Mapping Tobacco Fields Using UAV RGB Images
Tobacco planting information is an important part of tobacco production management. Unmanned aerial vehicle (UAV) remote sensing systems have become a popular topic worldwide because they are mobile, rapid and economic. In this paper, an automatic identification method for tobacco fields based on UA...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/8/1791 |
| _version_ | 1798005664695451648 |
|---|---|
| author | Xiufang Zhu Guofeng Xiao Ping Wen Jinshui Zhang Chenyao Hou |
| author_facet | Xiufang Zhu Guofeng Xiao Ping Wen Jinshui Zhang Chenyao Hou |
| author_sort | Xiufang Zhu |
| collection | DOAJ |
| description | Tobacco planting information is an important part of tobacco production management. Unmanned aerial vehicle (UAV) remote sensing systems have become a popular topic worldwide because they are mobile, rapid and economic. In this paper, an automatic identification method for tobacco fields based on UAV images is developed by combining supervised classifications with image morphological operations, and this method was used in the Yunnan Province, which is the top province for tobacco planting in China. The results show that the produce accuracy, user accuracy, and overall accuracy of tobacco field identification using the method proposed in this paper are 92.59%, 96.61% and 95.93%, respectively. The method proposed in this paper has the advantages of automation, flow process, high accuracy and easy operation, but the ground sampling distance (GSD) of the UAV image has an effect on the accuracy of the proposed method. When the image GSD was reduced to 1 m, the overall accuracy decreased by approximately 10%. To solve this problem, we further introduced the convolution method into the proposed method, which can ensure the recognition accuracy of tobacco field is above 90% when GSD is less than or equal to 1 m. Some other potential improvements of methods for mapping tobacco fields were also discussed in this paper. |
| first_indexed | 2024-04-11T12:43:00Z |
| format | Article |
| id | doaj.art-52c58dc4a7c949cf91ae4b2106c90a0a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:43:00Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-52c58dc4a7c949cf91ae4b2106c90a0a2022-12-22T04:23:26ZengMDPI AGSensors1424-82202019-04-01198179110.3390/s19081791s19081791Mapping Tobacco Fields Using UAV RGB ImagesXiufang Zhu0Guofeng Xiao1Ping Wen2Jinshui Zhang3Chenyao Hou4State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, ChinaKey Laboratory of Environmental Change and Natural Disaster, Ministry of Education, Beijing Normal University, Beijing 100875, ChinaPowerchina Kunming Engineering Corporation Limited, Kunming 650051, ChinaState Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, ChinaInstitute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaTobacco planting information is an important part of tobacco production management. Unmanned aerial vehicle (UAV) remote sensing systems have become a popular topic worldwide because they are mobile, rapid and economic. In this paper, an automatic identification method for tobacco fields based on UAV images is developed by combining supervised classifications with image morphological operations, and this method was used in the Yunnan Province, which is the top province for tobacco planting in China. The results show that the produce accuracy, user accuracy, and overall accuracy of tobacco field identification using the method proposed in this paper are 92.59%, 96.61% and 95.93%, respectively. The method proposed in this paper has the advantages of automation, flow process, high accuracy and easy operation, but the ground sampling distance (GSD) of the UAV image has an effect on the accuracy of the proposed method. When the image GSD was reduced to 1 m, the overall accuracy decreased by approximately 10%. To solve this problem, we further introduced the convolution method into the proposed method, which can ensure the recognition accuracy of tobacco field is above 90% when GSD is less than or equal to 1 m. Some other potential improvements of methods for mapping tobacco fields were also discussed in this paper.https://www.mdpi.com/1424-8220/19/8/1791tobacco fieldUAV imagemorphologyconvolution |
| spellingShingle | Xiufang Zhu Guofeng Xiao Ping Wen Jinshui Zhang Chenyao Hou Mapping Tobacco Fields Using UAV RGB Images Sensors tobacco field UAV image morphology convolution |
| title | Mapping Tobacco Fields Using UAV RGB Images |
| title_full | Mapping Tobacco Fields Using UAV RGB Images |
| title_fullStr | Mapping Tobacco Fields Using UAV RGB Images |
| title_full_unstemmed | Mapping Tobacco Fields Using UAV RGB Images |
| title_short | Mapping Tobacco Fields Using UAV RGB Images |
| title_sort | mapping tobacco fields using uav rgb images |
| topic | tobacco field UAV image morphology convolution |
| url | https://www.mdpi.com/1424-8220/19/8/1791 |
| work_keys_str_mv | AT xiufangzhu mappingtobaccofieldsusinguavrgbimages AT guofengxiao mappingtobaccofieldsusinguavrgbimages AT pingwen mappingtobaccofieldsusinguavrgbimages AT jinshuizhang mappingtobaccofieldsusinguavrgbimages AT chenyaohou mappingtobaccofieldsusinguavrgbimages |