Scholarlink

This paper introduces an innovative approach for handling radar data that combines Long Short-Term Memory (LSTM) networks with Joint Probabilistic Data Association (JPDA). To tackle the challenge of clutter in radar signal processing we utilized the sequential data analysis capabilities of LSTM to minimize clutter and enhance measurements quality effectively. Subsequently, JPDA is employed for precise target tracking data association. This collaborative approach results in enhancements of tracking accuracy, completeness, and ambiguity which underscores the approach’s ability to improve radar multi-target tracking performance. This paper thoroughly assesses the proposed approach, backed up by experimental data and comparative analysis.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advanced Radar Target Tracking: Synergizing Deep Learning LSTM Clutter Filtering with Joint Probabilistic Data Association

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Esra Alhadhrami,
  • Clément Pira,
  • Rami Kassab,
  • Amal El Fallah Segrouchni,
  • Frederic Barbaresco,
  • Ahmed Y. Alhammadi,
  • Chan Yeob Yeun,
  • Deepak Puthal

摘要

This paper introduces an innovative approach for handling radar data that combines Long Short-Term Memory (LSTM) networks with Joint Probabilistic Data Association (JPDA). To tackle the challenge of clutter in radar signal processing we utilized the sequential data analysis capabilities of LSTM to minimize clutter and enhance measurements quality effectively. Subsequently, JPDA is employed for precise target tracking data association. This collaborative approach results in enhancements of tracking accuracy, completeness, and ambiguity which underscores the approach’s ability to improve radar multi-target tracking performance. This paper thoroughly assesses the proposed approach, backed up by experimental data and comparative analysis.