An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots
The common method for evaluating the extent of grape disease is to classify the disease spots according to the area. The prerequisite for this operation is to accurately segment the disease spots. This paper presents an improved DeepLab v3+ deep learning network for the segmentation of grapevine lea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.795410/full |
| _version_ | 1818285014731718656 |
|---|---|
| author | Hongbo Yuan Jiajun Zhu Qifan Wang Man Cheng Zhenjiang Cai |
| author_facet | Hongbo Yuan Jiajun Zhu Qifan Wang Man Cheng Zhenjiang Cai |
| author_sort | Hongbo Yuan |
| collection | DOAJ |
| description | The common method for evaluating the extent of grape disease is to classify the disease spots according to the area. The prerequisite for this operation is to accurately segment the disease spots. This paper presents an improved DeepLab v3+ deep learning network for the segmentation of grapevine leaf black rot spots. The ResNet101 network is used as the backbone network of DeepLab v3+, and a channel attention module is inserted into the residual module. Moreover, a feature fusion branch based on a feature pyramid network is added to the DeepLab v3+ encoder, which fuses feature maps of different levels. Test set TS1 from Plant Village and test set TS2 from an orchard field were used for testing to verify the segmentation performance of the method. In the test set TS1, the improved DeepLab v3+ had 0.848, 0.881, and 0.918 on the mean intersection over union (mIOU), recall, and F1-score evaluation indicators, respectively, which was 3.0, 2.3, and 1.7% greater than the original DeepLab v3+. In the test set TS2, the improved DeepLab v3+ improved the evaluation indicators mIOU, recall, and F1-score by 3.3, 2.5, and 1.9%, respectively. The test results show that the improved DeepLab v3+ has better segmentation performance. It is more suitable for the segmentation of grape leaf black rot spots and can be used as an effective tool for grape disease grade assessment. |
| first_indexed | 2024-12-13T01:01:58Z |
| format | Article |
| id | doaj.art-c6841b01e65a42ad90c190c48a211662 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-13T01:01:58Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-c6841b01e65a42ad90c190c48a2116622022-12-22T00:04:39ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-02-011310.3389/fpls.2022.795410795410An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot SpotsHongbo YuanJiajun ZhuQifan WangMan ChengZhenjiang CaiThe common method for evaluating the extent of grape disease is to classify the disease spots according to the area. The prerequisite for this operation is to accurately segment the disease spots. This paper presents an improved DeepLab v3+ deep learning network for the segmentation of grapevine leaf black rot spots. The ResNet101 network is used as the backbone network of DeepLab v3+, and a channel attention module is inserted into the residual module. Moreover, a feature fusion branch based on a feature pyramid network is added to the DeepLab v3+ encoder, which fuses feature maps of different levels. Test set TS1 from Plant Village and test set TS2 from an orchard field were used for testing to verify the segmentation performance of the method. In the test set TS1, the improved DeepLab v3+ had 0.848, 0.881, and 0.918 on the mean intersection over union (mIOU), recall, and F1-score evaluation indicators, respectively, which was 3.0, 2.3, and 1.7% greater than the original DeepLab v3+. In the test set TS2, the improved DeepLab v3+ improved the evaluation indicators mIOU, recall, and F1-score by 3.3, 2.5, and 1.9%, respectively. The test results show that the improved DeepLab v3+ has better segmentation performance. It is more suitable for the segmentation of grape leaf black rot spots and can be used as an effective tool for grape disease grade assessment.https://www.frontiersin.org/articles/10.3389/fpls.2022.795410/fullgrape black rotsemantic segmentationDeepLab V3+channel attentionfeature pyramid network |
| spellingShingle | Hongbo Yuan Jiajun Zhu Qifan Wang Man Cheng Zhenjiang Cai An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots Frontiers in Plant Science grape black rot semantic segmentation DeepLab V3+ channel attention feature pyramid network |
| title | An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots |
| title_full | An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots |
| title_fullStr | An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots |
| title_full_unstemmed | An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots |
| title_short | An Improved DeepLab v3+ Deep Learning Network Applied to the Segmentation of Grape Leaf Black Rot Spots |
| title_sort | improved deeplab v3 deep learning network applied to the segmentation of grape leaf black rot spots |
| topic | grape black rot semantic segmentation DeepLab V3+ channel attention feature pyramid network |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.795410/full |
| work_keys_str_mv | AT hongboyuan animproveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT jiajunzhu animproveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT qifanwang animproveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT mancheng animproveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT zhenjiangcai animproveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT hongboyuan improveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT jiajunzhu improveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT qifanwang improveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT mancheng improveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots AT zhenjiangcai improveddeeplabv3deeplearningnetworkappliedtothesegmentationofgrapeleafblackrotspots |