|Search by item||HOME > Access full text > Search by item|
JBE, vol. 25, no. 5, pp.750-757, September, 2020
A Study on Improvement of the Human Posture Estimation Method for Performing Robots
Cheonyu Park, Jaehun Park, and Jeakweon Han
C.A E-mail: firstname.lastname@example.org
One of the basic tasks for robots to interact with humans is to quickly and accurately grasp human behavior. Therefore, it is necessary to increase the accuracy of human pose recognition when the robot is estimating the human pose and to recognize it as quickly as possible. However, when the human pose is estimated using deep learning, which is a representative method of artificial intelligence technology, recognition accuracy and speed are not satisfied at the same time. Therefore, it is common to select one of a top-down method that has high inference accuracy or a bottom-up method that has high processing speed. In this paper, we propose two methods that complement the disadvantages while including both the advantages of the two methods mentioned above. The first is to perform parallel inference on the server using multi GPU, and the second is to mix bottom-up and One-class Classification. As a result of the experiment, both of the methods presented in this paper showed improvement in speed. If these two methods are applied to the entertainment robot, it is expected that a highly reliable interaction with the audience can be performed.
Keyword: Pose estimation, bottom-up, top-down, One-class Classification
 C. Breazeal et al., "Interactive robot theatre," Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453), Las Vegas, NV, USA, 2003, pp. 3648-3655 vol.3, doi: 10.1109/IROS.2003.1249722.
 T. Mukai, M. Onishi, T. Odashima, S. Hirano and Z. Luo, "Development of the Tactile Sensor System of a Human-Interactive Robot “RI-MAN”," in IEEE Transactions on Robotics, vol. 24, no. 2, pp. 505-512, April 2008, doi: 10.1109/TRO.2008.917006.
 Ishiguro, H., Ono, T., Imai, M., Maeda, T., Kanda, T. and Nakatsu, R. (2001), "Robovie: an interactive humanoid robot", Industrial Robot, Vol. 28 No. 6, pp. 498-504. https://doi.org/10.1108/0143991011 0410051
 Oved, D. Real-time human pose estimation in the browserwith TensorFlow.js.TensorFlow Medium, May 2018. URL https://bit.ly/ 2KMnwgv. (accessed Jul. 14, 2020)
 Jin, Sheng, et al. "Towards multi-person pose tracking: Bottom-up and top-down methods." ICCV PoseTrack Workshop. Vol. 2. No. 3. 2017.
 Sandler, Mark, et al. "Mobilenetv2: Inverted residuals and linear bottlenecks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. https://doi.org/10.1109/cvpr.2018. 00474
 Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. https://doi.org/10.1109/cvpr.2014.81
 Chalapathy, Raghavendra, and Sanjay Chawla. "Deep learning for anomaly detection: A survey." arXiv preprint arXiv:1901.03407 (2019).
 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
 Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE international conference on computer vision. 2015. https://doi.org/10.1109/iccv. 2015.169