Human Activity Recognition Based on $\Re$ Transform and Fourier Mellin Transform
| Autor: | Weiming Hu, Pengfei Zhu, Qingdi Wei, Li Li |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
business.industry
Dimensionality reduction Pattern recognition Fractional Fourier transform Activity recognition Fourier mellin transform Computer Science::Computer Vision and Pattern Recognition Image sequence Mellin inversion theorem Two-sided Laplace transform Computer vision Artificial intelligence Invariant (mathematics) business Mathematics |
| Zdroj: | Advances in Visual Computing ISBN: 9783642105197 ISVC (2) |
| Popis: | Human activity recognition is attracting a lot of attention in the computer vision domain. In this paper we present a novel human activity recognition method based on $\Re$ transform and Fourier Mellin Transform (FMT). Firstly, we convert the original image sequence to the Radon domain, get the $\Re$ transform curves by $\Re$ transform. Then we extract the Rotation-Scaling-Translation (RST) invariant features by FMT and use to have dimension reduction by PCA method. At the recognition stage, the Earth Mover's Distance (EMD) is used here. In the experiment, we compare our method to other methods. The experimental results show the effectiveness of our method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|