Abstract
Action recognition systems mostly work with videos of proper quality and resolution. Even most challenging bench- mark databases for action recognition, hardly include videos of low-resolution from, e.g., surveillance cameras. In videos recorded by such cameras, due to the distance between people and cameras, people are pictured very small and hence challenge action recognition algorithms. Simple upsampling methods, like bicubic interpolation, cannot retrieve all the detailed information that can help the recognition. To deal with this problem, in this paper we combine results of bicubic interpolation with results of a state-of- the-art deep learning-based super-resolution algorithm, through an alpha-blending approach. The experimental results obtained on down-sampled version of a large subset of Hoolywood2 benchmark database show the importance of the proposed system in increasing the recognition rate of a state-of-the-art action recognition system for handling low-resolution videos.
Original language | English |
---|---|
Title of host publication | International Conference on Image Processing Theory, Tools and Applications (IPTA), 2015 |
Number of pages | 6 |
Publisher | IEEE Signal Processing Society |
Publication date | 2015 |
Pages | 67 - 72 |
ISBN (Print) | 978-1-4799-8636-1, 978-1-4799-8637-8 |
DOIs | |
Publication status | Published - 2015 |
Event | IEEE International Conference on Image Processing Theory, Tools and Applications - Orleans, France Duration: 10 Nov 2015 → 13 Nov 2015 Conference number: 5th |
Conference
Conference | IEEE International Conference on Image Processing Theory, Tools and Applications |
---|---|
Number | 5th |
Country/Territory | France |
City | Orleans |
Period | 10/11/2015 → 13/11/2015 |