论文部分内容阅读
为了提高海杂波中的小目标检测能力,提出了基于递归最小二乘线性预测的海面小目标检测方法。首先,建立线性预测模型;其次,利用递归最小二乘法动态调整模型的参数;最后,计算绝对预测误差的均值,通过阈值比较得到检测目标结果。采用加拿大IPIX雷达数据的实验结果表明,该方法的检测性能优于线性预测的检测目标方法和神经网络集成的检测目标方法的检测性能;同极化方式下,HH极性的检测效果优于VV极性的检测效果。该方法实时更新了预测模型参数,同步跟踪海杂波的变化,克服预测模型固定不变的局限,提高了目标检测的能力。
In order to improve the small target detection ability in sea clutter, a small target detection method based on recursive least squares linear prediction is proposed. Firstly, the linear prediction model is established. Secondly, the parameters of the model are dynamically adjusted by using the recursive least squares method. Finally, the average of the absolute prediction errors is calculated and the result of the detection target is obtained by comparing the thresholds. Experimental results using Canadian IPIX radar data show that the detection performance of this method is better than that of the linear prediction detection method and the neural network integrated detection target method. Under the same polarization mode, the detection effect of HH polarity is better than VV Polarity test results. The method updates the parameters of the prediction model in real time, tracks the changes of the sea clutter synchronously, overcomes the fixed limitations of the prediction model and improves the ability of target detection.