6533b7d0fe1ef96bd125a26c

RESEARCH PRODUCT

Efficient smart-camera accelerator: A configurable motion estimator dedicated to video codec

Barthélémy HeyrmanDominique GinhacJohel MiteranWajdi ElhamziWajdi ElhamziMohamed AtriJulien Dubois

subject

Motion compensationHardware and ArchitectureComputer scienceMotion estimationReal-time computingHardware accelerationCodecSmart cameraField-programmable gate arraySoftwareQuarter-pixel motionBlock-matching algorithm

description

Smart cameras are used in a large range of applications. Usually the smart cameras transmit the video or/and extracted information from the video scene, frequently on compressed format to fit with the application requirements. An efficient hardware accelerator that can be adapted and provide the required coding performances according to the events detected in the video, the available network bandwidth or user requirements, is therefore a key element for smart camera solutions. We propose in this paper to focus on a key part of the compression system: motion estimation. We have developed a flexible hardware implementation of the motion estimator based on FPGA component, fully compatible with H.264, which enables the integer motion search, the fractional search and variable block size to be selected and adjusted. The main contributions of this paper are the definition of an architecture allowing flexibility and some new hardware optimizations of the architecture of the motion estimation allowing the improvement of the performances (computing time or hardware resources) compared to the state of the art. The paper describes the design and proposes a comparison with state-of-art architectures. The obtained FPGA based architecture can process integer motion estimation on 720x576 video streams at 67fps using full search strategy, and sub-pel refinement up to 650KMacroblocks/s.

https://doi.org/10.1016/j.sysarc.2013.05.005