A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM
This paper focuses on the problems of inaccurate extraction of winter wheat edges from high-resolution images, misclassification and omission due to intraclass differences as well as the large number of network parameters and long training time of existing classical semantic segmentation models. Thi...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4156 |
| _version_ | 1797581938100273152 |
|---|---|
| author | Yao Zhang Hong Wang Jiahao Liu Xili Zhao Yuting Lu Tengfei Qu Haozhe Tian Jingru Su Dingsheng Luo Yalei Yang |
| author_facet | Yao Zhang Hong Wang Jiahao Liu Xili Zhao Yuting Lu Tengfei Qu Haozhe Tian Jingru Su Dingsheng Luo Yalei Yang |
| author_sort | Yao Zhang |
| collection | DOAJ |
| description | This paper focuses on the problems of inaccurate extraction of winter wheat edges from high-resolution images, misclassification and omission due to intraclass differences as well as the large number of network parameters and long training time of existing classical semantic segmentation models. This paper proposes a lightweight winter wheat planting area extraction model that combines the DeepLabv3+ model and a dual-attention mechanism. The model uses the lightweight network MobileNetv2 to replace the backbone network Xception of DeepLabv3+ to reduce the number of parameters and improve the training speed. It also introduces the lightweight Convolutional Block Attention Module (CBAM) dual-attention mechanism to extract winter wheat feature information more accurately and efficiently. Finally, the model is used to complete the dataset creation, model training, winter wheat plantation extraction, and accuracy evaluation. The results show that the improved lightweight DeepLabv3+ model in this paper has high reliability in the recognition extraction of winter wheat, and its recognition results of OA, mPA, and mIoU reach 95.28%, 94.40%, and 89.79%, respectively, which are 1.52%, 1.51%, and 2.99% higher than those for the original DeepLabv3+ model. Meanwhile, the model’s recognition accuracy was much higher than that of the three classical semantic segmentation models of UNet, ResUNet and PSPNet. The improved lightweight DeepLabv3+ also has far fewer model parameters and training time than the other four models. The model has been tested in other regions, and the results show that it has good generalization ability. The model in general ensures the extraction accuracy while significantly reducing the number of parameters and satisfying the timeliness, which can achieve the fast and accurate extraction of winter wheat planting sites and has good application prospects. |
| first_indexed | 2024-03-10T23:14:44Z |
| format | Article |
| id | doaj.art-cb767622c663470d89d0b0c8b68ea9ab |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:14:44Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-cb767622c663470d89d0b0c8b68ea9ab2023-11-19T08:45:12ZengMDPI AGRemote Sensing2072-42922023-08-011517415610.3390/rs15174156A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAMYao Zhang0Hong Wang1Jiahao Liu2Xili Zhao3Yuting Lu4Tengfei Qu5Haozhe Tian6Jingru Su7Dingsheng Luo8Yalei Yang9College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaFaculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaCollege of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, ChinaFaculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaThis paper focuses on the problems of inaccurate extraction of winter wheat edges from high-resolution images, misclassification and omission due to intraclass differences as well as the large number of network parameters and long training time of existing classical semantic segmentation models. This paper proposes a lightweight winter wheat planting area extraction model that combines the DeepLabv3+ model and a dual-attention mechanism. The model uses the lightweight network MobileNetv2 to replace the backbone network Xception of DeepLabv3+ to reduce the number of parameters and improve the training speed. It also introduces the lightweight Convolutional Block Attention Module (CBAM) dual-attention mechanism to extract winter wheat feature information more accurately and efficiently. Finally, the model is used to complete the dataset creation, model training, winter wheat plantation extraction, and accuracy evaluation. The results show that the improved lightweight DeepLabv3+ model in this paper has high reliability in the recognition extraction of winter wheat, and its recognition results of OA, mPA, and mIoU reach 95.28%, 94.40%, and 89.79%, respectively, which are 1.52%, 1.51%, and 2.99% higher than those for the original DeepLabv3+ model. Meanwhile, the model’s recognition accuracy was much higher than that of the three classical semantic segmentation models of UNet, ResUNet and PSPNet. The improved lightweight DeepLabv3+ also has far fewer model parameters and training time than the other four models. The model has been tested in other regions, and the results show that it has good generalization ability. The model in general ensures the extraction accuracy while significantly reducing the number of parameters and satisfying the timeliness, which can achieve the fast and accurate extraction of winter wheat planting sites and has good application prospects.https://www.mdpi.com/2072-4292/15/17/4156deep learninglightweightDeepLabv3+attention mechanismwinter wheat recognition |
| spellingShingle | Yao Zhang Hong Wang Jiahao Liu Xili Zhao Yuting Lu Tengfei Qu Haozhe Tian Jingru Su Dingsheng Luo Yalei Yang A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM Remote Sensing deep learning lightweight DeepLabv3+ attention mechanism winter wheat recognition |
| title | A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM |
| title_full | A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM |
| title_fullStr | A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM |
| title_full_unstemmed | A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM |
| title_short | A Lightweight Winter Wheat Planting Area Extraction Model Based on Improved DeepLabv3+ and CBAM |
| title_sort | lightweight winter wheat planting area extraction model based on improved deeplabv3 and cbam |
| topic | deep learning lightweight DeepLabv3+ attention mechanism winter wheat recognition |
| url | https://www.mdpi.com/2072-4292/15/17/4156 |
| work_keys_str_mv | AT yaozhang alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT hongwang alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT jiahaoliu alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT xilizhao alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT yutinglu alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT tengfeiqu alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT haozhetian alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT jingrusu alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT dingshengluo alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT yaleiyang alightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT yaozhang lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT hongwang lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT jiahaoliu lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT xilizhao lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT yutinglu lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT tengfeiqu lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT haozhetian lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT jingrusu lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT dingshengluo lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam AT yaleiyang lightweightwinterwheatplantingareaextractionmodelbasedonimproveddeeplabv3andcbam |