Implementation of Diamond Search Algorithm Using Parallel Processing Architecture

K. Shuma Roshini, M. Tejaswi
Gudlavalleru Engineering College, Gudlavalleru, A.P.India
International Journal of Engineering Research and Application (IJERA), Volume 3, Issue 6, 2013


   title={Implementation of Diamond Search Algorithm Using Parallel Processing Architecture},

   author={Roshini, K. Shuma and Tejaswi, M.},



Download Download (PDF)   View View   Source Source   



In video communication whole content of video cannot be stored without processing. So there is a need to compress the video before transmission and storage this process is called as video compression. Video compression plays an important role with regard to real-time scouting/video conferencing applications. Regarding the entire motion based video compression process, movement estimation is the most computationally expensive and time consuming process. Motion estimation is the key element in video compression. The Motion Estimation is a process which determines motion between two or more frames and finds best possible macro block. There are several algorithms on block matching to name a few, Full Search Motion estimation [FS], Three Step Search Motion Estimation [TSS], New Three Step Search Motion Estimation [NTSS], Four Step Search Motion Estimation [FSS], Diamond Search Motion Estimation [DS].Instead of trying to further reduce computational complexity of these algorithms it is better to implement these algorithms on parallel processing architecture. In this paper Diamond Search Algorithm is implementation on CPU and GPU.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: