Dual-Concentrated Network With Morphological Features for Tree Species Classification Using Hyperspectral Image

Abstract

At present, deep learning is a hot topic in the field of the classification of hyperspectral image (HSI), and it has aroused wide attention. However, in fine-grained classification tasks, such as tree species classification, the uncertain spectrum remains the major factor restraining the classification performance. In order to solve the dilemma of forest tree species classification, a Dualconcentrated Network with Morphological Features (DNMF) is proposed. Firstly, mathematical morphology is used to extract the morphological features of HSI. Then, coarse-grained information is extracted from the original hyperspectral data, and finegrained information is extracted from morphological features. After that, both morphological representations and spectral inputs are fed into DNMF, and the overall evaluation index and visual image are obtained. The advantage of DNMF is that it decouples the spatial and spectral information, and a multisource information fusion process is then simulated. Accordingly, DNMF obtains high tree species classification accuracy. In order to verify the superiority of DNMF, we choose Gaofeng Stateowned Forest Farm (GSFF) in Guangxi Province and the Belgium dataset which was collected near the western part of Belgium as the research area. Related experiments demonstrate that the DNMF model achieves clearly better classification performance over other competitive baselines.

The prediction model of nitrogen nutrition in cotton canopy leaves based on hyperspectral visible‐near infrared band feature fusion

“…(4) Improve model stability: Fused features can reduce the dependence of the model on a single feature, improve the stability and robustness of the model, and reduce the risk of model over‐fitting. (5) Improve the interpretability of the model: fused features can combine different types of feature information, improve the interpretability of the model, and better understand the prediction process and results of the model [ 33–35 ] …”

“…[32] The advantages of building prediction model by fusing features are Improve the interpretability of the model: fused features can combine different types of feature information, improve the interpretability of the model, and better understand the prediction process and results of the model. [33][34][35] The information fusion type used in this paper was feature level…”

ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers

“…To reduce computing expenses in the MDCNN, high-dimensional input data are converted into low-dimensional data using the PCA algorithm. Guo et al [45] propose a dual-concentrated network with morphological features (DNMFs) to address the challenge of forest tree species classification. The method uses mathematical morphology to extract morphological features from HSI and extracts both coarse-grained and fine-grained information from the original HSI data and morphological features, respectively.…”

Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model

“…The traditional analysis method has low recognition accuracy for high-dimensional spectral data, and the analysis process is cumbersome, which makes it difficult to meet the actual needs. In recent years, scholars have developed and optimized the convolutional neural network model for the data characteristics and ground object characteristics of remote sensing data sets [ 15 , 16 ]. However, these deep network models have limitations in processing hyperspectral data of degraded grassland vegetation and cannot show the same performance.…”