Mutually reinforcing motion-pose framework for pose invariant action recognition
| Autor: | Nadia Magnenat Thalmann, Eam Khwang Teoh, Manoj Ramanathan, Wei Yun Yau |
|---|---|
| Přispěvatelé: | School of Electrical and Electronic Engineering, Institute for Media Innovation (IMI), Research Techno Plaza |
| Rok vydání: | 2019 |
| Předmět: |
Pose-invariant Motion Feature
Aaction Recognition Computer science business.industry Applied Mathematics ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Kinematics Computer Science Applications Robustness (computer science) Computer Science::Computer Vision and Pattern Recognition Electrical and electronic engineering [Engineering] Action recognition Computer vision Computer Vision and Pattern Recognition Artificial intelligence Electrical and Electronic Engineering Invariant (mathematics) business |
| Zdroj: | International Journal of Biometrics. 11:113 |
| ISSN: | 1755-831X 1755-8301 |
| DOI: | 10.1504/ijbm.2019.10020082 |
| Popis: | Action recognition from videos has many potential applications. However, there are many unresolved challenges, such as pose-invariant recognition, robustness to occlusion and others. In this paper, we propose to combine motion of body parts and pose hypothesis generation validated with specific canonical poses observed in a novel mutually reinforcing framework to achieve pose-invariant action recognition. To capture the temporal dynamics of an action, we introduce temporal stick features computed using the stick poses obtained. The combination of pose-invariant kinematic features from motion, pose hypothesis and temporal stick features are used for action recognition, thus forming a mutually reinforcing framework that repeats until the action recognition result converges. The proposed mutual reinforcement framework is capable of handling changes in posture of the person, occlusion and partial view-invariance. We perform experiments on several benchmark datasets which showed the performance of the proposed algorithm and its ability to handle pose variation and occlusion. NRF (Natl Research Foundation, S’pore) ASTAR (Agency for Sci., Tech. and Research, S’pore) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|