A self-adaptive weighted affinity propagation clustering for key frames extraction on human action recognition

Display Omitted We propose a novel approach for key frames extraction on human action recognition.Energy Feature (EF) presents human action effectively and intuitively.We propose a Self-adaptive Weighted Affinity Propagation (SWAP) algorithm. In this paper, we propose a novel approach for key frames extraction on human action recognition from 3D video sequences. To represent human actions, an Energy Feature (EF), combining kinetic energy and potential energy, is extracted from 3D video sequences. A Self-adaptive Weighted Affinity Propagation (SWAP) algorithm is then proposed to extract the key frames. Finally, we employ SVM to recognize human actions on the EFs of selected key frames. The experiments show the information including whole action course can be effectively extracted by our method, and we obtain good recognition performance without losing classification accuracy. Moreover, the recognition speed is greatly improved.

[1]  Zhou Yong.  Affinity propagation based on K-mutual nearest neighbor consistency , 2012 .

[2]  Hongjie Jia,et al.  A density-adaptive affinity propagation clustering algorithm based on spectral dimension reduction , 2014, Neural Computing and Applications.

[3]  Yongxiong Wang,et al.  Human activities segmentation and location of key frames based on 3D skeleton , 2014, CCC 2014.

[4]  Yifan Wang,et al.  Web Page Clustering via Partition Adaptive Affinity Propagation , 2009, ISNN.

[5]  Adrian Hilton,et al.  Automatic 3D Video Summarization: Key Frame Extraction from Self-Similarity , 2008 .

[6]  Fan Chen,et al.  Extraction of Discriminative Patterns from Skeleton Sequences for Human Action Recognition , 2012, 2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future.

[7]  Pong C. Yuen,et al.  Human action recognition using boosted EigenActions , 2010, Image Vis. Comput..

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  Fan Yang,et al.  A Poisson-based adaptive affinity propagation clustering for SAGE data , 2010, Comput. Biol. Chem..

[10]  Wei Zheng,et al.  Human Action Recognition Based on Key Frames , 2011 .

[11]  Xiangliang Zhang,et al.  K-AP: Generating Specified K Clusters by Efficient Affinity Propagation , 2010, 2010 IEEE International Conference on Data Mining.

[12]  Xuelong Li,et al.  Selecting Key Poses on Manifold for Pairwise Action Recognition , 2012, IEEE Transactions on Industrial Informatics.

[13]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Yang Gao,et al.  Multi-layered gesture recognition with Kinect , 2015, J. Mach. Learn. Res..

[15]  Shengping Zhang,et al.  Action recognition based on overcomplete independent components analysis , 2014, Inf. Sci..

[16]  Hans-Peter Seidel,et al.  An efficient algorithm for keyframe-based motion retrieval in the presence of temporal deformations , 2008, MIR '08.

[17]  Rémi Ronfard,et al.  A survey of vision-based methods for action representation, segmentation and recognition , 2011, Comput. Vis. Image Underst..

[18]  Zhou Jia-xin.  Background generation based on modified K-means clustering algorithm , 2007 .

[19]  Ronald Poppe,et al.  A survey on vision-based human action recognition , 2010, Image Vis. Comput..

[20]  Ling Shao,et al.  Boosted key-frame selection and correlated pyramidal motion-feature representation for human action recognition , 2013, Pattern Recognit..

[21]  Zohreh Azimifar,et al.  A new approach to speed up in action recognition based on key-frame extraction , 2013, 2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP).

[22]  Ruzena Bajcsy,et al.  Sequence of the Most Informative Joints (SMIJ): A new representation for human skeletal action recognition , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[23]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[24]  Luc Van Gool,et al.  Action snippets: How many frames does human action recognition require? , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  J. Sullivan,et al.  Action Recognition by Shape Matching to Key Frames , 2002 .

[26]  Qi Meng,et al.  Density-Sensitive Semi-supervised Affinity Propagation Clustering , 2014 .