一种基于正向云的自动目标识别效果评估方法

近年来随着自动目标识别(ATR)技术的快速发展,对于目标识别系统性能科学评估方法的研究越来越迫切.在总结已有方法的基础之上,针对基于模糊综合评判的评估方法中指标权重的难以合理量化,从而导致评估结果对权重数值敏感而不稳健这一瓶颈问题,引入了云理论中的正向云模型,实现了权重由定性到定量的不确定性转换.通过采用外场实测数据的仿真,验证了改进后的方法比传统的模糊综合评判方法具有更好的稳健性.

Performance Evaluation Method for Automatic Target Recognition System Based on Forward Cloud

In the recent years,as the development of automatic target recognition (ATR) technology,the performance evaluation for it becomes more and more important.On the base of the summarization for the existing performance evaluation methods,the cloud theory was introduce into the fuzzy comprehensive evaluation in order to resolve the problem that the evaluation results are impressible to the values of the weights.Then the availability of the method supposed was improved via the real measurements.