EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions

Thi-Nguyen Nguyen, Manh-Tuan Do, Dinh-Thai Kim, Tuan-Minh Nguyen, Huyen-Trang Nguyen

EAI Endorsed Transactions on AI and Robotics · 27.07.2026 · 5

DOI: 10.4108/airo.12140 ↗

Kurz gefasst

Fachartikel in der Zeitschrift EAI Endorsed Transactions on AI and Robotics, online erschienen am 27.07.2026. Verfasst von Thi-Nguyen Nguyen und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate lychee growth-stage detection in natural orchards is challenging because blossoms and fruits are often small, densely clustered, partially occluded, and visually similar to surrounding foliage. This study proposes YOLO-Lychee, a YOLOv8s-based detector for four developmental stages: blossom, young fruit, green fruit, and ripe fruit. The dataset contains 1,145 original orchard images and 19,422 annotated instances collected in Hai Duong and Bac Giang provinces, Vietnam. To reduce blossom-class imbalance, exposure-based augmentation was applied only to blossom samples in the training subset, resulting in 1,324 images and 20,261 annotations, while the validation and test sets remained unchanged. YOLO-Lychee replaces the original SPPF module with a Spatial and Channel Cross-Transformer module, incorporates a Context Augmentation Module in the neck, and uses EIoU instead of the default CIoU loss for bounding-box regression. Across six random seeds, YOLO-Lychee achieved a Precision of 83.02 ± 2.38%, Recall of 82.19 ± 1.87%, mAP50 of 88.42 ± 0.38%, and mAP50:95 of 72.76 ± 0.45%. Compared with recent YOLO-family detectors under the same protocol, the proposed model obtained the highest mAP50 and competitive mAP50:95 while maintaining real-time inference. Ablation results confirm the complementary contributions of SC3T, CAM, and EIoU, whereas qualitative analysis shows that blossom detection remains the most challenging case. These results demonstrate that YOLO-Lychee is a practical empirical baseline for lychee growth-stage detection and vision-assisted orchard monitoring.

Zitieren

APA

Nguyen, T., Do, M., Kim, D., Nguyen, T., & Nguyen, H. (2026). YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions. EAI Endorsed Transactions on AI and Robotics, 5. https://doi.org/10.4108/airo.12140

Vancouver

Nguyen T, Do M, Kim D, Nguyen T, Nguyen H. YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions. EAI Endorsed Transactions on AI and Robotics. 2026;5. doi:10.4108/airo.12140

BibTeX
@article{Nguyen2026,
  author = {Nguyen, Thi-Nguyen and Do, Manh-Tuan and Kim, Dinh-Thai and Nguyen, Tuan-Minh and Nguyen, Huyen-Trang},
  title = {YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions},
  journal = {EAI Endorsed Transactions on AI and Robotics},
  year = {2026},
  volume = {5},
  doi = {10.4108/airo.12140}
}
Kostenlos starten →