提出了基于支持向量机(Support Vector Machine,SVM)的遥感影像分类方法,结合空间特征等信息,对IKONOS高空间分辨率影像进行分类,实施对生态公益林的监测,并将此分类方法与传统分类方法进行比较分析。研究结果表明,基于SVM的遥感分类方法能够有效解决分类效果破碎、精度不高等问题,而且在学习速度、自适应能力、可表达性等方面具有优势。 This paper proposes a remote sensing image classification method based on Support Vector Machine (SVM), classifies IKONOS high spatial resolution image according to the spatial characteristics and other information, and implements the monitoring of ecological public welfare forest. And this classification method and tradition Classification methods for comparative analysis. The results show that SVM-based remote sensing classification method can effectively solve the problem of fragmentation and poor accuracy, and has advantages in learning speed, adaptability and expressibility.