SAD PROCESSOR FOR MULTIPLE MACROBLOCK MATCHING IN FAST SEARCH VIDEO MOTION ESTIMATION

Abstract
Motion estimation is a very important but computationally complex task in video coding. Process of determining motion vectors based on the temporal correlation of consecutive frame is used for video compression. In order to reduce the computational complexity of motion estimation and maintain the quality of encoding during motion compensation, different fast search techniques are available. These block based motion estimation algorithms use the sum of absolute difference (SAD) between corresponding macroblock in current frame and all the candidate macroblocks in the reference frame to identify best match. Existing implementations can perform SAD between two blocks using sequential or pipeline approach but performing multi operand SAD in single clock cycle with optimized recourses is state of art. In this paper various parallel architectures for computation of the fixed block size SAD is evaluated and fast parallel SAD architecture is proposed with optimized resources. Further SAD processor is described with 9 processing elements which can be configured for any existing fast search block matching algorithm. Proposed SAD processor consumes 7% fewer adders compared to existing implementation for one processing elements. Using nine PE it can process 84 HD frames per second in worse case which is good outcome for real time implementation. In average case architecture process 325 HD frames per second.

Authors
Nehal N. Shah1, Upena D. Dalal2
Sarvajanik College of Engineering and Technology, India1, Sardar Vallaabhbhai National Institute of Technology, India2

Keywords
Motion estimation (ME), Block Matching Algorithm (BMA), Sum of Absolute Difference (SAD), Processing Element (PE), Macroblock (MB), SAD processor, Diamond Search Architecture
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 5 , Issue: 3 )
Date of Publication :
February 2015

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.