Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis
Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/21/6774 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173151131598848 |
|---|---|
| author | Francisco Oliveira Daniel Queirós da Silva Vítor Filipe Tatiana Martins Pinho Mário Cunha José Boaventura Cunha Filipe Neves dos Santos |
| author_facet | Francisco Oliveira Daniel Queirós da Silva Vítor Filipe Tatiana Martins Pinho Mário Cunha José Boaventura Cunha Filipe Neves dos Santos |
| author_sort | Francisco Oliveira |
| collection | DOAJ |
| description | Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed us to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection in images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70% and 86.5% with inference times of around 89 ms for an input size of 1280 × 1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system. |
| format | Article |
| id | doaj-art-21cf39d3f64940369c4b72eaa4a8d7d0 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-21cf39d3f64940369c4b72eaa4a8d7d02024-11-08T14:40:54ZengMDPI AGSensors1424-82202024-10-012421677410.3390/s24216774Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image AnalysisFrancisco Oliveira0Daniel Queirós da Silva1Vítor Filipe2Tatiana Martins Pinho3Mário Cunha4José Boaventura Cunha5Filipe Neves dos Santos6School of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, PortugalINESC Technology and Science (INESC TEC), 4200-465 Porto, PortugalSchool of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, PortugalINESC Technology and Science (INESC TEC), 4200-465 Porto, PortugalINESC Technology and Science (INESC TEC), 4200-465 Porto, PortugalSchool of Science and Technology, University of Trás-os-Montes and Alto Douro (UTAD), 5000-801 Vila Real, PortugalINESC Technology and Science (INESC TEC), 4200-465 Porto, PortugalAutomating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed us to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection in images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70% and 86.5% with inference times of around 89 ms for an input size of 1280 × 1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.https://www.mdpi.com/1424-8220/24/21/6774deep learningprecision agriculturepruningrobotic systemsYOLO |
| spellingShingle | Francisco Oliveira Daniel Queirós da Silva Vítor Filipe Tatiana Martins Pinho Mário Cunha José Boaventura Cunha Filipe Neves dos Santos Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis Sensors deep learning precision agriculture pruning robotic systems YOLO |
| title | Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis |
| title_full | Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis |
| title_fullStr | Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis |
| title_full_unstemmed | Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis |
| title_short | Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis |
| title_sort | enhancing grapevine node detection to support pruning automation leveraging state of the art yolo detection models for 2d image analysis |
| topic | deep learning precision agriculture pruning robotic systems YOLO |
| url | https://www.mdpi.com/1424-8220/24/21/6774 |
| work_keys_str_mv | AT franciscooliveira enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT danielqueirosdasilva enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT vitorfilipe enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT tatianamartinspinho enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT mariocunha enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT joseboaventuracunha enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis AT filipenevesdossantos enhancinggrapevinenodedetectiontosupportpruningautomationleveragingstateoftheartyolodetectionmodelsfor2dimageanalysis |