Three-Dimensional Microwave Imaging Problems Solved Through an Efficient Multiscaling Particle Swarm Optimization
Three-Dimensional Microwave Imaging Problems Solved Through an Efficient Multiscaling Particle Swarm Optimization
复制标题
DOI：
10.1109/tgrs.2008.2005529
复制
发表时间：
2009-05-01
影响因子：
8.2
通讯作者：
Massa, Andrea
中科院分区：
文献类型：
--
作者：
Donelli, Massimo;Franceschini, Davide;Massa, Andrea
提出了一种基于多分辨率粒子群优化器的增强型多步骤策略，用于 3D 微波成像。这种集成的目的是提高该方法的收敛能力，并通过对自适应确定的粒子速度的约束控制来减少搜索空间的维度和优化策略的计算负担。这有利于在大规模 3-D 逆散射问题的框架中利用粒子群的全局搜索能力。通过考虑与单个和多个 3D 目标相关的数值测试来评估所提出的技术。还讨论了实验测试的结果。
An enhanced multistep strategy based on a multiresolution particle swarm optimizer is proposed for 3-D microwave imaging. The aim of such an integration is to improve the convergence capabilities of the approach and to reduce the dimension of the search space and the computational burden of the optimization strategy, thanks to a constrained control of the particle velocities adaptively determined. This favors the exploitation of the global search capabilities of the particle swarms also in the framework of large-scale 3-D inverse scattering problems. The proposed technique is assessed by considering numerical tests concerned with single and multiple 3-D targets. The results of an experimental testing are also discussed.