空间目标识别技术与威胁评估算法综述

简要介绍了现有的空间目标探测技术地基／天基的雷达、光电等，指出目标识别的难点在于高效、准确、实时的数据融合。针对空间环境的复杂性，指出空间目标威胁评估的关键在于属性权值向量的确定，详细分析了现有的威胁评估算法：层次分析、专家系统、灰色聚类、Bayesian网络、云模型、神经网络、支持向量机等；通过对比研究，着重探讨其优势与不足，最后给出此类算法在空间环境下的普适性。

A Survey of Space Objects Identification and Threat Assessment Algorithms

This paper reviews the technologies of the space object detection, including the ground/space-based radars, optical telescopes and electronics, etc. It is revealed that the main difficulty of identification is the efficient, accurate and real time data fusion. Considering the complexity of space environment, the key to threat assessment of space objects is the determination of a proper weight vector. A dedicated survey of the existing algorithms is performed ： analytic hierarchy process, expert system, grey clustering, Bayesian network, cloud model, artificial neural network, support vector machine, etc. The strengths and drawbacks are discussed and evaluated. Finally the generality of the algorithms is presented.