DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images
Multi-source data remote sensing provides innovative technical support for tree species recognition. Tree species recognition is relatively poor despite noteworthy advancements in image fusion methods because the features from multi-source data for each pixel in the same region cannot be deeply expl...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/1/33 |
| _version_ | 1797494062215856128 |
|---|---|
| author | Xueliang Wang Honge Ren |
| author_facet | Xueliang Wang Honge Ren |
| author_sort | Xueliang Wang |
| collection | DOAJ |
| description | Multi-source data remote sensing provides innovative technical support for tree species recognition. Tree species recognition is relatively poor despite noteworthy advancements in image fusion methods because the features from multi-source data for each pixel in the same region cannot be deeply exploited. In the present paper, a novel deep learning approach for hyperspectral imagery is proposed to improve accuracy for the classification of tree species. The proposed method, named the double branch multi-source fusion (DBMF) method, could more deeply determine the relationship between multi-source data and provide more effective information. The DBMF method does this by fusing spectral features extracted from a hyperspectral image (HSI) captured by the HJ-1A satellite and spatial features extracted from a multispectral image (MSI) captured by the Sentinel-2 satellite. The network has two branches in the spatial branch to avoid the risk of information loss, of which, sandglass blocks are embedded into a convolutional neural network (CNN) to extract the corresponding spatial neighborhood features from the MSI. Simultaneously, to make the useful spectral feature transfer more effective in the spectral branch, we employed bidirectional long short-term memory (Bi-LSTM) with a triple attention mechanism to extract the spectral features of each pixel in the HSI with low resolution. The feature information is fused to classify the tree species after the addition of a fusion activation function, which could allow the network to obtain more interactive information. Finally, the fusion strategy allows for the prediction of the full classification map of three study areas. Experimental results on a multi-source dataset show that DBMF has a significant advantage over other state-of-the-art frameworks. |
| first_indexed | 2024-03-10T01:28:55Z |
| format | Article |
| id | doaj.art-9fc8c36993e946e8b62a6b51b6fd8c9f |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T01:28:55Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-9fc8c36993e946e8b62a6b51b6fd8c9f2023-11-23T13:46:42ZengMDPI AGForests1999-49072021-12-011313310.3390/f13010033DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source ImagesXueliang Wang0Honge Ren1College of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, ChinaMulti-source data remote sensing provides innovative technical support for tree species recognition. Tree species recognition is relatively poor despite noteworthy advancements in image fusion methods because the features from multi-source data for each pixel in the same region cannot be deeply exploited. In the present paper, a novel deep learning approach for hyperspectral imagery is proposed to improve accuracy for the classification of tree species. The proposed method, named the double branch multi-source fusion (DBMF) method, could more deeply determine the relationship between multi-source data and provide more effective information. The DBMF method does this by fusing spectral features extracted from a hyperspectral image (HSI) captured by the HJ-1A satellite and spatial features extracted from a multispectral image (MSI) captured by the Sentinel-2 satellite. The network has two branches in the spatial branch to avoid the risk of information loss, of which, sandglass blocks are embedded into a convolutional neural network (CNN) to extract the corresponding spatial neighborhood features from the MSI. Simultaneously, to make the useful spectral feature transfer more effective in the spectral branch, we employed bidirectional long short-term memory (Bi-LSTM) with a triple attention mechanism to extract the spectral features of each pixel in the HSI with low resolution. The feature information is fused to classify the tree species after the addition of a fusion activation function, which could allow the network to obtain more interactive information. Finally, the fusion strategy allows for the prediction of the full classification map of three study areas. Experimental results on a multi-source dataset show that DBMF has a significant advantage over other state-of-the-art frameworks.https://www.mdpi.com/1999-4907/13/1/33tree species classificationdeep learning fusion methodmulti-source images classification |
| spellingShingle | Xueliang Wang Honge Ren DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images Forests tree species classification deep learning fusion method multi-source images classification |
| title | DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images |
| title_full | DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images |
| title_fullStr | DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images |
| title_full_unstemmed | DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images |
| title_short | DBMF: A Novel Method for Tree Species Fusion Classification Based on Multi-Source Images |
| title_sort | dbmf a novel method for tree species fusion classification based on multi source images |
| topic | tree species classification deep learning fusion method multi-source images classification |
| url | https://www.mdpi.com/1999-4907/13/1/33 |
| work_keys_str_mv | AT xueliangwang dbmfanovelmethodfortreespeciesfusionclassificationbasedonmultisourceimages AT hongeren dbmfanovelmethodfortreespeciesfusionclassificationbasedonmultisourceimages |