基于深度信念网络的视觉人体动作识别

doi:10.11896/jsjkx.210200079

摘要/Abstract

摘要： 为实现互联网上大量背景复杂、视点变化的视频中人体动作的识别,提出了一种使用无监督的深度信念网络(DBNs)进行人体动作识别的创新方法。该方法采用深度信念网络(DBNs)和受限玻耳兹曼机进行无约束视频的动作识别,利用无监督深度学习模型自动提取合适的特征表示,不需要任何先验知识。在一个具有挑战性的 UCF 体育数据集上进行实验,证明了该方法准确有效。同时该方法也适用于其他视觉识别任务,并在未来可扩展到非结构化的人体活动识别。

关键词: 玻耳兹曼机, 人体动作识别, 深度信念网络, 无监督

Abstract: In order to solve the problem of human action recognition in a large number of videos with complex backgrounds and changing viewpoints on the Internet,an innovative method for human action recognition using unsupervised deep belief networks (DBNs) is proposed.This method uses deep belief networks (DBNs) and restricted Boltzmann machines for unconstrained video action recognition,and uses an unsupervised deep learning model to automatically extract appropriate feature representations without any prior knowledge.Through the identification of a challenging UCF sports data set,the method is proved to be accurate and effective.At the same time,this method is suitable for other visual recognition tasks,and will be extended to unstructured human activity recognition in the future.

Key words: Boltzmann machine, Deep belief networks, Human action recognition, Unsupervised

中图分类号:

TP391

洪耀球. 基于深度信念网络的视觉人体动作识别[J]. 计算机科学, 2021, 48(11A): 400-403. https://doi.org/10.11896/jsjkx.210200079

HONG Yao-qiu. Visual Human Action Recognition Based on Deep Belief Network[J]. Computer Science, 2021, 48(11A): 400-403. https://doi.org/10.11896/jsjkx.210200079

参考文献

[1]CHEN J L,LIU X F,ZHAN S.Realization of face sketch image based on unsupervised generative confrontation network[J].Computer Engineering and Science,2021,43(1):125-133.
[2]CHEN Y P,QIU W G.A review of human behavior recognition algorithms based on vision[J].Application Research of Computers,2019,36(7):1927-1934.
[3]GORELICK L,BLANK M,SHECHTMAN E,et al.Actions-asspace-timeshapes[J].IEEE Transactions on Pattern Anlysis and Machine Intelligence,2007,29(12):2247-2253.
[4]SCHULDT C,LAPTEV I,CAPUTO B.Recognizinghumanac-tions:alocalsvmapproach[C]//Proceedings of the 17th International Conference on Pattern Recognition(ICPR 2004).2004:32-36.
[5]REDDY K K,SHAH M.Recognizing 50 human actioncate gories of web videos[J].MachineVisionand Applications,2013,24(5):971-981.
[6]SARGANO A B,ANGELOV P,HABIB Z.A comprehensivereviewonh and craftedandlearning-based action representation approaches for human activity recognition[J].Applied Sciences,2017,7(1):110.
[7]SALAKHUTDINOV R,HINTON G.Deep boltzmannmachines[C]//Artificial Intelligence and Statistics.2009:448-455.
[8]ZHANG H.Research on Human Action Image RecognitionMethod under High Intensity Exercise[J].Computer Simulation,2019,36(9):469-472.
[9]HINTON G E,DAYAN P,FREY B J,et al.The“wake-sleep”algorithmfor unsupervised neural networks[J].Science,1995,268(5214):1158.
[10]SARGANO A B,WANG X,ANGELOV P,et al.Human action recognition using transfer learning with deep representations[C]//2017 International JointConferenceonNeural Networks(IJCNN).IEEE,2017:463-469.
[11]ATMOSUKARTO I,AHUJA N,GHANEM B.Actionre cognition using discrim inatives tructured trajectory groups[C]//IEEE Winter Conferenceon Applicationsof Computer Vision.IEEE,2015:899-906.
[12]YUAN C,LI X,HU W,et al.Modeling geometric-temporalc on text with directional pyramid co-occurrence for action recognition[J].IEEETransactionson ImageProcessing,2014,23(2):658-672.
[13]WANG H,KLSER A,SCHMID C,et al.Dense trajectories and motion bound arydescriptors for actionre cognition[J].International Journal of Computervision,2013,103(1):60-79.
[14]TIAN Y,SUKTHANKAR R,SHAH M.Spatiotemporalde-formable partmodels for action detection[C]//Proceedings of the IEEE Conference on Computer Visionan Dpattern Recognition.2013:2642-2649.
[15]WANG H,KLSER A,SCHMID C,et al.Actionrecognition by dense trajectories[C]//2011 IEEE Conference on ComputerVisionandPatternRecognition(CVPR).IEEE,2011:3169-3176.
[16]LE Q V,ZOU W Y,YEUNG S Y,et al.Learning hierarch icalinvariants patio-temporal features for actionre cognition with indepen dentsub space analysis[C]//2011 IEEE Conferenceon Computer Visionand PatternRecognition (CVPR).IEEE,2011:3361-3368.
[17]KOVASHKA A,GRAUMAN K.Learningahierarchy of dis-criminative space-time neigh borhood features for human action recognition[C]//2010 IEEE Conferenceon Computer Visionand Pattern Recognition (CVPR).IEEE,2010:2046-2053.

