当前的位置：

首页 >

文章列表页 >

基于双流卷积与双中心loss的行为识别研究

更新时间：2026-09-04

- 基于双流卷积与双中心loss的行为识别研究
- Research on action recognition based on two-stream convolution and double center loss
- 微电子学与计算机 2019年36卷第3期页码：96-100
- 作者机构：
  
  1. 华北理工大学机构电气工程学院,河北,唐山,063210
  2. 北京交通大学海滨学院,河北,沧州,061100
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61171058
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
毛志强, 马翠红, 崔金龙, 王毅. 基于双流卷积与双中心loss的行为识别研究[J]. 微电子学与计算机, 2019, 36(3): 96-100.

MAO Zhi-qiang, MA Cui-hong, CUI Jin-long, et al. Research on action recognition based on two-stream convolution and double center loss[J]. 2019, 36(3): 96-100.
毛志强, 马翠红, 崔金龙, 王毅. 基于双流卷积与双中心loss的行为识别研究[J]. 微电子学与计算机, 2019, 36(3): 96-100. DOI：

MAO Zhi-qiang, MA Cui-hong, CUI Jin-long, et al. Research on action recognition based on two-stream convolution and double center loss[J]. 2019, 36(3): 96-100. DOI：

摘要

针对行为视频中相似动作类内差异大、类间差异小

识别准确率不高的问题

提出了一种基于双流卷积网络与双中心loss的行为识别方法.该方法首先构建双流卷积网络结构

以C3Dnet模型作为双流结构的基础模型

分别提取多尺度RGB视频帧中的表观短时运动信息和堆叠光流图中的长时运动信息; 然后将双流结构提取的深度信息经长短时记忆(LSTM)网络解析后进行特征融合; 最后

利用基于双中心loss的2C-softmax目标函数

来最大化类间距离和最小化类内距离

从而实现相似动作的分类与识别.在数据集KTH上的实验结果表明

该方法能够准确识别相似动作

识别准确率可达98.2%

具有很好的识别效果.

Abstract

Aiming at the problem of large difference in similar action classes

small difference between classes in action video and low recognition accuracy

a action recognition method based on two-stream convolution network and double-center loss is proposed. The method first constructs a two-stream convolutional network structure

and uses the C3Dnet model as the basic model of the two-stream structure to extract the apparent short-term motion information in the multi-scale RGB video frame and the long-term motion information in the stacked optical flow map respectively; Then

the depth information extracted by the two-stream structure is parsed by a long and short time memory (LSTM) network to perform feature fusion; Finally

the 2C-softmax objective function based on dual-center loss is used to maximize the distance between classes and minimize the distance within the class

so as to classify and identify similar actions. The experimental results on the data set KTH show that the method can accurately identify similar actions

and the recognition accuracy can reach 98.2%

which has a good recognition effect.

关键词

Keywords

references

KARPATHY A, TODERICI G, SHETTY S, et al. Large-scale video classification with convolutional neural networks[C]// IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, IEEE Computer Society, 2014: 1725-1732.

DU T, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]// IEEE International Conference on Computer Vision. Rome, Italy, IEEE, 2016: 4489-4497.

HERATH S, HARANDI M, PORIKLI F. Going deeper into action recognition: a survey [J]. Image % Vision Computing, 2017, 60(4):4-21. DOI: 4

CHéRON G, LAPTEV I, SCHMID C. P-CNN: pose-based cnn features for action recognition[C]// IEEE International Conference on Computer Vision. Santiago, Chile, IEEE Computer Society, 2015: 3218-3226.

WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C]// Computer Vision, ECCV 2016. Amsterdam, The Netherlands, Springer International Publishing, 2016: 499-515.

杨天明, 陈志, 岳文静.基于视频深度学习的时空双流人物动作识别模型[J].计算机应用, 2018, 38(3):895-899. DOI: 895

SIMONYAN K, ZISSERMAN A. Two-stream convolutional networks for action recognition in videos[J]. Computer Vision and Pattern Recognition, 2014, 1(4):568-576. DOI: 568

DONAHUE J, HENDRICKS L A, ROHRBACH M, et al. Long-term recurrent convolutional networks for visual recognition and description [J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2017, 39(4):677-691. DOI: 677

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

V型沟槽SiC中子探测器的蒙特卡洛分析

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

大模型发展综述：从BERT到Deepseek的技术演进

基于区块链的AI生成内容溯源框架设计研究