|
|
- 2016
基于深度学习的人体行为识别
|
Abstract:
为了识别公共区域等特定场所下的人体行为,提出了一种基于深度学习的人体行为识别方法。首先,预处理训练样本集和测试样本集中的所有图像,通过高斯混合模型提取出目标运动前景。其次,对训练样本集中各种目标行为建立样本库,定义不同类别的识别行为作为先验知识,用于训练深度学习网络。最后,结合深度学习所得到的网络模型,分类识别测试样本集中的各种行为,并将识别的结果和当前流行方法进行了比较。实验结果表明,该人体行为识别方法优于其它方法,平均识别率相比其他方法有较大的提高
| [1] | Wu Xinyu, Ou Yongsheng, Qian Huihuan, et al. A Detection System for Human Abnormal Behavior[C]. 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China, 2005 |
| [2] | Chen Yufeng, Liang Guoyuan, Lee K K, et al. Abnormal Behavior Detection by Multi-SVM-based Bayesian Network[C]. International Conference on Information Acquisition, Guangzhou, China, 2007 |
| [3] | Wei Xiaoli,Shen Weiming. Gabor-MRF Model Based on Color Texture Image Segmentation[J]. Geomatics and Information Science of Wuhan University, 2010, 35(8):955-958(魏小莉,沈未名. 一种基于马尔科夫随机场模型的彩色纹理图像分割[J]. 武汉大学学报·信息科学版, 2010, 35(8):955-958) |
| [4] | Yang Lujing,Wang Deshi,Li Yu. A SAR Image Shadow Modeling and Classification Method Based on HMM and Chain Code[J]. Geomatics and Information Science of Wuhan University, 2010, 35(2):215-218(杨露菁,王德石,李煜. 利用边界链编码和HMM进行SAR图像阴影建模和分类[J]. 武汉大学学报·信息科学版, 2010, 35(2):215-218) |
| [5] | Cai D, He X, Han J. Using Graph Model for Face Analysis[OL]. http://www.cad.zju.edu.cn/home/dengcai/Publication/TR/UIUCDCS-R-2005-2636.pdf, 2005 |
| [6] | Kosmopoulos D I, Voulodimos A S, Varvarigou T A. Behavior Recognition from Multiple Views Using Fused Hidden Markov Models[M]. Berlin:Springer-Verlag, 2010 |
| [7] | Zhang Fan, Guo Li, Lu Haixian, et al. Star Skeleton for Human Behavior Recognition[C]. IEEE International Conference on Audio, Language and Image Processing, Shanghai, China,2012 |
| [8] | Meng Y, Jin Y, Yin J. Modeling Activity-dependent Plasticity in Bcm Spiking Neural Networks with Application to Human Behavior Recognition[J]. IEEE Transactions on Neural Networks, 2011, 22(12):1952-1966 |
| [9] | Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786):504-507 |
| [10] | Chen C C, Aggarwal J K. An Adaptive Background Model Initialization Algorithm with Objects Moving At Different Depths[C]. IEEE International Conference on Image Processing, San Diego, USA, 2008 |
| [11] | Niu F, Abdel-Mottaleb M. HMM-based Segmentation and Recognition of Human Activities from Video Sequences[C]. IEEE International Conference on Multimedia and Expo, Amsterdam, Netherlands, 2005 |
| [12] | Hinton G E, Dayan P, Frey B J, et al. The "Wake-sleep" Algorithm for Unsupervised Neural Networks[J]. Science, 1995, 268:1158-1161 |
| [13] | Laptev I, Marszalek M, Schmid C, et al. Learning Realistic Human Actions from Movies[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008 |
| [14] | Zhou Hanning, Kimber D. Unusual Event Detection via Multi-Camera Video Mining[C]. 18th International Conference on Pattern Recognition, Hong Kong, China, 2006 |
| [15] | Fathi A, Mori G. Action Recognition by Learning Mid-level Motion Features[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008 |
| [16] | Hinton G E, Osindero S, Teh Y W. A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation, 2006, 18(7):1527-1554 |
| [17] | Dollár P, Rabaud V, Cottrell G, et al. Behavior Recognition via Sparse Spatio-temporal Features[C]. IEEE International Workshop on Joint, Beijing, 2005 |
| [18] | Baccouche M, Mamalet F, Wolt C, et al. Sequential Deep Learning for Human Action Recognition[M]//Human Behavior Understanding, Berlin:Springer-Verlag, 2011:29-39 |
| [19] | Gilbert A, Illingworth J, Bowden R. Fast Realistic Multi-Action Recognition Using Mined Dense Spatio-Temporal Features[C]. IEEE International Conference on Computer Vision, Kyoto, Japan, 2009 |
| [20] | Bregonzio M, Gong S, Xiang T. Recognising Action as Clouds of Space-time Interest Points[C]. IEEE International Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009 |
| [21] | Abdi J, Nekoui M A. Determined Prediction of Nonlinear Time Series via Emotion Temporal Difference Learning[C]. Control and Decision Conference, Yantai, China, 2008 |
| [22] | Ning Huazhong, Xu Wei, Zhou Yue, et al. Temporal Difference Learning to Detect Unsafe System States[C]. IEEE International Conference on pattern Recognition, Tampa, USA, 2008 |
| [23] | Stauffer C, Grimson W E L. Adaptive Background Mixture Model for Real-time Tracking[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, Washington, USA, 1999 |
