影响ETM影像土地利用/覆盖分类精度因素的研究

Research on the Factors Affecting the Classification Accuracy of ETM Remote Sensing Image Land Cover/Use

训练样本量、辅助数据和分类法是影响土地利用/覆盖分类精度的3个主要因素,通过找到这3个因素的最佳组合方式以提高分类精度,分别在25%、50%、75%、100%样本量下,加入NDVI、DEM和纹理均值特征作为辅助数据,比较了分类回归树、支持向量机、最大似然法3种分类法的效果,探讨了训练样本、辅助数据以及分类技术对土地利用/覆盖分类精度的影响。结果表明:支持向量机总体分类精度较高,在相同样本量和没有有效辅助数据的情况下,SVM可以获得最佳的分类结果,总体分类精度在85%以上;在进行分类时,加入NDVI和纹理均值特征使分类回归树分类精度提高了2.82%,说明该方法对有效辅助数据的加入较为敏感;在获取的训练样本集有限而可获取有效的辅助数据时,应优先考虑利用分类回归树进行土地利用/覆盖分类。

Training sample size,auxiliary data and classification algorithm are the three main factors influen cing on the land use and cover classification accuracy,through finding out the best combination of the three factors to improve the classification accuracy. Multispectral imagery and DEM from ETM satellite are applied to perform experiments under four sample sizes （100% ,75% ,50 %,25 %）,along with calculated NDVI layer and mean texture measure. By contrasting the classification accuracy produced using three different classification algorithms： Classification and Regression Tree（CART）, Support Vector Machine（SVM） and Maximum Likelihood Classification（MLC）, to discuss the influence of training sample, auxiliary data and different classification algorithms to the classification accuracy. The results indicate that the SVM can obtain the best classification result when there is no effective auxiliary data, and the total accuracy can reach to 85% ,when CART is used to classification ,as the additional NDVI and texture feature,the accuracy increased 2.82 % ,it is sensitive to auxiliary data , which can obviously improve the classification accuracy. While in the condition of limited training sample obtain the effective auxiliary data, the CART can achieve the highest classification accuracy.