Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images
The acquisition of maize tassel phenotype information plays a vital role in studying maize growth and improving yield. Unfortunately, detecting maize tassels has proven challenging because of the complex field environment, including image resolution, varying sunlight conditions, plant varieties, and...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/10/2530 |
| _version_ | 1827740227260645376 |
|---|---|
| author | Binbin Wang Guijun Yang Hao Yang Jinan Gu Sizhe Xu Dan Zhao Bo Xu |
| author_facet | Binbin Wang Guijun Yang Hao Yang Jinan Gu Sizhe Xu Dan Zhao Bo Xu |
| author_sort | Binbin Wang |
| collection | DOAJ |
| description | The acquisition of maize tassel phenotype information plays a vital role in studying maize growth and improving yield. Unfortunately, detecting maize tassels has proven challenging because of the complex field environment, including image resolution, varying sunlight conditions, plant varieties, and planting density. To address this situation, the present study uses unmanned aerial vehicle (UAV) remote sensing technology and a deep learning algorithm to facilitate maize tassel identification and counting. UAVs are used to collect maize tassel images in experimental fields, and RetinaNet serves as the basic model for detecting maize tassels. Small maize tassels are accurately identified by optimizing the feature pyramid structure in the model and introducing attention mechanisms. We also study how mapping differences in image resolution, brightness, plant variety, and planting density affect the RetinaNet model. The results show that the improved RetinaNet model is significantly better at detecting maize tassels than the original RetinaNet model. The average precision in this study is 0.9717, the precision is 0.9802, and the recall rate is 0.9036. Compared with the original model, the improved RetinaNet improves the average precision, precision, and recall rate by 1.84%, 1.57%, and 4.6%, respectively. Compared with mainstream target detection models such as Faster R-CNN, YOLOX, and SSD, the improved RetinaNet model more accurately detects smaller maize tassels. For equal-area images of differing resolution, maize tassel detection becomes progressively worse as the resolution decreases. We also analyze how detection depends on brightness in the various models. With increasing image brightness, the maize tassel detection worsens, especially for small maize tassels. This paper also analyzes the various models for detecting the tassels of five maize varieties. Zhengdan958 tassels prove the easiest to detect, with R<sup>2</sup> = 0.9708, 0.9759, and 0.9545 on 5, 9, and 20 August 2021, respectively. Finally, we use the various models to detect maize tassels under different planting densities. At 29,985, 44,978, 67,466, and 89,955 plants/hm<sup>2</sup>, the mean absolute errors for detecting Zhengdan958 tassels are 0.18, 0.26, 0.48, and 0.63, respectively. Thus, the detection error increases gradually with increasing planting density. This study thus provides a new method for high-precision identification of maize tassels in farmland and is especially useful for detecting small maize tassels. This technology can be used for high-throughput investigations of maize phenotypic traits. |
| first_indexed | 2024-03-11T03:21:01Z |
| format | Article |
| id | doaj.art-01383c0ddc764b9e831f0604132a2309 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T03:21:01Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-01383c0ddc764b9e831f0604132a23092023-11-18T03:06:28ZengMDPI AGRemote Sensing2072-42922023-05-011510253010.3390/rs15102530Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV ImagesBinbin Wang0Guijun Yang1Hao Yang2Jinan Gu3Sizhe Xu4Dan Zhao5Bo Xu6Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaSchool of Mechanical Engineering, Jiangsu University, Zhenjiang 212000, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaThe acquisition of maize tassel phenotype information plays a vital role in studying maize growth and improving yield. Unfortunately, detecting maize tassels has proven challenging because of the complex field environment, including image resolution, varying sunlight conditions, plant varieties, and planting density. To address this situation, the present study uses unmanned aerial vehicle (UAV) remote sensing technology and a deep learning algorithm to facilitate maize tassel identification and counting. UAVs are used to collect maize tassel images in experimental fields, and RetinaNet serves as the basic model for detecting maize tassels. Small maize tassels are accurately identified by optimizing the feature pyramid structure in the model and introducing attention mechanisms. We also study how mapping differences in image resolution, brightness, plant variety, and planting density affect the RetinaNet model. The results show that the improved RetinaNet model is significantly better at detecting maize tassels than the original RetinaNet model. The average precision in this study is 0.9717, the precision is 0.9802, and the recall rate is 0.9036. Compared with the original model, the improved RetinaNet improves the average precision, precision, and recall rate by 1.84%, 1.57%, and 4.6%, respectively. Compared with mainstream target detection models such as Faster R-CNN, YOLOX, and SSD, the improved RetinaNet model more accurately detects smaller maize tassels. For equal-area images of differing resolution, maize tassel detection becomes progressively worse as the resolution decreases. We also analyze how detection depends on brightness in the various models. With increasing image brightness, the maize tassel detection worsens, especially for small maize tassels. This paper also analyzes the various models for detecting the tassels of five maize varieties. Zhengdan958 tassels prove the easiest to detect, with R<sup>2</sup> = 0.9708, 0.9759, and 0.9545 on 5, 9, and 20 August 2021, respectively. Finally, we use the various models to detect maize tassels under different planting densities. At 29,985, 44,978, 67,466, and 89,955 plants/hm<sup>2</sup>, the mean absolute errors for detecting Zhengdan958 tassels are 0.18, 0.26, 0.48, and 0.63, respectively. Thus, the detection error increases gradually with increasing planting density. This study thus provides a new method for high-precision identification of maize tassels in farmland and is especially useful for detecting small maize tassels. This technology can be used for high-throughput investigations of maize phenotypic traits.https://www.mdpi.com/2072-4292/15/10/2530deep learningtarget detectionmaize tasselsUAVimage analysis |
| spellingShingle | Binbin Wang Guijun Yang Hao Yang Jinan Gu Sizhe Xu Dan Zhao Bo Xu Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images Remote Sensing deep learning target detection maize tassels UAV image analysis |
| title | Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images |
| title_full | Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images |
| title_fullStr | Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images |
| title_full_unstemmed | Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images |
| title_short | Multiscale Maize Tassel Identification Based on Improved RetinaNet Model and UAV Images |
| title_sort | multiscale maize tassel identification based on improved retinanet model and uav images |
| topic | deep learning target detection maize tassels UAV image analysis |
| url | https://www.mdpi.com/2072-4292/15/10/2530 |
| work_keys_str_mv | AT binbinwang multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT guijunyang multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT haoyang multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT jinangu multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT sizhexu multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT danzhao multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages AT boxu multiscalemaizetasselidentificationbasedonimprovedretinanetmodelanduavimages |