Real-time Video Enhancement Using Graphical Processing Units
| Autor: | Asela Dasanayaka, Roshan Ragel, Rosen Silva |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Video recording
0209 industrial biotechnology Computer science Computation media_common.quotation_subject Real-time computing 02 engineering and technology Video quality Instruction set CUDA 020901 industrial engineering & automation Histogram 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Quality (business) Graphics media_common |
| Zdroj: | 2018 Moratuwa Engineering Research Conference (MERCon). |
| DOI: | 10.1109/mercon.2018.8421937 |
| Popis: | In this paper, we propose a real-time video enhancing algorithm which uses the Graphical Processing Units(GPUs) for faster parallel computations. Also, the paper will discuss the performance gains with GPU respect to a Central Processing Units(CPUs). The video enhancing algorithm is written to address the real-time video enhancement scenario, hence this paper will discuss more on the speed and the quality of the video enhancement. The paper contains the discussion about the trade-off between the quality and speed of the real-time-video enhancement. The latter part of the paper will discuss the optimizations to have real-time performance that is needed to enhance and play videos up to 4k videos. This paper proposes a generic implementation that can be used to have high-end video quality using low-end video recording devices like mass scale CCTV cameras, etc. This implementation will use NVIDIA CUDA enabled graphics cards. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|