论文部分内容阅读
基于飞机目标的轮廓特点和成像特性,提出了一种基于可变参数化几何模型的合成孔径雷达(SAR)图像飞机目标特征提取方法。首先,利用飞机目标的先验知识构造一个描述飞机目标外形轮廓的参数化模型;然后,对于输入的实测飞机目标切片图像,构建目标函数来度量模型与实测图像中目标区域的拟合程度,通过遗传算法求解最优参数;最后,在最优参数模型的基础上计算目标的几何特征。基于仿真和实测数据的实验结果验证了该方法的有效性。
Based on the contour features and imaging characteristics of aircraft targets, a target feature extraction method of Synthetic Aperture Radar (SAR) images based on variable parameterized geometric model is proposed. Firstly, a parametric model describing the outline of the aircraft target is constructed by using the priori knowledge of the aircraft target. Then, for the input target slice image of the aircraft, an objective function is constructed to measure the fitting degree between the model and the target area in the measured image. Genetic algorithm to solve the optimal parameters; Finally, the geometric parameters of the target are calculated based on the optimal parameter model. Experimental results based on simulation and measured data verify the effectiveness of the proposed method.