Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+
Aiming to determine the inaccurate image segmentation of strawberries with varying maturity levels due to fruit adhesion and stacking, this study proposed a strawberry image segmentation method based on the improved DeepLabV3+ model. The technique introduced the attention mechanism into the backbone...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/8/1875 |
| _version_ | 1827618270845337600 |
|---|---|
| author | Changqing Cai Jianwen Tan Peisen Zhang Yuxin Ye Jian Zhang |
| author_facet | Changqing Cai Jianwen Tan Peisen Zhang Yuxin Ye Jian Zhang |
| author_sort | Changqing Cai |
| collection | DOAJ |
| description | Aiming to determine the inaccurate image segmentation of strawberries with varying maturity levels due to fruit adhesion and stacking, this study proposed a strawberry image segmentation method based on the improved DeepLabV3+ model. The technique introduced the attention mechanism into the backbone network and the atrous spatial pyramid pooling module of the DeepLabV3+ network, adjusted the weights of feature channels in the neural network propagation process through the attention mechanism to enhance the feature information of strawberry images, reduced the interference of environmental factors, and improved the accuracy of strawberry image segmentation. The experimental results showed that the proposed method can accurately segment images of strawberries with different maturities; the mean pixel accuracy and mean intersection over union of the model were 90.9% and 83.05%, respectively, and the frames per second (FPS) was 7.67. The method can effectively reduce the influence of environmental factors on strawberry image segmentation and provide an effective approach for accurate operation of strawberry picking robots. |
| first_indexed | 2024-03-09T10:02:17Z |
| format | Article |
| id | doaj.art-3a51a193df8e46e3b8f3ac3a79ee7c8f |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-09T10:02:17Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-3a51a193df8e46e3b8f3ac3a79ee7c8f2023-12-01T23:18:06ZengMDPI AGAgronomy2073-43952022-08-01128187510.3390/agronomy12081875Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+Changqing Cai0Jianwen Tan1Peisen Zhang2Yuxin Ye3Jian Zhang4Engineering Training Center, Changchun Institute of Technology, Changchun 130012, ChinaCollege of Electrical and Information Engineering, Changchun Institute of Technology, Changchun 130012, ChinaCollege of Energy and Power Engineering, Changchun Institute of Technology, Changchun 130012, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaFaculty of Agronomy, Jilin Agricultural University, Changchun 130018, ChinaAiming to determine the inaccurate image segmentation of strawberries with varying maturity levels due to fruit adhesion and stacking, this study proposed a strawberry image segmentation method based on the improved DeepLabV3+ model. The technique introduced the attention mechanism into the backbone network and the atrous spatial pyramid pooling module of the DeepLabV3+ network, adjusted the weights of feature channels in the neural network propagation process through the attention mechanism to enhance the feature information of strawberry images, reduced the interference of environmental factors, and improved the accuracy of strawberry image segmentation. The experimental results showed that the proposed method can accurately segment images of strawberries with different maturities; the mean pixel accuracy and mean intersection over union of the model were 90.9% and 83.05%, respectively, and the frames per second (FPS) was 7.67. The method can effectively reduce the influence of environmental factors on strawberry image segmentation and provide an effective approach for accurate operation of strawberry picking robots.https://www.mdpi.com/2073-4395/12/8/1875improved DeepLabV3+attention mechanismimage segmentationstrawberry |
| spellingShingle | Changqing Cai Jianwen Tan Peisen Zhang Yuxin Ye Jian Zhang Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ Agronomy improved DeepLabV3+ attention mechanism image segmentation strawberry |
| title | Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ |
| title_full | Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ |
| title_fullStr | Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ |
| title_full_unstemmed | Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ |
| title_short | Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+ |
| title_sort | determining strawberries varying maturity levels by utilizing image segmentation methods of improved deeplabv3 |
| topic | improved DeepLabV3+ attention mechanism image segmentation strawberry |
| url | https://www.mdpi.com/2073-4395/12/8/1875 |
| work_keys_str_mv | AT changqingcai determiningstrawberriesvaryingmaturitylevelsbyutilizingimagesegmentationmethodsofimproveddeeplabv3 AT jianwentan determiningstrawberriesvaryingmaturitylevelsbyutilizingimagesegmentationmethodsofimproveddeeplabv3 AT peisenzhang determiningstrawberriesvaryingmaturitylevelsbyutilizingimagesegmentationmethodsofimproveddeeplabv3 AT yuxinye determiningstrawberriesvaryingmaturitylevelsbyutilizingimagesegmentationmethodsofimproveddeeplabv3 AT jianzhang determiningstrawberriesvaryingmaturitylevelsbyutilizingimagesegmentationmethodsofimproveddeeplabv3 |