Next Article in Journal
Plant Growth Regulators Improve Soybean Yield in Northwest China Through Nutritional and Hormonal Regulation
Previous Article in Journal
Net-Zero Emissions for Sustainable Food Production and Land Management
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Optimization of Litchi Fruit Detection Based on Defoliation and UAV

1
Key Laboratory of South Subtropical Fruit Biology and Genetic Resource Utilization, Guangdong Provincial Key Laboratory of Science and Technology Research on Fruit Trees, Institute of Fruit Tree Research, Guangdong Academy of Agricultural Sciences, Ministry of Agriculture and Rural Affairs, Guangzhou 510640, China
2
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
3
Institute of Agricultural Machinery, Chinese Academy of Tropical Agricultural Sciences, Zhanjiang 524013, China
4
College of Horticulture, South China Agricultural University, Guangzhou 510642, China
*
Authors to whom correspondence should be addressed.
Agronomy 2025, 15(10), 2421; https://doi.org/10.3390/agronomy15102421
Submission received: 14 August 2025 / Revised: 22 September 2025 / Accepted: 1 October 2025 / Published: 19 October 2025
(This article belongs to the Section Precision and Digital Agriculture)

Abstract

The use of UAVs to detect litchi in natural environments is imperative for rapid litchi yield estimation and automated harvesting systems. However, UAV-based lychee fruit detection bottlenecks arise from complex canopy architecture and leaf occlusion. This study proposed a collaborative optimization strategy integrating agronomic technique with deep learning. Three leaf thinning intensities (0, 6, and 12 compound leaves) were applied at the early stage of fruit to systematically evaluate their effects on fruit growth, canopy structure, and detection performance. Results indicated that moderate defoliation (six leaves) significantly enhanced canopy openness and light penetration without adversely impacting on yield and fruit quality. Subsequent UAV-based detection under moderate versus no defoliation treatment revealed that the YOLOv8-based model achieved significant performance gains: mean average precision (mAP) increased from 0.818 to 0.884, and the F1-score improved from 0.796 to 0.842. The study contributes a novel collaborative optimization strategy that effectively mitigates occlusion issues in fruit detection. This approach demonstrates that agronomic techniques can be strategically used to enhance AI perception, offering a significant step forward in the integration of agricultural machinery and agronomy for intelligent orchard systems.
Keywords: Litchi; fruit detection; defoliation; UAV; YOLOv8 Litchi; fruit detection; defoliation; UAV; YOLOv8

Share and Cite

MDPI and ACS Style

Wang, J.; Zhang, M.; Zheng, Z.; Yao, Z.; Nie, B.; Guo, D.; Chen, L.; Li, J.; Xiong, J. Optimization of Litchi Fruit Detection Based on Defoliation and UAV. Agronomy 2025, 15, 2421. https://doi.org/10.3390/agronomy15102421

AMA Style

Wang J, Zhang M, Zheng Z, Yao Z, Nie B, Guo D, Chen L, Li J, Xiong J. Optimization of Litchi Fruit Detection Based on Defoliation and UAV. Agronomy. 2025; 15(10):2421. https://doi.org/10.3390/agronomy15102421

Chicago/Turabian Style

Wang, Jing, Mingyue Zhang, Zhenhui Zheng, Zhaoshen Yao, Boxuan Nie, Dongliang Guo, Ling Chen, Jianguang Li, and Juntao Xiong. 2025. "Optimization of Litchi Fruit Detection Based on Defoliation and UAV" Agronomy 15, no. 10: 2421. https://doi.org/10.3390/agronomy15102421

APA Style

Wang, J., Zhang, M., Zheng, Z., Yao, Z., Nie, B., Guo, D., Chen, L., Li, J., & Xiong, J. (2025). Optimization of Litchi Fruit Detection Based on Defoliation and UAV. Agronomy, 15(10), 2421. https://doi.org/10.3390/agronomy15102421

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop