scholarly journals Performance Analysis of OpenCL and CUDA Programming Models for the High Efficiency Video Coding

2021 ◽  
Author(s):  
Randa Khemiri ◽  
Soulef Bouaafia ◽  
Asma Bahba ◽  
Maha Nasr ◽  
Fatma Ezahra Sayadi
Keyword(s):  
Motion Estimation ◽  
Execution Time ◽  
High Efficiency ◽  
Graphics Processing Unit ◽  
Block Matching ◽  
Performance Ratio ◽  
Processing Unit ◽  
High Efficiency Video Coding ◽  
Estimation Algorithms ◽  
Cuda Programming

In Motion estimation (ME), the block matching algorithms have a great potential of parallelism. This process of the best match is performed by computing the similarity for each block position inside the search area, using a similarity metric, such as Sum of Absolute Differences (SAD). It is used in the various steps of motion estimation algorithms. Moreover, it can be parallelized using Graphics Processing Unit (GPU) since the computation algorithm of each block pixels is similar, thus offering better results. In this work a fixed OpenCL code was performed firstly on several architectures as CPU and GPU, secondly a parallel GPU-implementation was proposed with CUDA and OpenCL for the SAD process using block of sizes from 4x4 to 64x64. A comparative study established between execution time on GPU on the same video sequence. The experimental results indicated that GPU OpenCL execution time was better than that of CUDA times with performance ratio that reached the double.

An Efficient Algorithm for Fast Block Motion Estimation in High Efficiency Video Coding

2016 ◽  
pp. 132-150
Author(s):  
Murugesan Ezhilarasan ◽  
Kumar K. Nirmal ◽  
P. Thambidurai
Keyword(s):  
Motion Estimation ◽  
High Efficiency ◽  
Search Time ◽  
Temporal Correlation ◽  
Block Matching ◽  
Video Encoding ◽  
Computational Time ◽  
High Efficiency Video Coding ◽  
Block Matching Algorithm ◽  
Estimation Algorithms

The Motion Estimation is an indispensable module in the design of video encoder. It employs Block Matching algorithm which involves searching a candidate block in the entire search window of the reference frame taking up to 80% of the total video encoding time. In order to increase the efficiency, several Block Matching Algorithms are employed to minimize the computational time involved in block matching. The chapter throws light on an efficient approach to be applied to the existing Block Matching Search techniques in HEVC which outperforms the various Block Matching algorithms. It involves two steps namely – Prediction and Refinement. The prediction step considers two parameters such as the temporal correlation and the direction to predict the MV of the candidate block. Several combinations of the search points are formulated in the refinement step of the algorithm to minimize the search time. The results depict that the Efficient Motion Estimation schemes provide a faster search minimizing the computational time upon comparison with the existing Motion Estimation algorithms.

Parallel Full Search Algorithm for Motion Estimation on Graphic Processing Unit

2019 ◽  
Vol 12 (4) ◽  
pp. 317-323
Author(s):  
Fatma Ezzahra Sayadi ◽  
Marwa Chouchene ◽  
Haithem Bahri ◽  
Randa Khemiri ◽  
Mohamed Atri
Keyword(s):  
Motion Estimation ◽  
Video Compression ◽  
High Performance ◽  
High Efficiency ◽  
Search Algorithm ◽  
Low Cost ◽  
Video Quality ◽  
Processing Unit ◽  
High Efficiency Video Coding ◽  
Nvidia Gpu

Background: Advances in video compression technology have been driven by everincreasing processing power available in software and hardware. Methods: The emerging High-Efficiency Video Coding (HEVC) standard aims to provide a doubling in coding efficiency with respect to the H.264/AVC high profile, delivering the same video quality at half the bit rate. Results: Thus, the results show high computational complexity. In both standards, the motion estimation block presents a significant challenge in clock latency since it consumes more than 40% of the total encoding time. For these reasons, we proposed an optimized implementation of this algorithm on a low-cost NVIDIA GPU developed with CUDA language. Conclusion: This optimized implementation can provide high-performance video encoder where the speed reaches about 85.

scholarly journals Motion Estimation-Assisted Denoising for an Efficient Combination with an HEVC Encoder

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 895 ◽  
Author(s):  
Seung-Yong Lee ◽  
Chae Rhee
Keyword(s):  
Computational Complexity ◽  
Motion Estimation ◽  
High Efficiency ◽  
Three Dimensional ◽  
Block Matching ◽  
High Efficiency Video Coding ◽  
Compression Efficiency ◽  
The Hierarchical Structure ◽  
Tightly Coupled ◽  
Low Performance

Noise, which is commonly generated in low-light environments or by low-performance cameras, is a major cause of the degradation of compression efficiency. In previous studies that attempted to combine a denoise algorithm and a video encoder, denoising was used independently of the code for pre-processing or post-processing. However, this process must be tightly coupled with encoding because noise affects the compression efficiency greatly. In addition, this represents a major opportunity to reduce the computational complexity, because the encoding process and a denoise algorithm have many similarities. In this paper, a simple, add-on denoising scheme is proposed through a combination of high-efficiency video coding (HEVC) and block matching three-dimensional collaborative filtering (BM3D) algorithms. It is known that BM3D has excellent denoise performance but that it is limited in its use due to its high computational complexity. This paper employs motion estimation in HEVC to replace the block matching of BM3D so that most of the time-consuming functions are shared. To overcome the challenging algorithmic differences, the hierarchical structure in HEVC is uniquely utilized. As a result, the computational complexity is drastically reduced while the competitive performance capabilities in terms of coding efficiency and denoising quality are maintained.

Sign in / Sign up

Export Citation Format

Share Document