Extreme Low-Resolution Activity Recognition Using a Super-Resolution-Oriented Generative Adversarial Network Article Swipe
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.3390/mi12060670
Activity recognition is a fundamental and crucial task in computer vision. Impressive results have been achieved for activity recognition in high-resolution videos, but for extreme low-resolution videos, which capture the action information at a distance and are vital for preserving privacy, the performance of activity recognition algorithms is far from satisfactory. The reason is that extreme low-resolution (e.g., 12 × 16 pixels) images lack adequate scene and appearance information, which is needed for efficient recognition. To address this problem, we propose a super-resolution-driven generative adversarial network for activity recognition. To fully take advantage of the latent information in low-resolution images, a powerful network module is employed to super-resolve the extremely low-resolution images with a large scale factor. Then, a general activity recognition network is applied to analyze the super-resolved video clips. Extensive experiments on two public benchmarks were conducted to evaluate the effectiveness of our proposed method. The results demonstrate that our method outperforms several state-of-the-art low-resolution activity recognition approaches.
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.3390/mi12060670
- https://www.mdpi.com/2072-666X/12/6/670/pdf?version=1623212894
- OA Status
- gold
- Cited By
- 11
- References
- 36
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3171471732