Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images
Cotton constitutes 81% of the world’s natural fibers. Accurate and rapid cotton yield estimation is important for cotton trade and agricultural policy development. Therefore, we developed a remote sensing index that can intuitively represent cotton boll characteristics and support cotton yield estim...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/6/9/254 |
| _version_ | 1797489283826712576 |
|---|---|
| author | Guanwei Shi Xin Du Mingwei Du Qiangzi Li Xiaoli Tian Yiting Ren Yuan Zhang Hongyan Wang |
| author_facet | Guanwei Shi Xin Du Mingwei Du Qiangzi Li Xiaoli Tian Yiting Ren Yuan Zhang Hongyan Wang |
| author_sort | Guanwei Shi |
| collection | DOAJ |
| description | Cotton constitutes 81% of the world’s natural fibers. Accurate and rapid cotton yield estimation is important for cotton trade and agricultural policy development. Therefore, we developed a remote sensing index that can intuitively represent cotton boll characteristics and support cotton yield estimation by extracting cotton boll pixels. In our study, the Density of open Cotton boll Pixels (DCPs) was extracted by designing different cotton boll indices combined with the threshold segmentation method. The relationship between DCP and field survey datasets, the Density of Total Cotton bolls (DTC), and yield were compared and analyzed. Five common yield estimation models, Linear Regression (LR), Support Vector Regression (SVR), Classification and Regression Trees (CART), Random Forest (RF), and K-Nearest Neighbors (KNN), were implemented and evaluated. The results showed that DCP had a strong correlation with yield, with a Pearson correlation coefficient of 0.84. The RF method exhibited the best yield estimation performance, with average R<sup>2</sup> and rRMSE values of 0.77 and 7.5%, respectively (five-fold cross-validation). This study showed that RedGreenBlue (RGB) and Near Infrared Red (NIR) normalized, a normalized form index consisting of the RGB and NIR bands, performed best. |
| first_indexed | 2024-03-10T00:14:20Z |
| format | Article |
| id | doaj.art-bce37d78ecc7494fbc736a9769f2545a |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-10T00:14:20Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-bce37d78ecc7494fbc736a9769f2545a2023-11-23T15:54:00ZengMDPI AGDrones2504-446X2022-09-016925410.3390/drones6090254Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV ImagesGuanwei Shi0Xin Du1Mingwei Du2Qiangzi Li3Xiaoli Tian4Yiting Ren5Yuan Zhang6Hongyan Wang7Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaState Key Laboratory of Plant Physiology and Biochemistry, Key Laboratory of Crop Cultivation and Farming System, Center of Crop Chemical Control, China Agricultural University, Beijing 100193, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaState Key Laboratory of Plant Physiology and Biochemistry, Key Laboratory of Crop Cultivation and Farming System, Center of Crop Chemical Control, China Agricultural University, Beijing 100193, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCotton constitutes 81% of the world’s natural fibers. Accurate and rapid cotton yield estimation is important for cotton trade and agricultural policy development. Therefore, we developed a remote sensing index that can intuitively represent cotton boll characteristics and support cotton yield estimation by extracting cotton boll pixels. In our study, the Density of open Cotton boll Pixels (DCPs) was extracted by designing different cotton boll indices combined with the threshold segmentation method. The relationship between DCP and field survey datasets, the Density of Total Cotton bolls (DTC), and yield were compared and analyzed. Five common yield estimation models, Linear Regression (LR), Support Vector Regression (SVR), Classification and Regression Trees (CART), Random Forest (RF), and K-Nearest Neighbors (KNN), were implemented and evaluated. The results showed that DCP had a strong correlation with yield, with a Pearson correlation coefficient of 0.84. The RF method exhibited the best yield estimation performance, with average R<sup>2</sup> and rRMSE values of 0.77 and 7.5%, respectively (five-fold cross-validation). This study showed that RedGreenBlue (RGB) and Near Infrared Red (NIR) normalized, a normalized form index consisting of the RGB and NIR bands, performed best.https://www.mdpi.com/2504-446X/6/9/254cottonUAVcotton boll indexthreshold segmentationyield estimation |
| spellingShingle | Guanwei Shi Xin Du Mingwei Du Qiangzi Li Xiaoli Tian Yiting Ren Yuan Zhang Hongyan Wang Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images Drones cotton UAV cotton boll index threshold segmentation yield estimation |
| title | Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images |
| title_full | Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images |
| title_fullStr | Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images |
| title_full_unstemmed | Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images |
| title_short | Cotton Yield Estimation Using the Remotely Sensed Cotton Boll Index from UAV Images |
| title_sort | cotton yield estimation using the remotely sensed cotton boll index from uav images |
| topic | cotton UAV cotton boll index threshold segmentation yield estimation |
| url | https://www.mdpi.com/2504-446X/6/9/254 |
| work_keys_str_mv | AT guanweishi cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT xindu cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT mingweidu cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT qiangzili cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT xiaolitian cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT yitingren cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT yuanzhang cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages AT hongyanwang cottonyieldestimationusingtheremotelysensedcottonbollindexfromuavimages |