Optimized particle swarm optimization for faster and accurate video compression

The motion of objects in a video from one frame to another must be estimated quickly to speed up the video compression process. However, this should not deteriorate the visual appearance of the contents beyond the appropriate scope. This paper proposes improvisation of the fundamental Particle Swarm...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Multimedia tools and applications Ročník 81; číslo 16; s. 23289 - 23310
Hlavní autori: Saikia, Monjul, Choudhury, Hussain Ahmed, Sinha, Nidul
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.07.2022
Springer Nature B.V
Predmet:
Algorithms
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Diamonds
Elementary particles
Image reconstruction
Matching
Motion simulation
Multimedia Information Systems
Object motion
Optimization
Particle swarm optimization
Process parameters
Special Purpose and Application-Based Systems
Video compression
MAD
Cost function
Motion estimation
Block matching algorithm
Particle swarm optimization
ISSN:1380-7501, 1573-7721
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The motion of objects in a video from one frame to another must be estimated quickly to speed up the video compression process. However, this should not deteriorate the visual appearance of the contents beyond the appropriate scope. This paper proposes improvisation of the fundamental Particle Swarm Optimization (PSO), known as Optimized PSO, to balance video compression quality and speed. The inertia portion of the particle velocity is modified dynamically to address the quality needed and broadly defines the movement to the global best place. To make the process quicker, additional stopping parameters, including predefined block distortion measurement, i.e., thresholds and the early identification of static macroblocks, are used to eradicate the movement estimation process for non-moving macroblocks. A small diamond search pattern is also implemented to investigate the impact of search patterns on optimizing the particulate swarm on the motion estimation process. The detailed simulations performed on different videos have proved that the proposed Optimized PSO versions for the block matching algorithm surpass several current modular block matching algorithms. It also produces even better estimation precision and speed than the possible particle swarm optimization-based motion estimation. The proposed versions of PSO-BMA referred to as Optimized PSOs have gained a speed up to 90-95% than that of FS with an acceptable compromise between the qualities of the reconstructed image.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-022-12522-x