A new relational geometric feature for human action recognition
Author
Vinagre, M.; Aranda, J.; Casals, A.
Type of activity
Book chapter
Book
Informatics in Control, Automation and Robotics: 10th International Conference, ICINCO 2013: Reykjavík, Iceland, July 29-31, 2013: revised selected papers
Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. In this article, a new geometric correspondence between joints called Trisarea feature is presented. It is defined as the area of the triangle formed by three joints. Relevant triangles describing human pose are identified and it is shown how the variation over time of the s...
Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. In this article, a new geometric correspondence between joints called Trisarea feature is presented. It is defined as the area of the triangle formed by three joints. Relevant triangles describing human pose are identified and it is shown how the variation over time of the selected Trisarea features constitutes a descriptor of human action.
Experimental results show a comparison with other methods and demonstrate how this Trisarea-based representation can be applied to human action recognition.
Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. In this article, a new geometric correspondence between joints called Trisarea feature is presented. It is defined as the area of the triangle formed by three joints. Relevant triangles describing human pose are identified and it is shown how the variation over time of the selected Trisarea features constitutes a descriptor of human action. Experimental results show a comparison with other methods and demonstrate how this Trisarea-based representation can be applied to human action recognition.
Citation
Vinagre, M.; Aranda, J.; Casals, A. A new relational geometric feature for human action recognition. "Lecture notes in electrical engineering", Gener 2015, vol. 325, p. 263-278.
Share
