Page 75 - 《武汉大学学报（信息科学版）》2025年第9期

第 50 卷第 9 期 刘逸娴等：融合颜色特征的随机森林特征优选的黄河三角洲植被信息分类 1803

conditions and the spread of the invasive species Spartina alterniflora, vegetation detection and classifica⁃
tion are particularly important. Methods: This paper takes part of the YRD wetland as the study area, and
chooses high-resolution aerial images as data source. Four feature variables are generated, including spec⁃
tral features, color features, index features and texture features. Six different classification schemes are con⁃
structed. Scheme 1 with only spectral features is regarded as the control group. Index features, texture fea⁃
tures and color features are integrated into scheme 2, scheme 3 and scheme 4, respectively. Scheme 5 con⁃
tains all features, and scheme 6 constructs a multi-feature optimization feature set. Random forest method
is used to classify vegetation for each extraction scheme and the corresponding accuracies are verified, aiming
to explore the influences and reasons of different feature variables on the classification. The best preferred
features are selected to improve the effect of vegetation classification. Results: Based on the visible and
near-infrared spectra, just adding different features to the experiment has different effects on the accuracies
of vegetation classification. Scheme 1, scheme 2 and scheme 3 have unsatisfactory extraction effect on
Phragmites australis and Suaeda salsa. Scheme 4, scheme 5 and scheme 6 with the addition of color fea⁃
tures can better distinguish between the two, probably because Suaeda salsa shows dark red on the image,
which is quite different from other vegetation. Scheme 4 divides non-vegetated tidal flat areas and water
body edges into Phragmites australis, which are similar in color, and adds color features results in some
misclassifications. Scheme 5 and scheme 6 are well classified, but due to the mixed nature of vegetation, all
schemes have varying degrees of misclassification of Tamarix chinensis, Phragmites australis and Spartina
alterniflora. Index features have positive effects on Suaeda salsa extraction, texture features reduce the ac⁃
curacy of vegetation classification, and the integration of color features is the key to improve overall accura⁃
cy of classification. Based on multi-feature optimization of random forest, the extraction effect is the best,
with overall accuracy of 88% and Kappa coefficient of 0.85. Conclusions: The main advantages of this
study are the acquisition of new data sources, the introduction of multiple feature variables, and the experi⁃
mental evaluation and classification accuracy analysis of different feature variables. The importance of color
features is verified and multi-feature optimization of random forest by integrating color features is a feasible
method to classify vegetation information in the YRD. The proposed method can effectively distinguish vegeta⁃
tion from non-vegetation and extract each vegetation type at the same time. This study provides an effec⁃
tive technical route in feature selection and methodology for vegetation information extraction in the YRD.
Key words： the Yellow River Delta； aerial image； random forest； vegetation information extraction； color
features

湿地是自然界中最富生物多样性的生态系 滨海湿地生态系统恢复和保护的重要基础。
统，在保护生态环境、调节气候、控制土壤侵蚀和 随着对地观测系统的快速演进与分类算法
发展经济社会中发挥着不可替代的重要作用 ［1-2］ 。 的 不 断 发 展 ，因 时 间 分 辨 率 与 空 间 分 辨 率 的 提
黄河三角洲拥有着中国最完整、最广泛、最年轻 高，遥感成为重要的农林业监测手段。目前对于
的河口湿地生态系统 。植被作为生态系统功能 黄河三角洲湿地植被的分类与提取多涉及 Land⁃
［3］
的主体，在生物多样性的恢复与保护中发挥着重 sat 数 据 ［5］ 。 文 献［6］选 取 3 个 时 相 的 Landsat 数
要的作用。在黄河三角洲湿地中，碱蓬、互花米 据，分别对芦苇、碱蓬与互花米草进行提取；文献
［4］
草、芦苇和柽柳等群落是最典型的植被群落 ，各 ［7］基于多年 Landsat 数据，以芦苇、互花米草、碱
类植被通过竞争、共生等相互作用，形成了复杂 蓬与柽柳典型 4 种植被为对象，采用支持向量机
的生态关系。它们在长期协同进化过程中不断 进行分类。因 Sentinel-2 卫星的重访周期短且空
演变，反映着湿地生态系统的发展方向。随着气 间分辨率高，利用此卫星影像的学者逐渐增多。
候的变化、人口与经济的增长、工业和港口的建 文 献［8］利 用 多 时 相 Sentinel-2 影 像 对 黄 河 三 角
设以及水体的污染，湿地面临着巨大压力。在此 洲湿地信息进行提取；文献［9］基于 Sentinel-2 数
背景下，对植被信息进行精细分类、准确获取黄 据对滨海湿地植被进行分类研究；文献［10］获取
河三角洲湿地典型盐沼植被的分布情况，是进行 12 个月份的 Sentinel-2 数据提取 264 个特征，采用