面对数量激增、包含信息日趋复杂的遥感影像，如何快速有效地自动分类已成为遥感领域亟待解决的问题。以TM影像为实例，探讨了Fuzzy ARTMAP神经网络在土地覆盖分类方面的应用。在总结Fuzzy ARTMAP网络警戒系数调整方法的基础上，提出了一种新的设置和调整警戒系数的方法。实验结果表明，这种新方法可以解决人为选择警戒系数效率低、难以取得合适数值的问题，并能提高网络的收敛速度和分类精度，结合本文所提算法的Fuzzy ARTMAP神经网络与最大似然法和传统Fuzzy ARTMAP网络相比较，训练时间缩短，分类精度有所提高。Fuzzy ARTMAP网络用于土地覆盖分类研究可以获得相对较好的分类结果。

The amount of remotely data images increases rapidly, and the information that the images contain becomes more and more complicated. How to classify remotely sensed images automatically and effectively is a problem needed to be solved. This paper explores the application of Fuzzy ARTMAP neural network in classification of land cover. The adjusting methods of vigilance parameter are summarized. An automatic adjusting algorithm is proposed. The simulation results show that the automatic adjustment algorithm can increase the efficiency of selecting the optimum parameter value. The convergence speed and classification accuracy can also be improved through the automatic adjusting algorithm. The Fuzzy ARTMAP neural network with the automatic adjusting algorithm has shorter training time and higher classification accuracy than maximum likelihood classifier and traditional Fuzzy ARTMAP. A relatively satisfied classification result can be achieved by using Fuzzy ARTMAP in land cover classification.