Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages
Strawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowe...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/13/1584 |
| _version_ | 1819289327578906624 |
|---|---|
| author | Yang Chen Won Suk Lee Hao Gan Natalia Peres Clyde Fraisse Yanchao Zhang Yong He |
| author_facet | Yang Chen Won Suk Lee Hao Gan Natalia Peres Clyde Fraisse Yanchao Zhang Yong He |
| author_sort | Yang Chen |
| collection | DOAJ |
| description | Strawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowers and their distribution in a strawberry field is, therefore, imperative for predicting the coming strawberry yield. Usually, the number of flowers and their distribution are estimated manually, which is time-consuming, labor-intensive, and subjective. In this paper, we develop an automatic strawberry flower detection system for yield prediction with minimal labor and time costs. The system used a small unmanned aerial vehicle (UAV) (DJI Technology Co., Ltd., Shenzhen, China) equipped with an RGB (red, green, blue) camera to capture near-ground images of two varieties (Sensation and Radiance) at two different heights (2 m and 3 m) and built orthoimages of a 402 m<sup>2</sup> strawberry field. The orthoimages were automatically processed using the Pix4D software and split into sequential pieces for deep learning detection. A faster region-based convolutional neural network (R-CNN), a state-of-the-art deep neural network model, was chosen for the detection and counting of the number of flowers, mature strawberries, and immature strawberries. The mean average precision (mAP) was 0.83 for all detected objects at 2 m heights and 0.72 for all detected objects at 3 m heights. We adopted this model to count strawberry flowers in November and December from 2 m aerial images and compared the results with a manual count. The average deep learning counting accuracy was 84.1% with average occlusion of 13.5%. Using this system could provide accurate counts of strawberry flowers, which can be used to forecast future yields and build distribution maps to help farmers observe the growth cycle of strawberry fields. |
| first_indexed | 2024-12-24T03:05:05Z |
| format | Article |
| id | doaj.art-4bf49609c98641b6bcad46f1a95ab97f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T03:05:05Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4bf49609c98641b6bcad46f1a95ab97f2022-12-21T17:18:01ZengMDPI AGRemote Sensing2072-42922019-07-011113158410.3390/rs11131584rs11131584Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial OrthoimagesYang Chen0Won Suk Lee1Hao Gan2Natalia Peres3Clyde Fraisse4Yanchao Zhang5Yong He6College of Biosystem Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaDepartment of Agricultural and Biological Engineering, University of Florida, Gainesville, FL 32611, USADepartment of Biosystems Engineering and Soil Science, University of Tennessee institute of Agriculture, Knoxville, TN 37996, USAGulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USADepartment of Agricultural and Biological Engineering, University of Florida, Gainesville, FL 32611, USAFaculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaCollege of Biosystem Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaStrawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowers and their distribution in a strawberry field is, therefore, imperative for predicting the coming strawberry yield. Usually, the number of flowers and their distribution are estimated manually, which is time-consuming, labor-intensive, and subjective. In this paper, we develop an automatic strawberry flower detection system for yield prediction with minimal labor and time costs. The system used a small unmanned aerial vehicle (UAV) (DJI Technology Co., Ltd., Shenzhen, China) equipped with an RGB (red, green, blue) camera to capture near-ground images of two varieties (Sensation and Radiance) at two different heights (2 m and 3 m) and built orthoimages of a 402 m<sup>2</sup> strawberry field. The orthoimages were automatically processed using the Pix4D software and split into sequential pieces for deep learning detection. A faster region-based convolutional neural network (R-CNN), a state-of-the-art deep neural network model, was chosen for the detection and counting of the number of flowers, mature strawberries, and immature strawberries. The mean average precision (mAP) was 0.83 for all detected objects at 2 m heights and 0.72 for all detected objects at 3 m heights. We adopted this model to count strawberry flowers in November and December from 2 m aerial images and compared the results with a manual count. The average deep learning counting accuracy was 84.1% with average occlusion of 13.5%. Using this system could provide accurate counts of strawberry flowers, which can be used to forecast future yields and build distribution maps to help farmers observe the growth cycle of strawberry fields.https://www.mdpi.com/2072-4292/11/13/1584strawberry yield predictionunmanned aerial vehicleorthoimagesdeep neural networkdistribution map |
| spellingShingle | Yang Chen Won Suk Lee Hao Gan Natalia Peres Clyde Fraisse Yanchao Zhang Yong He Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages Remote Sensing strawberry yield prediction unmanned aerial vehicle orthoimages deep neural network distribution map |
| title | Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages |
| title_full | Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages |
| title_fullStr | Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages |
| title_full_unstemmed | Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages |
| title_short | Strawberry Yield Prediction Based on a Deep Neural Network Using High-Resolution Aerial Orthoimages |
| title_sort | strawberry yield prediction based on a deep neural network using high resolution aerial orthoimages |
| topic | strawberry yield prediction unmanned aerial vehicle orthoimages deep neural network distribution map |
| url | https://www.mdpi.com/2072-4292/11/13/1584 |
| work_keys_str_mv | AT yangchen strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT wonsuklee strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT haogan strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT nataliaperes strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT clydefraisse strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT yanchaozhang strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages AT yonghe strawberryyieldpredictionbasedonadeepneuralnetworkusinghighresolutionaerialorthoimages |