By synergistically using the object-based image analysis (OBIA) and the classification and regression tree (CART) methods, the distribution information, the indexes (including diameter at breast, tree height, and crown closure), and the aboveground carbon storage (AGC) of moso bamboo forest in Shanchuan Town, Anji County, Zhejiang Province were investigated. The results showed that the moso bamboo forest could be accurately delineated by integrating the multi-scale ima ge segmentation in OBIA technique and CART, which connected the image objects at various scales, with a pretty good producer's accuracy of 89.1%. The investigation of indexes estimated by regression tree model that was constructed based on the features extracted from the image objects reached normal or better accuracy, in which the crown closure model archived the best estimating accuracy of 67.9%. The estimating accuracy of diameter at breast and tree height was relatively low, which was consistent with conclusion that estimating diameter at breast and tree height using optical remote sensing could not achieve satisfactory results. Estimation of AGC reached relatively high accuracy, and accuracy of the region of high value achieved above 80%.
综合面向对象和CART决策树方法，对浙江省安吉县山川乡毛竹林分布信息及胸径、树高、郁闭度等调查因子和地上部分碳储量进行遥感定量估算.结果表明： 综合基于多尺度分割的对象特征及决策树，能够充分利用不同尺度层次信息关联的优势，实现毛竹林专题信息高精度提取，其用户精度达到89.1%；基于对象特征构建的毛竹林调查因子回归树估算模型，其估算结果均能达到正常或较好水平，其中，郁闭度回归树模型的精度最高为67.9%，估算效果较好；而平均胸径和树高估算的总精度相对较低，这与采用光学遥感数据进行森林树高、胸径估算达不到理想结果的结论一致；毛竹林地上部分碳储量回归树模型的估算结果较好，高值区域估算精度达到80%以上.
Keywords: SPOT5; aboveground carbon storage; decision tree; forest inventory parameter; object-based method.