| 摘要: |
| 目前,海面小目标已成为海洋雷达探测的重点和难点对象。现有的检测方法局限于雷达回波幅度或频谱的单方面信息的使用,难以有效探测小目标。为此,本文提出一种基于双通道图特征联合的海面小目标检测方法。首先,从雷达复回波序列中提取时域相位序列和频域幅度序列,生成时域-频域双通道。在每个通道,分别生成连通图,为检测提供丰富的相关性。其次,在时域通道,通过分析图拉普拉斯矩阵特征值的差异性,选取最大和次大特征值的融合值作为第一个特征,衡量图的连通密度。在频域通道,通过提取度矩阵的对角线非零元素,计算其熵值作为第二特征,衡量图顶点分布的分散度。然后,将两个特征作为检测统计量,并判断是否落在具有目标引导的凸包算法决定的判决区域内,获得检测结果。最后,使用实测数据的实验结果表明,所提出的检测器在复杂探测环境下能够获得稳健且高效的检测性能。 |
| 关键词: 海杂波 目标检测 双通道 连通图 特征联合 |
| DOI： |
| 分类号:TN957 |
| 基金项目:国家自然科学基金项目（622011184），江苏省“双创团队”（JSSCTD202308） |
|
| Sea-surface Small Target Detection Using Joint Graph Features in Dual Channels |
|
|
|
|
| Abstract: |
| Currently, sea-surface small targets have become a key and challenging focus in maritime radar detection. The existing detection methods are limited to the use of unilateral information such as radar echo amplitude or spectrum, making it difficult to effectively detect small targets. Thus, a sea-surface small target detection method using dual-channel joint graph features (DC-JGF) is proposed in this paper. First, the time-domain phase and frequency-domain amplitude sequences are extracted from radar complex return to form a dual-channel of time and frequency domains. In each channel, graphs are generated to provide rich correlation information. Second, in the time domain, the largest and second-largest eigenvalues of graph Laplacian matrix are fused to evaluate graph density as the first feature. In the frequency domain channel, by extracting non-zero elements from the diagonal of the degree matrix, the entropy value is calculated as the second feature to measure the dispersion of the vertex distribution in the graph. Third, the two features are used as detection statistics, and it is determined whether they fall within the decision region given by the convex hull algorithm with target guidance. Finally, experimental results using measured data demonstrate that the proposed detector can achieve robust and efficient detection performance in complex detection environments. |
| Key words: sea clutter target detection dual channels connected graph feature fusion |