基于改进型C3D神经网络的动作识别技术

doi:10.3969/j.issn.1006-2475.2019.03.007

计算机与现代化

基于改进型C3D神经网络的动作识别技术

(华北计算技术研究所系统八部，北京100083)

收稿日期:2018-08-27 出版日期:2019-04-08 发布日期:2019-04-10
作者简介:廖小东（1995-），男，江西赣州人，硕士研究生，研究方向：计算机视觉，动作识别，图像处理,E-mail: 1457667862@qq.com；贾晓霞(1976-)，女，山西原平人，研究员级高级工程师，研究方向：信息服务。

Action Recognition Technology Based on Improved C3D Neural Network

(Eigth System Department, North China Institute of Computing Technology, Beijing 100083, China)

Received:2018-08-27 Online:2019-04-08 Published:2019-04-10

摘要/Abstract

摘要： Facebook提出的C3D三维卷积神经网络虽然能达到良好的视频动作识别准确率，但是在速度方面还有很大的改进余地，而且训练得到的模型过大，不便于移动设备使用。本文利用小型卷积核能够减少参数的特点，对已有网络结构进行优化，提出一种新的动作识别方案，将原C3D神经网络常用的3×3×3卷积核分解成深度卷积和点卷积（1×1×1卷积核），并且在UCF101数据集和ActivityNet数据集训练测试。结果表明，与原C3D网络进行对比：改进后的C3D网络准确率比C3D提升了2.4%，在速度方面比C3D提升了12.9%，模型大小压缩到原来的25.8%。

关键词: 动作识别, 卷积分解, 识别速度, 模型压缩

Abstract: Although the C3D convolutional neural network proposed by Facebook can achieve good video action recognition accuracy, there is still much room for improvement in terms of speed, and the model obtained by training is too large to be used by mobile devices. This paper uses small convolutional kernels to reduce the characteristics of parameters, optimizes the existing network structure, and proposes a new action recognition scheme, which decomposes the 3×3×3 convolutional kernel commonly used in the original C3D neural network into deep convolution and point convolution (1×1×1 convolution kernel), and training tests on the UCF101 dataset and ActivityNet dataset. The results show that compared with the original C3D network, the improved C3D network accuracy is 2.4% higher than C3D, 12.9% faster than C3D in speed, and the model size is compressed to 25.8%.

Key words: action recognition, convolution decomposition, recognition speed, model compression

中图分类号:

TP391

廖小东，贾晓霞 . 基于改进型C3D神经网络的动作识别技术[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2019.03.007.

LIAO Xiao-dong, JIA Xiao-xia . Action Recognition Technology Based on Improved C3D Neural Network[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.03.007.

