Deep Learning based Super-Resolution for Improved Action Recognition

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

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.
Luk

Detaljer

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.
OriginalsprogEngelsk
TitelInternational Conference on Image Processing Theory, Tools and Applications (IPTA), 2015
Antal sider6
UdgiverIEEE Signal Processing Society
Publikationsdato2015
Sider67 - 72
ISBN (trykt)978-1-4799-8636-1, 978-1-4799-8637-8
DOI
StatusUdgivet - 2015
Begivenhed - Orleans, Frankrig

Konference

KonferenceIEEE International Conference on Image Processing Theory, Tools and Applications
Nummer5th
LandFrankrig
ByOrleans
Periode10/11/201513/11/2015

Download-statistik

Ingen data tilgængelig
ID: 215920478