论文部分内容阅读
混合像元的存在是影响识别分类精度的主要因素之一。把灰色系统理论与神经网络理论结合起来 ,提出了一种新的分解模型 ,对由 TM影像退化生成的模拟数据进行分解的结果表明 ,使用该模型在分解混合像元时能得到很高的精度。
The existence of mixed pixels is one of the main factors that affect the classification accuracy. Combining the gray system theory with the neural network theory, a new decomposition model is proposed. The decomposition of the simulation data generated by the TM image degradation shows that the model can be used to decompose mixed pixels with high accuracy .