相关文章 15

[1]	宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲. 基于无监督集群级的科技论文异质图节点表示学习方法 Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level 计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196
[2]	李斌, 万源. 基于相似度矩阵学习和矩阵校正的无监督多视角特征选择 Unsupervised Multi-view Feature Selection Based on Similarity Matrix Learning and Matrix Alignment 计算机科学, 2022, 49(8): 86-96. https://doi.org/10.11896/jsjkx.210700124
[3]	解宇, 杨瑞玲, 刘公绪, 李德玉, 王文剑. 基于动态拓扑图的人体骨架动作识别算法 Human Skeleton Action Recognition Algorithm Based on Dynamic Topological Graph 计算机科学, 2022, 49(2): 62-68. https://doi.org/10.11896/jsjkx.210900059
[4]	侯宏旭, 孙硕, 乌尼尔. 蒙汉神经机器翻译研究综述 Survey of Mongolian-Chinese Neural Machine Translation 计算机科学, 2022, 49(1): 31-40. https://doi.org/10.11896/jsjkx.210900006
[5]	宁秋怡, 史小静, 段湘煜, 张民. 基于风格感知的无监督领域适应算法 Unsupervised Domain Adaptation Based on Style Aware 计算机科学, 2022, 49(1): 271-278. https://doi.org/10.11896/jsjkx.201200094
[6]	吴兰, 王涵, 李斌全. 基于自监督任务最优选择的无监督域自适应方法 Unsupervised Domain Adaptive Method Based on Optimal Selection of Self-supervised Tasks 计算机科学, 2021, 48(6A): 357-363. https://doi.org/10.11896/jsjkx.201000030
[7]	邹承明, 陈德. 高维大数据分析的无监督异常检测方法 Unsupervised Anomaly Detection Method for High-dimensional Big Data Analysis 计算机科学, 2021, 48(2): 121-127. https://doi.org/10.11896/jsjkx.191100141
[8]	马闯, 田青, 孙赫阳, 曹猛, 马廷淮. 基于双重权重偏差建模的无监督域适应 Unsupervised Domain Adaptation Based on Weighting Dual Biases 计算机科学, 2021, 48(2): 217-223. https://doi.org/10.11896/jsjkx.200700028
[9]	李金霞, 赵志刚, 李强, 吕慧显, 李明生. 改进的局部和相似性保持特征选择算法 Improved Locality and Similarity Preserving Feature Selection Algorithm 计算机科学, 2020, 47(6A): 480-484. https://doi.org/10.11896/JsJkx.20190800095
[10]	王成章, 白晓明, 杜金栗. 图像的扩散界面无监督聚类算法 Diffuse Interface Based Unsupervised Images Clustering Algorithm 计算机科学, 2020, 47(5): 149-153. https://doi.org/10.11896/jsjkx.190300125
[11]	罗月,童卞,景帅,张蒙,饶永明,闫峰. 基于卷积去噪自编码器的芯片表面弱缺陷检测方法 Detection Method of Chip Surface Weak Defect Based on Convolution Denoising Auto-encoders 计算机科学, 2020, 47(2): 118-125. https://doi.org/10.11896/jsjkx.190100141
[12]	任雪婷, 赵涓涓, 强彦, Saad Abdul RAUF, 刘继华. 联合成对学习和图像聚类的无监督肺癌亚型识别 Lung Cancer Subtype Recognition with Unsupervised Learning Combining Paired Learning and Image Clustering 计算机科学, 2020, 47(10): 200-206. https://doi.org/10.11896/jsjkx.190900073
[13]	陈深进, 薛洋. 基于改进卷积神经网络的短时公交客流预测 Short-term Bus Passenger Flow Prediction Based on Improved Convolutional Neural Network 计算机科学, 2019, 46(5): 175-184. https://doi.org/10.11896/j.issn.1002-137X.2019.05.027
[14]	曾凡智, 周燕, 余家豪, 罗粤, 邱腾达, 钱杰昌. 基于无监督学习的二维工程CAD模型端到端检索算法 End-to-End Retrieval Algorithm of Two-dimensional Engineering CAD Model Based on Unsupervised Learning 计算机科学, 2019, 46(12): 298-305. https://doi.org/10.11896/jsjkx.190900003
[15]	李锋,谢嗣弘. 基于无监督学习的移动心电信号异常诊断研究 Study on Abnormal Diagnosis of Moving ECG Signals Based on Unsupervised Learning 计算机科学, 2017, 44(Z11): 68-71. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.013

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed