首页> 中文期刊> 《西北工业大学学报》 >基于Dice匹配的SWOMP压缩感知重构算法

基于Dice匹配的SWOMP压缩感知重构算法

         

摘要

传统的分段弱正交匹配追踪(SWOMP)重构算法在重构信号时,由于采用了内积匹配准则,观测矩阵中任意2个相似的原子都会影响残差信号的匹配过程,降低信号重构质量.利用Dice系数匹配度量准则,优化了支撑集的选择,降低了相似原子对匹配过程的影响.仿真结果证明:在相同的条件下,与传统的SWOMP算法相比,优化后的基于Dice系数的分段弱正交匹配追踪(Dice-SWOMP)算法具有更小的恢复残差以及更高的信号重构成功率.%When reconstructing the signal with the traditional SWOMP reconstruction algorithm , any two similar at-oms in the observation matrix will affect the matching process of the residual information and reduce the quality of signal reconstruction due to the use of inner product matching criterion .In this paper , the Dice coefficient matching metric is used to optimize the selection of the support set and reduce the impact of similar atom on the matching process.Finally, the simulation results show that the optimized Dice-SWOMP algorithm based on the Dice coeffi-cient has smaller recovery residuals and higher signal reconstruction success rate than the SWOMP algorithm under the same conditions .

著录项

相似文献

  • 中文文献
  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号