Single and two-person(s) pose estimation based on R-WAA
| Autor: | Zhongfu Ye, Rashid Khan, Khush Bakhat, M. Mattah Islam, M. Shujah Islam |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer Networks and Communications
business.industry Computer science Estimator Pattern recognition Domain (software engineering) Activity recognition Alpha (programming language) Hardware and Architecture Media Technology Waveform Artificial intelligence business Focus (optics) Pose Spatial analysis Software |
| Zdroj: | Multimedia Tools and Applications. 81:681-694 |
| ISSN: | 1573-7721 1380-7501 |
| Popis: | Human pose estimation methods have difficulties predicting the correct pose for persons due to challenges in scale variation. Existing works in this domain mainly focus on single-person pose estimation. To counter this challenge we have developed a system that can efficiently estimate both one and two individual poses. We termed remarkable joint based, Waveform, Angle, and Alpha characteristics, as R-WAA. R-WAA is a novel up-bottom human pose estimation method developed using two-dimensional body skeletal joint points. They are capturing all required spatial information using waveform characteristics, angle characteristics, and alpha characteristics. All pose estimator characteristics are developed using a remarkable joint, which is the origin of all poses. The proposed algorithm is evaluated for one and two individuals databases: KARD- Kinect Activity Recognition Dataset and SBU Kinect Interaction Dataset. The results of experiments validate that R-WAA outperforms state-of-the-art approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink