李添恒,丛佩超,胥羽涛,梁吉,王昆

• 1:广西科技大学机械与汽车工程学院

摘要(Abstract)：

荔枝果实的准确识别与采摘是实现其机械化采摘的关键。由于荔枝体积小、生长密集，传统目标检测算法难以对荔枝果实进行高效识别。本文基于YOLOv8模型提出了YOLOv8-SC算法，通过将Swin Transformer引入主干网络，以提升小目标检测性能；设计共享参数检测头，替代原解耦头，以实现模型轻量化。此外，利用基于密度空间的数据聚类算法（density-based spatial clustering of applications with noise, DBSCAN）对荔枝生长形态进行划分，为采摘策略提供指导。实验结果表明，YOLOv8-SC在复杂场景下表现优异：精确率、召回率、F1分数、平均精度m AP@0.5和mAP@0.5:0.95分别达到88.5%、76.3%、0.819、82.1%和58.2%，模型帧率提高至119帧/s，在Jetson Xavier NX上的实时帧率（FPS）提升至26帧/s，性能显著优化。在广东廉江荔枝园的实地测试中，DBSCAN算法表现出良好的目标聚类效果，为采摘规划提供了可靠依据。

关键词(KeyWords)： 荔枝采摘;YOLOv8;DBSCAN;小目标检测;模型轻量化

Abstract:

Keywords:

基金项目(Foundation): 中央引导地方科技发展专项资金项目（桂科ZY19183003）;; 广西重点研发计划项目（桂科AB20058001）资助

作者(Author): 李添恒,丛佩超,胥羽涛,梁吉,王昆

DOI: 10.16375/j.cnki.cn45-1395/t.2026.03.002

参考文献(References)：

• [1]LI H,HUANG D J,MA Q Z,et al. Factors influencing the technology adoption behaviours of litchi farmers in China[J]. Sustainability,2020,12(1):271.
• [2]JIAO Z Y,HUANG K,JIA G Z,et al. An effective litchi detection method based on edge devices in a complex scene[J]. Biosystems Engineering,2022,222:15-28.
• [3]BU L X,CHEN C K,HU G R,et al. Design and evaluation of a robotic apple harvester using optimized picking patterns[J]. Computers and Electronics in Agriculture,2022,198:107092.
• [4]MU L T,CUI G P,LIU Y D,et al. Design and simulation of an integrated end-effector for picking kiwifruit by robot[J]. Information Processing in Agriculture,2020,7(1):58-71.
• [5]SHI Y G,JIN S T,ZHAO Y M,et al.Lightweight forcesensing tomato picking robotic arm with a“global-local”visual servo[J].Computers and Electronics in Agriculture,2023,204:107549.
• [6]李善达，王虎奇，丛佩超，等. Dense-YOLO：一种用于监测复杂场景灰飞虱虫害的检测算法[J].广西科技大学学报，2024,36(3):32-34.
• [7]吴静，王智文，王康权，等.基于改进CRNN算法的电动自行车车牌识别研究[J].广西科技大学学报，2022,33(4):63-69.
• [8]ZHAO S Y,LIU J Z,WU S. Multiple disease detection method for greenhouse-cultivated strawberry based on multiscale feature fusion Faster R-CNN[J]. Computers and Electronics in Agriculture,2022,199:107176.
• [9]HE K M,GKIOXARI G,DOLL??R P,et al. Mask RCNN[C]//2017 IEEE International Conference on Computer Vision(ICCV). October 22-29,2017,Venice,Italy. IEEE,2017:2980-2988.
• [10]CONG P C,LI S D,ZHOU J C,et al. Research on instance segmentation algorithm of greenhouse sweet pepper detection based on improved mask RCNN[J]. Agronomy,2023,13(1):196.
• [11]WANG L L,ZHAO Y J,XIONG Z J,et al. Fast and precise detection of litchi fruits for yield estimation based on the improved YOLOv5 model[J]. Frontiers in Plant Science,2022,13:965425.
• [12]LI C,LIN J Q,LI Z,et al. An efficient detection method for litchi fruits in a natural environment based on improved YOLOv7-litchi[J]. Computers and Electronics in Agriculture,2024,217:108605.
• [13]TANG Y C,CHEN M Y,WANG C L,et al. Recognition and localization methods for vision-based fruit picking robots:a review[J]. Frontiers in Plant Science,2020,11:510.
• [14]LIU Z,LIN Y T,CAO Y,et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV). October 10-17,2021,Montreal,QC,Canada. IEEE,2021:9992-10002.
• [15]QIU M L,HUANG L,TANG B H. Bridge detection method for HSRRSIs based on YOLOv5 with a decoupled head[J]. International Journal of Digital Earth,2023,16(1):113-129.
• [16]SCHUBERT E,SANDER J,ESTER M,et al. DBSCAN revisited,revisited:why and how you should(still)use DBSCAN[J]. ACM Transactions on Database Systems,2017,42(3):1-21.

文章评论(Comment)：

序号(No.) 时间(Time) 反馈人(User) 邮箱(Email) 标题(Title) 内容(Content)

反馈人(User) 邮箱地址(Email) 反馈标题(Title) 反馈内容(Content)