基于Rough集的信息融合目标识别方法

Approach of target recognition by data fusion based on Rough sets

研究了Rough集理论在基于不同谱段光学信息融合的目标识别系统中的应用技术,在介绍了目标知识表示方法的基础上,提出了用C均值算法实现连续信息离散化的方法,并通过决策表属性的约简来生成决策表,以实现对目标的识别。针对可见光、中/长波红外等三种不同谱段下的三种不同目标图像进行了实验,实验结果表明,该方法具有对先验知识获取的易实现性和对目标识别的有效性。

An application of Rough sets theory in target recognition system is researched based on data fusion of the multi-spectrum images. The method of expressing the information of the target is introduced, and the idea of dispersing the continued data by using the C-means method is presented. By reducing the decision-making table, targets recognition are realized. It is used to recognize the target from the light, middle and long wavelength infrared images in this paper. Experimental results prove that this approach is good for the target recognition and can easily get the pre-knowledge.