Geometric Algebra Representation and Ensemble Action Classification Method for 3D Skeleton Orientation Data

In this paper, we propose a novel human body posture representation based on Geometric Algebra to extract the angles and orientations of the most informative body joints to describe human body postures. As a motion usually consists of a number of postures, which are different even in the same type of motion. We treat the postures of a motion independently. For each posture, a new Geometric Algebra based skeleton posture descriptor is used to construct the feature vectors as the input for the Support Vector Machine classifier to decide its motion type. To get the type of the whole motion, we choose the most frequent class from the sequence of predictions of the motion postures using a simple voting scheme. We have tested the method on a public benchmark SYSU-3D-HIO and an in-house dataset of human exercises. The results have demonstrated the effectiveness of our method.

[1]  Weihua Sheng,et al.  Human gesture recognition through a Kinect sensor , 2012, 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[2]  Bart Selman,et al.  Unstructured human activity detection from RGBD images , 2011, 2012 IEEE International Conference on Robotics and Automation.

[3]  Min Huang,et al.  Discriminative parts learning for 3D human action recognition , 2018, Neurocomputing.

[4]  Wei-Shi Zheng,et al.  Jointly Learning Heterogeneous Features for RGB-D Activity Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Xiangyang Wang,et al.  GA-ORB: A New Efficient Feature Extraction Algorithm for Multispectral Images Based on Geometric Algebra , 2019, IEEE Access.

[6]  Peter H. N. de With,et al.  Automatic video-based human motion analyzer for consumer surveillance system , 2009, IEEE Transactions on Consumer Electronics.

[7]  Alan Dix,et al.  Human-computer interaction, foundations and new paradigms , 2017, J. Vis. Lang. Comput..

[8]  Zhihai He,et al.  Hybrid representation learning for cross-modal retrieval , 2019, Neurocomputing.

[9]  Dit-Yan Yeung,et al.  Multi-Task Learning in Heterogeneous Feature Spaces , 2011, AAAI.

[10]  Fei Han,et al.  Space-Time Representation of People Based on 3D Skeletal Data: A Review , 2016, Comput. Vis. Image Underst..

[11]  Jake K. Aggarwal,et al.  View invariant human action recognition using histograms of 3D joints , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Youfu Li,et al.  DSRF: A flexible trajectory descriptor for articulated human action recognition , 2018, Pattern Recognit..

[13]  Xiangyang Wang,et al.  A Novel Least-Mean Kurtosis Adaptive Filtering Algorithm Based on Geometric Algebra , 2019, IEEE Access.

[14]  Pradeep T. Kale,et al.  Hand gesture recognition for human-computer interaction , 2016 .

[15]  Wenming Cao,et al.  Joint Sparse Representation Model for Multi-Channel Image Based on Reduced Geometric Algebra , 2018, IEEE Access.

[16]  Joseph J. LaViola,et al.  Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition , 2013, International Journal of Computer Vision.

[17]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Wenming Cao,et al.  Liver Fibrosis Classification Based on Transfer Learning and FCNet for Ultrasound Images , 2017, IEEE Access.

[19]  Helena M. Mentis,et al.  Instructing people for training gestural interactive systems , 2012, CHI.

[20]  Zhi Zhang,et al.  Fast Deep Neural Networks With Knowledge Guided Training and Predicted Regions of Interests for Real-Time Video Object Detection , 2018, IEEE Access.

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

[22]  Wenming Cao,et al.  Multivector Sparse Representation for Multispectral Images Using Geometric Algebra , 2019, IEEE Access.

[23]  Michael J. Black,et al.  Pose-conditioned joint angle limits for 3D human pose reconstruction , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Ye Duan,et al.  Tongue Images Classification Based on Constrained High Dispersal Network , 2017, Evidence-based complementary and alternative medicine : eCAM.

[25]  Zicheng Liu,et al.  HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Wanqing Li,et al.  Action recognition based on a bag of 3D points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[27]  Mohan M. Trivedi,et al.  Joint Angles Similarities and HOG2 for Action Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[28]  Zhang Chun-xi.  Restricted Boltzmann Machines , 2015 .

[29]  Zhihai He,et al.  Multimodal Medical Image Registration Based on Feature Spheres in Geometric Algebra , 2018, IEEE Access.

[30]  Hans-Peter Seidel,et al.  VNect , 2017, ACM Trans. Graph..

[31]  Youfu Li,et al.  A new descriptor for multiple 3D motion trajectories recognition , 2013, 2013 IEEE International Conference on Robotics and Automation.