TY - GEN
T1 - Learning human motion intention with 3D Convolutional Neural Network
AU - Owoyemi, Joshua
AU - Hashimoto, Koichi
N1 - Funding Information:
This work is partially supported by JSPS Grant-in-Aid 16H06536.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/23
Y1 - 2017/8/23
N2 - In this paper, we present an end-to-end learning approach for human motion inference from 3D point cloud data. Examples of human motion to be learned are collected as point cloud data through a 3D sensor, mapped into 3D occupancy grids and then used as supervised learning samples for a 3D Convolutional Neural Network (3D CNN). The 3D CNN model is able to learn spatiotemporal features from time steps of occupancy grids and predict human motion intentions with an accuracy of 83% within 60% of the motion performed. We demonstrate the performance of this model in real time by predicting the intention of a human arm motion for some predetermined targets, and furthermore generalise the model to new users whose data were not used in the training of the model. This approach is useful for human-robot interaction and human-computer interaction applications that need human motion learning without explicitly modelling the dynamics of the human motion.
AB - In this paper, we present an end-to-end learning approach for human motion inference from 3D point cloud data. Examples of human motion to be learned are collected as point cloud data through a 3D sensor, mapped into 3D occupancy grids and then used as supervised learning samples for a 3D Convolutional Neural Network (3D CNN). The 3D CNN model is able to learn spatiotemporal features from time steps of occupancy grids and predict human motion intentions with an accuracy of 83% within 60% of the motion performed. We demonstrate the performance of this model in real time by predicting the intention of a human arm motion for some predetermined targets, and furthermore generalise the model to new users whose data were not used in the training of the model. This approach is useful for human-robot interaction and human-computer interaction applications that need human motion learning without explicitly modelling the dynamics of the human motion.
KW - Convolutional Neural Network
KW - Motion Prediction
KW - Point Clouds
KW - Spatiotemporal Learning
UR - http://www.scopus.com/inward/record.url?scp=85030323901&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030323901&partnerID=8YFLogxK
U2 - 10.1109/ICMA.2017.8016092
DO - 10.1109/ICMA.2017.8016092
M3 - Conference contribution
AN - SCOPUS:85030323901
T3 - 2017 IEEE International Conference on Mechatronics and Automation, ICMA 2017
SP - 1810
EP - 1815
BT - 2017 IEEE International Conference on Mechatronics and Automation, ICMA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE International Conference on Mechatronics and Automation, ICMA 2017
Y2 - 6 August 2017 through 9 August 2017
ER -