A novel approach for radar network’s detection power analysis based on GPU

The detection power analysis of radar network is an essential but time-consuming problem in the domain of situation awareness. In this paper, we propose a novel GPU based method more efficient than existing solutions. The proposed approach is based on the field model, and the calculation of detection power is regarded as the construction and information handling process of the field model. Furthermore, it's a computation and visualization combined method. It directly produces the geotagged image, which is needed in the final display terminal. Finally, it fully utilizes the GPU hardware through various techniques, such as compressing solution space, optimizing memory usage, and instruction usage optimization. The result of the comparative experiment has shown that this novel GPU based algorithm is scalable to various conditions such as different cell resolution, detection possibility, and height. The optimized GPU version can reap the processing efficiency to about 93 times than the serial version.

• Publication year

  2020

• Venue

  International Conference on Advanced Cloud and Big Data

• Publication date

  2020-12-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/CBD51900.2020.00015
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Revisiting linpack algorithm on large-scale CPU-GPU heterogeneous systems

  2020cited by this paper
• Ignite-GPU: a GPU-enabled in-memory computing architecture on clusters

  2020cited by this paper
• GFlink: An In-Memory Computing Architecture on Heterogeneous CPU-GPU Clusters for Big Data

  2018cited by this paper
• Calculation of radar network detection power under terrain masking

  2017cited by this paper
• A GPU-accelerated adaptive kernel density estimation approach for efficient point pattern analysis on spatial big data

  2017cited by this paper
• Fast Contour-Tracing Algorithm Based on a Pixel-Following Method for Image Sensors

  2016cited by this paper
• Massively parallel spatial point pattern analysis: Ripley’s K function accelerated using graphics processing units

  2015cited by this paper
• A parallel GPU-based approach for reporting flock patterns

  2014cited by this paper
• Parallel algorithm for viewshed analysis on a modern GPU

  2011cited by this paper
• Graphics Processing Algorithm for Complex Areas in Power Simulation of Radar Network

  2008cited by this paper
• Approach to Regional Radar Netting Optimization Based on Genetic Algorithm

  2005cited by this paper
• Modeling of Radar Detection Probability Based on the Comparative Calculation

  2005cited by this paper
• A New Algorithm for Calculating the Coverage Area of Radar Net

  2003cited by this paper

• No citing papers are available for this paper.