| 摘要: |
| 针对海杂波背景下的雷达弱目标检测问题以及孤立森林算法在处理高维数据时未充分利用雷达回波信号特征信息的问题,提出了一种基于改进多特征联合的孤立森林弱目标检测方法。该方法通过分析实测海杂波数据在时域、频域和时频域的特性构建了丰富的高维特征矩阵,在孤立森林算法中融合主成分分析算法进行数据降维,引入平均相关度构成双参数降维准则,以平衡主成分与原始特征之间的相关性。仿真结果表明,所提改进方法在不同海况以及极化方式下均能够有效提升海杂波背景下雷达弱目标检测的性能,且在虚警概率较低的情况下仍有较高的检测概率。 |
| 关键词: 雷达目标检测 孤立森林算法 主成分分析算法 多特征联合 海杂波 |
| DOI： |
| 分类号:TN957.51 |
| 基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| Sea Surface Small Target Detection Method Based on Improved Isolation Forest |
|
胡居荣, 邢延潇, 戴天石, 张伟杰
|
|
|
| Abstract: |
| To address the problem of radar small target detection under sea clutter conditions and the issue that the Isolation Forest algorithm does not fully utilize radar echo signal features when dealing with high-dimensional data, we propose a method for weak target detection based on an improved multi-feature joint Isolation Forest. This method constructs a rich high-dimensional feature matrix by analyzing the characteristics of actual sea clutter data in the time domain, frequency domain, and time-frequency domain. Principal Component Analysis is integrated into the Isolation Forest algorithm for data dimensionality reduction, introducing an average correlation-based dual-parameter criterion for dimensionality reduction to balance the correlation between principal components and the original features. Simulation results demonstrate that the proposed improved method effectively enhances radar weak target detection performance under sea clutter conditions across different sea states and polarization modes, while maintaining a high detection probability even at low false alarm rates. |
| Key words: radar target detection isolation forest principal component analysis multi-feature union sea clutter |