Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI
In the context of precision horticulture, decision support tools play a significant role in providing fruit growers with insights into orchard conditions, facilitating informed decisions regarding orchard management practices. This study presents the development of an autonomous yield estimation sys...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/8/12/734 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105036445188096 |
|---|---|
| author | Sergejs Kodors Imants Zarembo Gunārs Lācis Lienīte Litavniece Ilmārs Apeināns Marks Sondors Antons Pacejs |
| author_facet | Sergejs Kodors Imants Zarembo Gunārs Lācis Lienīte Litavniece Ilmārs Apeināns Marks Sondors Antons Pacejs |
| author_sort | Sergejs Kodors |
| collection | DOAJ |
| description | In the context of precision horticulture, decision support tools play a significant role in providing fruit growers with insights into orchard conditions, facilitating informed decisions regarding orchard management practices. This study presents the development of an autonomous yield estimation system designed to provide decision support to small commercial orchards. Autonomous yield estimation is based on the application of UAVs and AI. AI is used to identify and quantify fruitlets and fruits in photographs collected by UAV. In this article, we present our prototype of an autonomous yield estimation system. The adapted “4+1” architecture was applied to design a system with a holistic approach analyzing software, hardware, and ecosystem requirements. Six datasets are presented, which contain the images of fruitlets and fruits of apples, pears, and cherries. Three CNN models were trained: YOLOv8m, YOLOv9m, and YOLOv10m. The experiment showed that the most accurate was YOLOv9m, which achieved mean accuracies of 0.896 mAP@50 and 0.510 mAP@50:95 for all datasets. |
| format | Article |
| id | doaj-art-f9dfaf95688044a9b014f91f1c6b037b |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-f9dfaf95688044a9b014f91f1c6b037b2024-12-27T14:21:48ZengMDPI AGDrones2504-446X2024-12-0181273410.3390/drones8120734Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AISergejs Kodors0Imants Zarembo1Gunārs Lācis2Lienīte Litavniece3Ilmārs Apeināns4Marks Sondors5Antons Pacejs6Institute of Engineering, Faculty of Engineering, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaInstitute of Engineering, Faculty of Engineering, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaInstitute of Horticulture (LatHort), LV-3701 Dobele, LatviaResearch Institute for Business and Social Processes, Faculty of Economics and Management, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaInstitute of Engineering, Faculty of Engineering, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaInstitute of Engineering, Faculty of Engineering, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaInstitute of Engineering, Faculty of Engineering, Rezekne Academy of Technologies, Atbrivosanas Str. 115, LV-4601 Rezekne, LatviaIn the context of precision horticulture, decision support tools play a significant role in providing fruit growers with insights into orchard conditions, facilitating informed decisions regarding orchard management practices. This study presents the development of an autonomous yield estimation system designed to provide decision support to small commercial orchards. Autonomous yield estimation is based on the application of UAVs and AI. AI is used to identify and quantify fruitlets and fruits in photographs collected by UAV. In this article, we present our prototype of an autonomous yield estimation system. The adapted “4+1” architecture was applied to design a system with a holistic approach analyzing software, hardware, and ecosystem requirements. Six datasets are presented, which contain the images of fruitlets and fruits of apples, pears, and cherries. Three CNN models were trained: YOLOv8m, YOLOv9m, and YOLOv10m. The experiment showed that the most accurate was YOLOv9m, which achieved mean accuracies of 0.896 mAP@50 and 0.510 mAP@50:95 for all datasets.https://www.mdpi.com/2504-446X/8/12/734digital farminghorticultureobject detectionprecision farmingsystem modelingUAV |
| spellingShingle | Sergejs Kodors Imants Zarembo Gunārs Lācis Lienīte Litavniece Ilmārs Apeināns Marks Sondors Antons Pacejs Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI Drones digital farming horticulture object detection precision farming system modeling UAV |
| title | Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI |
| title_full | Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI |
| title_fullStr | Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI |
| title_full_unstemmed | Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI |
| title_short | Autonomous Yield Estimation System for Small Commercial Orchards Using UAV and AI |
| title_sort | autonomous yield estimation system for small commercial orchards using uav and ai |
| topic | digital farming horticulture object detection precision farming system modeling UAV |
| url | https://www.mdpi.com/2504-446X/8/12/734 |
| work_keys_str_mv | AT sergejskodors autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT imantszarembo autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT gunarslacis autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT lienitelitavniece autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT ilmarsapeinans autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT markssondors autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai AT antonspacejs autonomousyieldestimationsystemforsmallcommercialorchardsusinguavandai |