一种部位语义感知的视频行为识别方法

刘晓东; 李松阳; 王淼

Chinese

您当前的位置：

首页 >

文章列表页 >

一种部位语义感知的视频行为识别方法

更新时间：2026-09-04

- 一种部位语义感知的视频行为识别方法
- A Part Semantic Based Action Recognition Method
- 微电子学与计算机 2018年35卷第12期页码：12-15
- 作者机构：
  
  河南工程学院机构计算机学院,河南,郑州,451191
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61501174河南省科技厅科技攻关项目 182102310919河南工程学院博士基金项目 D2015022河南省教育厅科学技术研究重点项目 16A520041
- DOI：
  中图分类号：
- 纸质出版：2018
- 稿件说明：
移动端阅览
刘晓东, 李松阳, 王淼. 一种部位语义感知的视频行为识别方法[J]. 微电子学与计算机, 2018, 35(12): 12-15.

LIU Xiao-dong, LI Song-yang, WANG miao. A Part Semantic Based Action Recognition Method[J]. 2018, 35(12): 12-15.
刘晓东, 李松阳, 王淼. 一种部位语义感知的视频行为识别方法[J]. 微电子学与计算机, 2018, 35(12): 12-15. DOI：

LIU Xiao-dong, LI Song-yang, WANG miao. A Part Semantic Based Action Recognition Method[J]. 2018, 35(12): 12-15. DOI：

摘要

针对传统视频行为识别中在建模高层次语义运动模式和语义运动演化方面的不足

本文提出一种部位语义感知的行为识别方法.该方法首先基于人体部位位置信息

提取人体部位高层次语义特征; 然后基于人体部位语义特征和人体部位语义特征时间演变

对人体行为进行识别.我们基于caffe架构实现了该方法

实验结果表明该方法具有很好的性能。

Abstract

Aiming at the deficiency that model high level semantic motion pattern and semantic movement evolution in the research of traditional video action recognition

this paper proposes a part semantic based video action recognition method. First

it extracts high level semantic features based on the position information of the body parts. Second

we propose a feature descriptor for action recognition based on human part semantic and its movement evolution. The method is implemented on Caffe. The experiment results display good performance.

关键词

Keywords

references

Girshick R. Fast R-CNN[C]//IEEE International Conference on Computer Vision. Houston, TX, USA, 2015: 1440-1448.

Bilen H, Fernando B, Gavves E, et al. Dynamic image networks for action recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 3034-3042.

Kuehne H, Jhuang H, Garrote E, et al. HMDB: A large video database for human motion recognition[C]//IEEE International Conference on Computer Vision. Barcelona, Spain, 2011: 2556-2563.

Tran D, Bourdev L, Fergus R, et al. Learning spatiotemporal features with 3d convolutional networks[C]//Proceedings of the IEEE International Conference on Computer Vision. Houston, TX, USA, 2015: 4489-4497.

Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[C]//Advances in neural information processing systems. Montreal, Quebec, Canada, 2014: 568-576.

Wang L, Xiong Y, Wang Z, et al. Temporal segment networks: towards good practices for deep action recognition[J]. Acm Transactions on Information Systems, 2016, 22(1): 20-36. DOI: 20

Yang X, Molchanov P, Kautz J. Multilayer and multimodal fusion of deep neural networks for video classification[C]//ACM on Multimedia Conference 2016.Amsterdam, The Netherlands, 2016: 978-987.

Chu X, Ouyang W, Li H, et al. Structured feature learning for pose estimation[C]//IEEE Conference on Computer Vision and Pattern Recognition 2016. Boston, Massac, 2016: 4715-4723.

Chéron G, Laptev I, Schmid C. P-cnn: Pose-based cnn features for action recognition[C]//Proceedings of the IEEE International Conference on Computer Vision. Houston, TX, USA 2015: 3218-3226.

Zhang Bowen, Wang Limin, Wang Zhe, et al. Real-time action recognition with enhanced motion vector CNNs[C]//2016 IEEE International Conference on Computer Vision and Pattern Recognition. Boston, Massac, 2016: 2718-2726.

Fernando B, Anderson P, Hutter M, et al. Discriminative hierarchical rank pooling for activity recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 1924-1932.

Su W T, Lu Y H, Kaseb A S. Harvest the information from multimedia big data in global camera networks[C]//Multimedia Big Data (BigMM), 2015 IEEE International Conference on. Beijing, China, IEEE, 2015: 184-191.

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

一种基于行为上下文的视频情感识别方法

超低功耗实时时钟电路的设计

一种用于极低压boost系统的高效率电荷泵

V型沟槽SiC中子探测器的蒙特卡洛分析

基于监控指标关联性的微服务异常检测