论文部分内容阅读
对空间目标进行形态结构分析,对于航天器空间操作和空间攻防等空间任务具有重要意义。探索了一种空间目标结构分析方法。首先利用最小曲率准则和最短分割线准则,并结合目标骨架,构建了一种新的形状分解的方法;在此基础上,将小波矩特征引入到卫星部件形状分析中,并利用粗糙集约简算法选择有效的小波矩特征;最后利用支持向量机构造了多尺度形状识别器,结合目标先验信息实现对空间目标结构的分析。仿真实验结果表明了所提方法的有效性。
The analysis of the morphological structure of the space target is of great significance to space missions such as spacecraft space operations and space attack and defense. Explored a spatial target structure analysis method. Firstly, a new method of shape decomposition is constructed by using the minimum curvature criterion and the shortest dividing line criterion, combined with the target skeleton. On this basis, the wavelet moment features are introduced into the shape analysis of satellite components, and the rough set reduction algorithm Select the effective wavelet moment features. Finally, a multi-scale shape recognizer is constructed by using SVM, and the target structure of space is analyzed according to the priori information of the target. Simulation results show the effectiveness of the proposed method.