Impact of Phenological and Lighting Conditions on Early Detection of Grapevine Inflorescences and Bunches Using Deep Learning
Open Access
- 11 July 2025
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 15 (14) , 1495
Abstract
Reliable early-stage yield forecasts are essential in precision viticulture, enabling timely interventions such as harvest planning, canopy management, and crop load regulation. Since grape yield is directly related to the number and size of bunches, the early detection of inflorescences and bunches, carried out even before flowering, provides a valuable foundation for estimating potential yield far in advance of veraison. Traditional yield prediction methods are labor-intensive, subjective, and often restricted to advanced phenological stages. This study presents a deep learning-based approach for detecting grapevine inflorescences and bunches during early development, assessing how phenological stage and illumination conditions influence detection performance using the YOLOv11 architecture under commercial field conditions. A total of 436 RGB images were collected across two phenological stages (pre-bloom and fruit-set), two lighting conditions (daylight and artificial night-time illumination), and six grapevine cultivars. All images were manually annotated following a consistent protocol, and models were trained using data augmentation to improve generalization. Five models were developed: four specific to each condition and one combining all scenarios. The results show that the fruit-set stage under daylight provided the best performance (F1 = 0.77, R2 = 0.97), while for inflorescences, night-time imaging yielded the most accurate results (F1 = 0.71, R2 = 0.76), confirming the benefits of artificial lighting in early stages. These findings define optimal scenarios for early-stage organ detection and support the integration of automated detection models into vineyard management systems. Future work will address scalability and robustness under diverse conditions.Keywords
Funding Information
- Universidad de La Rioja and the Gobierno de La Rioja (591/2021)
This publication has 46 references indexed in Scilit:
- Smart-Viticulture and Deep Learning: Challenges and Recent Developments on Yield Prediction2025
- Grapevine inflorescence segmentation and flower estimation based on Computer Vision techniques for early yield assessmentSmart Agricultural Technology, 2024
- Three-view cotton flower counting through multi-object tracking and RGB-D imageryBiosystems Engineering, 2024
- Improved YOLOv5 Network with Attention and Context for Small Object Detection2022
- Early yield prediction in different grapevine varieties using computer vision and machine learningPrecision Agriculture, 2022
- Deep learning and computer vision for assessing the number of actual berries in commercial vineyardsBiosystems Engineering, 2022
- A computer vision system for early stage grape yield estimation based on shoot detectionComputers and Electronics in Agriculture, 2017
- Automated Visual Yield Estimation in VineyardsJournal of Field Robotics, 2014
- Immature peach detection in colour images acquired in natural illumination conditions using statistical classifiers and neural networkPrecision Agriculture, 2013
- Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and VegetablesFood and Bioprocess Technology, 2010