Wheat Ear Recognition Based on RetinaNet and Transfer Learning
The number of wheat ears is an essential indicator for wheat production and yield estimation, but accurately obtaining wheat ears requires expensive manual cost and labor time. Meanwhile, the characteristics of wheat ears provide less information, and the color is consistent with the background, whi...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4845 |
| _version_ | 1797526082115600384 |
|---|---|
| author | Jingbo Li Changchun Li Shuaipeng Fei Chunyan Ma Weinan Chen Fan Ding Yilin Wang Yacong Li Jinjin Shi Zhen Xiao |
| author_facet | Jingbo Li Changchun Li Shuaipeng Fei Chunyan Ma Weinan Chen Fan Ding Yilin Wang Yacong Li Jinjin Shi Zhen Xiao |
| author_sort | Jingbo Li |
| collection | DOAJ |
| description | The number of wheat ears is an essential indicator for wheat production and yield estimation, but accurately obtaining wheat ears requires expensive manual cost and labor time. Meanwhile, the characteristics of wheat ears provide less information, and the color is consistent with the background, which can be challenging to obtain the number of wheat ears required. In this paper, the performance of Faster regions with convolutional neural networks (Faster R-CNN) and RetinaNet to predict the number of wheat ears for wheat at different growth stages under different conditions is investigated. The results show that using the Global WHEAT dataset for recognition, the RetinaNet method, and the Faster R-CNN method achieve an average accuracy of 0.82 and 0.72, with the RetinaNet method obtaining the highest recognition accuracy. Secondly, using the collected image data for recognition, the <i>R</i><sup>2</sup> of RetinaNet and Faster R-CNN after transfer learning is 0.9722 and 0.8702, respectively, indicating that the recognition accuracy of the RetinaNet method is higher on different data sets. We also tested wheat ears at both the filling and maturity stages; our proposed method has proven to be very robust (the <i>R</i><sup>2</sup> is above 90). This study provides technical support and a reference for automatic wheat ear recognition and yield estimation. |
| first_indexed | 2024-03-10T09:24:07Z |
| format | Article |
| id | doaj.art-d5ca4f1025944ea5876e556bc04ac566 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:24:07Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d5ca4f1025944ea5876e556bc04ac5662023-11-22T04:56:54ZengMDPI AGSensors1424-82202021-07-012114484510.3390/s21144845Wheat Ear Recognition Based on RetinaNet and Transfer LearningJingbo Li0Changchun Li1Shuaipeng Fei2Chunyan Ma3Weinan Chen4Fan Ding5Yilin Wang6Yacong Li7Jinjin Shi8Zhen Xiao9School of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Mapping Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaThe number of wheat ears is an essential indicator for wheat production and yield estimation, but accurately obtaining wheat ears requires expensive manual cost and labor time. Meanwhile, the characteristics of wheat ears provide less information, and the color is consistent with the background, which can be challenging to obtain the number of wheat ears required. In this paper, the performance of Faster regions with convolutional neural networks (Faster R-CNN) and RetinaNet to predict the number of wheat ears for wheat at different growth stages under different conditions is investigated. The results show that using the Global WHEAT dataset for recognition, the RetinaNet method, and the Faster R-CNN method achieve an average accuracy of 0.82 and 0.72, with the RetinaNet method obtaining the highest recognition accuracy. Secondly, using the collected image data for recognition, the <i>R</i><sup>2</sup> of RetinaNet and Faster R-CNN after transfer learning is 0.9722 and 0.8702, respectively, indicating that the recognition accuracy of the RetinaNet method is higher on different data sets. We also tested wheat ears at both the filling and maturity stages; our proposed method has proven to be very robust (the <i>R</i><sup>2</sup> is above 90). This study provides technical support and a reference for automatic wheat ear recognition and yield estimation.https://www.mdpi.com/1424-8220/21/14/4845RetinaNetdeep learningtransfer learningwheat earsGlobal WHEAT |
| spellingShingle | Jingbo Li Changchun Li Shuaipeng Fei Chunyan Ma Weinan Chen Fan Ding Yilin Wang Yacong Li Jinjin Shi Zhen Xiao Wheat Ear Recognition Based on RetinaNet and Transfer Learning Sensors RetinaNet deep learning transfer learning wheat ears Global WHEAT |
| title | Wheat Ear Recognition Based on RetinaNet and Transfer Learning |
| title_full | Wheat Ear Recognition Based on RetinaNet and Transfer Learning |
| title_fullStr | Wheat Ear Recognition Based on RetinaNet and Transfer Learning |
| title_full_unstemmed | Wheat Ear Recognition Based on RetinaNet and Transfer Learning |
| title_short | Wheat Ear Recognition Based on RetinaNet and Transfer Learning |
| title_sort | wheat ear recognition based on retinanet and transfer learning |
| topic | RetinaNet deep learning transfer learning wheat ears Global WHEAT |
| url | https://www.mdpi.com/1424-8220/21/14/4845 |
| work_keys_str_mv | AT jingboli wheatearrecognitionbasedonretinanetandtransferlearning AT changchunli wheatearrecognitionbasedonretinanetandtransferlearning AT shuaipengfei wheatearrecognitionbasedonretinanetandtransferlearning AT chunyanma wheatearrecognitionbasedonretinanetandtransferlearning AT weinanchen wheatearrecognitionbasedonretinanetandtransferlearning AT fanding wheatearrecognitionbasedonretinanetandtransferlearning AT yilinwang wheatearrecognitionbasedonretinanetandtransferlearning AT yacongli wheatearrecognitionbasedonretinanetandtransferlearning AT jinjinshi wheatearrecognitionbasedonretinanetandtransferlearning AT zhenxiao wheatearrecognitionbasedonretinanetandtransferlearning |