文献类型：会议论文

英文题名：HYPERSPECTRAL IMAGE CLASSIFICATION OF TREE SPECIES WITH LOW-DEPTH FEATURES

作者：Guo, Zhengqi[1] Zhang, Mengmeng[1] Jia, Wen[2] Li, Wei[1]

第一作者：Guo, Zhengqi

通信作者：Zhang, MM[1]

机构：[1]Beijing Inst Technol, Sch Informat & Elect, Beijing, Peoples R China;[2]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing, Peoples R China

会议论文集：IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

会议日期：JUL 16-21, 2023

会议地点：Pasadena, CA

语种：英文

外文关键词：Tree species; Conv2DLSTM; low-level features; high-level features

年份：2023

摘要：Classification of tree species is of great significance to forest surveys. Recently, considering the low differences of spectral information among tree species, enhancing the dependence between long-distance bands has become a research hotspot. A tree species classification method based on a convolutional (2-dimension) long short-term memory (Conv2DLSTM) network and transformer is proposed. First, the main features of HSI are retained by principal component analysis (PCA). Then, the Conv2DLSTM network obtains the global correlation information between long-distance band pixels, and the 3-dimensional convolutional neural network (3DCNN) updates the local spatial-spectral information. Finally, low-level features are converted into semantic tags to guide the modeling of high-level semantic features. The experimental results on the forest dataset demonstrate that the proposed method is superior to other competitive work.