Action Recognition Using DMM-Gabor Descriptor and Temporal Segmentation

In this paper, an effective method is proposed for recognizing human actions from sequences of depth images. Specifically, we propose an easy and intuitive method to divide a video into temporal segments of fixed length. Furthermore, the Depth Motion Maps are employed to represent the dynamics and statics of action and uses Gabor feature to gain a compact feature representation. Finally, we use Kernel Extreme Learning Machines for classification. The experimental results on the public MSR Action3D dataset show the proposed method is effective and it achieves good real-time performance.

[1]  Xiaodong Yang,et al.  EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[2]  Marco La Cascia,et al.  3D skeleton-based human action classification: A survey , 2016, Pattern Recognit..

[3]  Chengjun Liu,et al.  Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition , 2002, IEEE Trans. Image Process..

[4]  Ying Wu,et al.  Robust 3D Action Recognition with Random Occupancy Patterns , 2012, ECCV.

[5]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Ivan Laptev,et al.  On Space-Time Interest Points , 2005, International Journal of Computer Vision.

[7]  Antonio Fernández-Caballero,et al.  A survey of video datasets for human action and activity recognition , 2013, Comput. Vis. Image Underst..

[8]  Mario Fernando Montenegro Campos,et al.  STOP: Space-Time Occupancy Patterns for 3D Action Recognition from Depth Map Sequences , 2012, CIARP.

[9]  Xiaodong Yang,et al.  Recognizing actions using depth motion maps-based histograms of oriented gradients , 2012, ACM Multimedia.

[10]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[11]  Ronald Poppe,et al.  Vision-based human motion analysis: An overview , 2007, Comput. Vis. Image Underst..

[12]  Nasser Kehtarnavaz,et al.  Real-time human action recognition based on depth motion maps , 2013, Journal of Real-Time Image Processing.

[13]  Rama Chellappa,et al.  Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.