Object-Oriented Multi-feature Ensemble Classification of Mangrove Species Using UAV Imagery

扫码查看

原文链接

NETL

外文摘要：Mangrove species classification is particularly important for coastal wetland protection and global warming mitigation。 However， it is challenging to identify species-level differences in practical applications。 In the paper， we propose an object-oriented multi-feature ensemble classifier for the fine classification of mangrove species。 First， mangrove images are segmented into objects by the multi-resolution segmentation method。 Second， multiple features of each object are extracted by feature calculation methods (Gray Level Co-occurrence Matrix， Standard Deviation， Mean， etc。)， and appropriate features are selected for species classification by weight estimation。 Finally， the selected features are fed to an ensemble classifier to generate the final mangrove species classification results。 Experiments performed on in-situ unmanned aerial vehicle (UAV) images collected in Yingzai， Guangdong Province demonstrate that the proposed multi-feature ensemble classifier achieves superior classification results to its single classifier counterparts。

外文关键词：

MangroveObject-Oriented classificationMangrove species classificationUnmanned aerial vehicle (UAV)Light detection and ranging (LiDAR)

作者：

Yujie Liu、Yiming Chen、Zhi He、Kai Liu

展开 >

作者单位：

School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510275, China

School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510275, China, the Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Guangzhou 510275, China

会议名称：

International Conference on Geographic Information and Remote Sensing Technology

会议地点：

Kunming(CN)

会议母体文献：

International Conference on Geographic Information and Remote Sensing Technology

页码：

125522Z.1-125522Z.7

出版时间：

2022

DOI：

10.1117/12.2667351