参考文献

［1］ LAPTEV I, LINDEBERG T. Space-time interest points［J］. International Journal of Computer Vision, 2005,64(2-3):107-123.
［2］ BOIMAN O, IRANI M. Detecting irregularities in images and in video［J］. International Journal of Computer Vision, 2007,74(1):17-31.
［3］ KITANI K M, ZIEBART B D, BAGNELL J A, et al. Activity forecasting［C］// European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2012:201-214.
［4］ WANG H , SCHMID C. Action recognition with improved trajectories［C］// IEEE International Conference on Computer Vision. 2014:3551-3558.
［5］ LE Q V, ZOU W Y, YEUNG S Y, et al. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis［C］// Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition. 2011:3361-3368.
［6］ NG Y H, HAUSKNECHT M, VIJAYANARASIMHAN S, et al. Beyond short snippets: Deep networks for video classification［C］// 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015:4694-4702.
［7］ DIBA A, SHARMA V, GOOL L V. Deep temporal linear encoding networks［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:430-443.
［8］ TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks［C］// 2015 IEEE International Conference on Computer Vision. 2015:4489-4497.
［9］ XU H, DAS A, SAENKO K. R-C3D: Region convolutional 3D network for temporal activity detection［C］// Proceedings of International Conference on Computer Vision. 2017:761-774.
［10］黄凯奇,陈晓棠,康运锋,等. 智能视频监控技术综述［J］. 计算机学报, 2015,20(6):1093-1118.
［11］王松,党建武,王阳萍,等. 实时动作识别方法研究［J］. 计算机工程与应用, 2017,53(3):28-31.
［12］JI S, XU W, YANG M, et al. 3D convolutional neural networks for human action recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(1):221-231.
［13］YAN Z, ZHANG H, PIRAMUTHU R, et al. HD-CNN: Hierarchical deep convolutional neural networks for large scale visual recognition［C］// Proceedings of International Conference on Computer Vision. 2015:2740-2748.
［14］KARPATHY A, TODERICI G, SHETTY S , et al. Large-scale video classication with convolutional neural networks［C］// International Conference on Computer Vision and Pattern Recognition. 2014:1-6.
［15］HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
［16］HOWARD A G, ZHU M, CHEN B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:21-26.
［17］ZHENG Q, ZHANG Z, ZHANG S, et al. Merging-and-evolution networks for mobile vision applications［J］. IEEE Access, 2018(99):1.
［18］YANG Z, MOCZULSKI M, DENIL M, et al. Deep fried convnets［J］. Computer Science, 2015(12):7-13.
［19］SIGURDSSON G A, DIVVALA S, FARHADI A, et al. Asynchronous temporal fields for action recognition［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2017:5650-5659.
［20］LI X, DING L, WANG L, et al. FPGA accelerates deep residual learning for image recognition［C］// IEEE Information Technology, Networking, Electronic and Automation Control Conference. 2017:834-840.

[1]	黄延辉, 兰海, 魏宪. 基于可分离结构变换的轻量级Vision Transformer[J]. 计算机与现代化, 2022, 0(10): 75-81.
[2]	包志强, 程萍, 黄琼丹, 吕少卿. 一种卷积神经网络的模型压缩算法[J]. 计算机与现代化, 2021, 0(10): 107-111.
[3]	白士磊, 殷柯欣, 朱建启. 轻量级YOLOv3的交通标志检测算法[J]. 计算机与现代化, 2020, 0(09): 83-88.
[4]	潘陈听, 谭晓阳, . 复杂背景下基于深度学习的视频动作识别[J]. 计算机与现代化, 2020, 0(07): 97-103.
[5]	郑轩宇，史畅，崔文成. 基于Kinect的运动训练辅助系统[J]. 计算机与现代化, 2019, 0(08): 12-.
[6]	王述，王庆，陈洪. 儿童教育游戏模式下眼动交互应用设计及验证[J]. 计算机与现代化, 2018, 0(07): 62-.
[7]	董哲宇,汪千军,李万杰,周波. 基于神经网络的人体动作识别方法[J]. 计算机与现代化, 2018, 0(03): 26-.
[8]	韩敏捷. 基于深度学习框架的多模态动作识别[J]. 计算机与现代化, 2017, 0(7): 48-52.
[9]	熊俊涛1，刘梓健1，孙宝霞2，俞守华1，陈建国1. 基于视觉技术的手势跟踪与动作识别算法[J]. 计算机与现代化, 2014, 0(7): 75-79.
[10]	邹灿,李柏岩. 基于BIC的语音识别模型压缩算法[J]. 计算机与现代化, 2014, 0(6): 71-73,78.
[11]	苏文瑛;刘艳;李文博. 基于Period的三维人体动作识别研究[J]. 计算机与现代化, 2013, 1(4): 90-94.
[12]	施惟;. 基于话题模型的视频动作识别系统研究[J]. 计算机与现代化, 2013, 1(4): 1-4.
[13]	孙锦红;刘卫东;马亮;杨伟蕾. 基于机器视觉的3D人体动作识别研究[J]. 计算机与现代化, 2011, 1(11): 86-4.

基于改进型C3D神经网络的动作识别技术

Action Recognition Technology Based on Improved C3D Neural Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价