Fuzzy Motion Detector based on 2D-Convolutions for Deinterlacing using Graphics Cards

In the last decade, consumer graphics cards have increased their computing power and capabilities mainly due to the computer games industry. These cards are programmable and capable of processing huge amounts of data in a Streaming Pipelined Architecture. In this situation, 2D convolutions are highly efficient and can be easily mapped on graphics hardware. In this work, we adapt a fuzzy motion detector to the hardware graphics computation framework in order to achieve a successful motion-adaptive video deinterlacing solution.