Parallelism and Scalability in an Image Processing Application

Rasmussen, Morten Sleth; Stuart, Matthias Bo; Karlsson, Sven

doi:10.1007/s10766-009-0098-5

Cited by 8 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ese difficulties are faced by most image processing applications, which inherit the problem of load balancing because of limited parallelism [9]. erefore, effective parallel processing methods for image processing applications are being researched.…”

Section: Parallel Image Processingmentioning

confidence: 99%

See 1 more Smart Citation

Effective Parallelization Method for Object Recognition in 2D Sonar Images Based on Task Partitioning

Lee

Kim

et al. 2019

Scientific Programming

View full text Add to dashboard Cite

Techniques for analyzing and avoiding hazardous objects and situations on the seabed are being developed to ensure the safety of ships and submersibles from various hazards. Improvements in accuracy and real-time response are critical for underwater object recognition, which rely on underwater sonar detection to remove noises and analyze the data. Therefore, parallel processing is being introduced for real-time processing of two-dimensional (2D) underwater sonar detector images for seabed monitoring. However, this requires optimized parallel processing between the modules for image processing and the data processing of a vast amount of data. This study proposes an effective parallel processing method, called Task Partitioning, based on central and graphical processing units for monitoring and identifying underwater objects in real time based on 2D-imaging sonar. The practicality of the proposed method is evaluated experimentally by comparing it to the sequential processing method. The experimental results show that the Task Partitioning method significantly improves the processing time for sonar images because it reduces the average execution time to 1% and 5% of the sequential processing method and general parallelization, respectively.

show abstract

Section: Parallel Image Processingmentioning

confidence: 99%

“…us, the target processor must be selected after understanding the characteristics of the algorithm, prior to the implementation. Furthermore, the algorithm must be designed per the characteristics of each processor [9][10][11].…”

Section: Parallel Image Processingmentioning

confidence: 99%

Effective Parallelization Method for Object Recognition in 2D Sonar Images Based on Task Partitioning

Lee

Kim

et al. 2019

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Some load balancing strategies work well for exhaustive searching [39], while others are geared towards handling the area of image processing [40]. Other specific strategies are proposed for Molecular Dynamics (MD) problems [22,41].…”

Section: Dag-dlbr Dynamic Load Balancing Algorithmmentioning

confidence: 99%

A Dynamic Load Balancing Framework for Real-time Applications in Message Passing Systems

Kabbany

Wanas²,

Hegazi

et al. 2010

Int J Parallel Prog

View full text Add to dashboard Cite

Load balancing algorithms are designed essentially to equally distribute the load on processors and maximize their utilities while minimizing the total task execution time. In order to achieve these goals, the load-balancing mechanism should be "fair" in distributing the load across the different processors. This implies that the difference between the heaviest-loaded and the lightest-loaded processors should be minimized. Therefore, the load information on each processor must be updated such that the load-balancing mechanism can be more effective. In this work, we present an application independent dynamic algorithm for scheduling tasks and loadbalancing in message passing systems. We propose a DAG-based Dynamic Load Balancing algorithm for Real time applications (DAG-DLBR) that is designed to work dynamically to cope with possible changes in the load that might occur during runtime. This algorithm addresses the challenge of devising a load balancing scheme which judicially deals with the hybrid execution of existing real-time application (represented by a Direct Acyclic Graph (DAG)) together with newly arriving jobs. The main objective of this algorithm is to reduce response times of the newly arriving jobs while maintaining the time constrains of the existing DAG. To evaluate the performance of the DAG-DLBR algorithm, a comparison with the performance of two common dynamic load balancing algorithms is presented. This comparison is performed by evaluating, experimentally, the execution time of different load balancing algorithms on a homogenous real parallel machine. In addition, the values of load imbalance, the execution time, and the communication overhead time are evaluated analytically using different benchmarks as test-bed workloads. These workloads cover a wide range of dynamic applications with different task types. Experimental results illustrate the improved performance of the DAG-DLBR algorithm compared to both distributed and hierarchal based algorithms by at least 12 and 19%, respectively. This improvement is true for all workloads, even with highly dependent workload. The DAG-DLBR algorithm achieves lower computation time than its corresponding values of both the distributed and the hierarchical-based algorithms for 4, 8, 12 and 16 processors.

show abstract

“…OpenMP is an application programming interface that supports multiplatform shared-memory parallel programming in C, C++, and Fortran [ 16 ]. With the advent of commodity inexpensive multicore processors and corresponding OpenMP-capable compliers, OpenMP has gained the popularity [ 17 – 19 ].…”

Section: Introductionmentioning

confidence: 99%

Parallelized Seeded Region Growing Using CUDA

Park

Lee

et al. 2014

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

This paper presents a novel method for parallelizing the seeded region growing (SRG) algorithm using Compute Unified Device Architecture (CUDA) technology, with intention to overcome the theoretical weakness of SRG algorithm of its computation time being directly proportional to the size of a segmented region. The segmentation performance of the proposed CUDA-based SRG is compared with SRG implementations on single-core CPUs, quad-core CPUs, and shader language programming, using synthetic datasets and 20 body CT scans. Based on the experimental results, the CUDA-based SRG outperforms the other three implementations, advocating that it can substantially assist the segmentation during massive CT screening tests.

show abstract

Parallelism and Scalability in an Image Processing Application

Cited by 8 publications

References 14 publications

Effective Parallelization Method for Object Recognition in 2D Sonar Images Based on Task Partitioning

Effective Parallelization Method for Object Recognition in 2D Sonar Images Based on Task Partitioning

A Dynamic Load Balancing Framework for Real-time Applications in Message Passing Systems

Parallelized Seeded Region Growing Using CUDA

Contact Info

Product

Resources

About