光学 精密工程, 2017, 25 (3): 799, 网络出版: 2017-04-18   

构建多尺度深度卷积神经网络行为识别模型

Action recognition model construction based on multi-scale deep convolution neural network
作者单位
1 重庆理工大学 计算机学院, 重庆 400054
2 广西师范学院 计算机与信息工程学院, 广西 南宁 530001
摘要
为了减化传统人体行为识别方法中的特征提取过程, 提高所提取特征的泛化性能, 本文提出了一种基于深度卷积神经网络和多尺度信息的人体行为识别方法。该方法以深度视频为研究对象, 通过构建基于卷积神经网络的深度结构, 并融合粗粒度的全局行为模式与细粒度的局部手部动作等多尺度信息来研究人体行为的识别。MSRDailyActivity3D数据集上的实验得出该数据集上第11~16种行为的平均识别准确率为98%, 所有行为的平均识别准确率为60.625%。结果表明, 本方法能对人体行为进行有效识别, 基本能准确识别运动较为明显的人体行为, 对仅有手部局部运动的行为的识别准确率有所下降。
Abstract
In order to simplify the feature extracting process of Human Activity Recognition (HAR) and improve the generalization of extracted feature, an algorithm based on multi-scale deep convolution neural network was proposed. In this algorithm, the depth video was selected as research object and a parallel CNN (Convolution Neural Network) based deep network was constructed to process coarse global information of the action and fine-grained local information of hand part simultaneously. Experiments were executed on MSRDailyActivity3D dataset. The average recognition accuracy on actions ranging from No.11 to No.16 was 98%, while that on all actions was 60.625%. The experimental results showed that proposed algorithm could take effective recognition for human activity. Almost all of the actions with obvious movements and most of actions with local movements just in hands could be recognized effectively.

刘智, 黄江涛, 冯欣. 构建多尺度深度卷积神经网络行为识别模型[J]. 光学 精密工程, 2017, 25(3): 799. LIU Zhi, HUANG Jiang-tao, FENG Xin. Action recognition model construction based on multi-scale deep convolution neural network[J]. Optics and Precision Engineering, 2017, 25(3): 799.

本文已被 15 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!