A Parallel Algorithm for Advanced Video Motion Estimation on Multicore Architectures

Momcilovic, Svetislav; Sousa, Leonel

doi:10.1109/cisis.2008.86

Cited by 12 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ME in AVC standards exploits the temporal redundancy between frames in a block-based approach: a current frame (CF) is divided into Macroblocks (MBs), and the best matching candidate is found for each of them, considering search areas (SAs) in several reference frames (RFs) and a distortion measure (typically the Sum of Absolute Differences (SAD)). Both the optimal search and the sub-optimal fast and adaptive (UMHS) search algorithms are used [2]. The most important computational challenges associated with the implementation of ME lie in the intensive processing, due to the large quantity of pixels being processed, the huge number of motion vector candidates intensively tested, and the high bandwidth requirements which impose complex questions such as data reutilization.…”

Section: Signal Processing For Codingmentioning

confidence: 99%

“…The Streaming SIMD Extensions 3 (SSE3) instruction set was also exploited to further improve performance. Experimental results for Video ME were obtained by using the JM 14.0 software implementation of H.264/MPEG-4 AVC [2]. Seven different sub-block types and five RFs are considered.…”

Section: Parallel Algorithms Implementationmentioning

confidence: 99%

“…A fast and efficient set of SIMD instructions is applied to speed up the SAD computation on the SPE, although the programmer has to perform the required data alignment. As soon as the ME process is finished, each ME thread sends the results back to the main memory [2]. The finest parallelization on best-matching-candidate perthread level was applied on the GPU/CUDA architecture with a huge number of cores and threads.…”

Section: Video Mementioning

confidence: 99%

See 2 more Smart Citations

Multi-core platforms for signal processing: source and channel coding

Sousa

Momcilovic

Silva

et al. 2009

2009 IEEE International Conference on Multimedia and Expo

Self Cite

View full text Add to dashboard Cite

In this paper we propose to show how signal processing algorithm designers can understand the nuances of multicore computing engines in order to conveniently exploit these powerful devices. This is illustrated by presenting source and channel coding, two fundamental operations in multimedia signal processing. We describe methods and principles to develop parallel signal processing algorithms to compute motion estimation for Advanced Video Coding, and Low-Density Parity-Check code decoding for forward error correction in the channel coding context. The paper will consider general purpose multi-core architectures and accelerators such as the Cell/B.E. and graphics processing units. Experimental evaluation of the multi-core systems allows their performance for signal processing applications to be compared side by side with previous hardware dedicated solutions.

show abstract

Section: Signal Processing For Codingmentioning

confidence: 99%

Section: Parallel Algorithms Implementationmentioning

confidence: 99%

Section: Video Mementioning

confidence: 99%

See 1 more Smart Citation

Multi-core platforms for signal processing: source and channel coding

Sousa

Momcilovic

Silva

et al. 2009

2009 IEEE International Conference on Multimedia and Expo

Self Cite

View full text Add to dashboard Cite

show abstract

“…Motion estimation (ME) is essential to reduce the temporal redundancy in video sequences, and is the most computationally intensive component of a video encoder. It contributes most of the compression ratio but consumes typically 60-80% of the video encoding time [1] [2]. So before applying the current video standards to real time applications, the ME process must be optimized deliberately.…”

Section: Introductionmentioning

confidence: 99%

Parallel optimization of motion estimation for video coding on cell BE processors

Zhu

Pan

Guo

et al. 2014

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

View full text Add to dashboard Cite

This paper proposes a parallel framework to speed up video coding on the Cell Broadband Engine (Cell BE) heterogeneous multicore platform. It integrates thread-level parallelism (TLP), data level parallelism (DLP) and an innovative data prefetching scheme to exploit the implicit parallelism of the most computationally intensive motion estimation procedure in video coding. The video frame is partitioned to several slices which are processed simultaneously on multicores to exploit TLP. The sum of absolute differences (SAD) calculation in the ME process is implemented by using SIMD instructions to exploit DLP. Slices are transferred using a data prefetching scheme to hide memory access delay, which enables the process of data access and the ME process to execute concurrently. Experimental results show that the proposed parallel implementation, compared with the serial implementation of video encoding, achieves significant performance improvement.

show abstract

“…Exploitation of the computational capacity of these heterogeneous multi-core processors without native shared memory is a research challenge. Programming models and parallel algorithms have been recently launched to the Cell/BE processor [1,4,5], namely algorithms and techniques to perform video parallel processing on the Cell/BE processor [17,18]. However, there is no general model suitable to implement in parallel the important class of LVIP methods on this type of architectures.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Evaluating Non-shared Memory CELL/BE Type Multi-core Architectures for Local Image and Video Processing

Momcilovic

Sousa

2010

J Sign Process Syst

Self Cite

View full text Add to dashboard Cite

Local processing, which is a dominant type of processing in image and video applications, requires a huge computational power to be performed in realtime. However, processing locality, in space and/or in time, allows to exploit data parallelism and data reusing. Although it is possible to exploit these properties to achieve high performance image and video processing in multi-core processors, it is necessary to develop suitable models and parallel algorithms, in particular for non-shared memory architectures. This paper proposes an efficient and simple model for local image and video processing on non-shared memory multi-core architectures. This model adopts a single program multiple data approach, where data is distributed, processed and reused in an optimal way, regarding the data size, the number of cores and the local memory capacity. The model was experimentally evaluated by developing video local processing algorithms and programming the Cell Broadband Engine multicore processor, namely for advanced video motion estimation and in-loop deblocking filtering. Furthermore, based on these experiences it is also addressed the main challenges of vectorization, and the reduction of branch mispredictions and computational load imbalances. The limits and advantages of the regular and adaptive algorithms are also discussed. Experimental results show the adequacy of the proposed model to perform local video processing, and that real-time is achieved even to process the most demanding parts of advanced video coding. Full-pixel motion estimation is performed over high resolution video (720 × 576 pixels) at a rate of 30 frames per second, by considering large search areas and five reference frames.

show abstract

A Parallel Algorithm for Advanced Video Motion Estimation on Multicore Architectures

Cited by 12 publications

References 9 publications

Multi-core platforms for signal processing: source and channel coding

Multi-core platforms for signal processing: source and channel coding

Parallel optimization of motion estimation for video coding on cell BE processors

Modeling and Evaluating Non-shared Memory CELL/BE Type Multi-core Architectures for Local Image and Video Processing

Contact Info

Product

Resources

About