Posture Pattern Recognition Analysis in Lectures
Abstract
The Study of Posture Analysis and Non-Verbal Communication plays a pivotal role in enhancing communication among individuals in various contexts. The ability to decode and comprehend messages conveyed through gestures, facial expressions, and body movements is crucial for fostering more effective and meaningful interactions. Accordingly, this present work aims to conduct an exploratory analysis of posture patterns among speakers worldwide. To achieve this, the Openpifpaf algorithm was employed in videos of lectures for pose extraction, and the K-means clustering algorithm was utilized to distinguish commonly adopted postures during this lectures. The evaluation regarding the representativeness of keyposes involved an online questionnaire in which participants were asked to classify certain speaker poses into one of the clusters. The results revealed that the K-means algorithm achieved an accuracy rate of 85.71%.
References
Wang, I., and Ruiz, J. (2021). Examining the Use of Nonverbal Communication in Virtual Agents. International Journal of Human–Computer Interaction, 37, 1648 - 1673.
Jeong, D.C., Xu, J.J., and Miller, L.C. (2020). Inverse Kinematics and Temporal Convolutional Networks for Sequential Pose Analysis in VR. 2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR), 274-281.
Willett, N.S., Shin, H.V., Jin, Z., Li, W., and Finkelstein, A. (2020). Pose2Pose: pose selection and transfer for 2D character animation. Proceedings of the 25th International Conference on Intelligent User Interfaces.
Miki, D., Abe, S., Chen, S., and Demachi, K. (2020). Robust human pose estimation from distorted wide-angle images through iterative search of transformation parameters. Signal, Image and Video Processing, 14, 693-700.
Qiu, R., Teng, W., Wei, Z., Zhang, C., Zhong, Y., and Zhai, J. (2022). Fall Detection Algorithm Based on Lightweight Openpose Model with Attention Mechanism. Academic Journal of Science and Technology.
Francisco, J.A. and Rodrigues, P.S. (2022). Computer Vision Based on a Modular Neural Network for Automatic Assessment of Physical Therapy Rehabilitation Activities. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 2174-2183.
Wu, A. and Qu, H. (2020). Multimodal Analysis of Video Collections: Visual Exploration of Presentation Techniques in TED Talks. IEEE Transactions on Visualization and Computer Graphics, 26, 2429-2442.
Kreiss, S., Bertoni, L., and Alahi, A. (2021). OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association. IEEE Transactions on Intelligent Transportation Systems, 23, 13498-13511.
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations.
Rousseeuw, P.J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53-65.
Caliński, T., and Harabasz, J. (1974). A dendrite method for cluster analysis. Communications in Statistics-theory and Methods, 3, 1-27.
Thorndike, R.L. (1953). Who belongs in the family? Psychometrika, 18, 267-276.
