数字农科院2.0

YOLOv8-MSP-PD: A Lightweight YOLOv8-Based Detection Method for Jinxiu Malus Fruit in Field Conditions

文献类型： 外文期刊

作者： Yi Liu;Xiang Han;Hongjian Zhang;Shuangxi Liu;Wei Ma;Yinfa Yan;Linlin Sun;Linlong Jing;Yongxian Wang;Jinxing Wang

作者机构：

关键词： Jinxiu Malus fruit;lightweight;multi-scale feature fusion;object detection;YOLOv8

期刊名称： Agronomy

ISSN： 2073-4395

年卷期： 2025 年 15 卷 7 期

页码：

收录情况： SCIE（2025版）

摘要： Accurate detection of Jinxiu Malus fruits in unstructured orchard environments is hampered by frequent overlap, occlusion, and variable illumination. To address these challenges, we propose YOLOv8-MSP-PD (YOLOv8 with Multi-Scale Pyramid Fusion and Proportional Distance IoU), a lightweight model built on an enhanced YOLOv8 architecture. We replace the backbone with MobileNetV4, incorporating unified inverted bottleneck (UIB) modules and depth-wise separable convolutions for efficient feature extraction. We introduce a spatial pyramid pooling fast cross-stage partial connections (SPPFCSPC) module for multi-scale feature fusion and a modified proportional distance IoU (MPD-IoU) loss to optimize bounding-box regression. Finally, layer-adaptive magnitude pruning (LAMP) combined with knowledge distillation compresses the model while retaining performance. On our custom Jinxiu Malus dataset, YOLOv8-MSP-PD achieves a mean average precision (mAP) of 92.2% (1.6% gain over baseline), reduces floating-point operations (FLOPs) by 59.9%, and shrinks to 2.2 MB. Five-fold cross-validation confirms stability, and comparisons with Faster R-CNN and SSD demonstrate superior accuracy and efficiency. This work offers a practical vision solution for agricultural robots and guidance for lightweight detection in precision agriculture.

分类号：

  • 相关文献

[1]Lightweight cotton diseases real-time detection model for resource-constrained devices in natural environments. Pan Pan,Mingyue Shao,Peitong He,Lin Hu,Sijian Zhao,Longyu Huang,Guomin Zhou,Jianhua Zhang. 2024

[2]Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm. Tao Sun,Longfei Cui,Lixuan Zong,Songchao Zhang,Yuxuan Jiao,Xinyu Xue,Yongkui Jin. 2024

[3]Small target tea bud detection based on improved YOLOv5 in complex background. Mengjie Wang,Yang Li,Hewei Meng,Zhiwei Chen,Zhiyong Gui,Yaping Li,Chunwang Dong. 2024

[4]Reb-DINO: A Lightweight Pedestrian Detection Model With Structural Re-Parameterization in Apple Orchard. Li, Ruiyang,Song, Ge,Wang, Shansong,Zeng, Qingtian,Yuan, Guiyuan,Ni, Weijian,Xie, Nengfu,Xiao, Fengjin. 2025

[5]A Lightweight and Rapid Dragon Fruit Detection Method for Harvesting Robots. Fei Yuan,Jinpeng Wang,Wenqin Ding,Song Mei,Chenzhe Fang,Sunan Chen,Hongping Zhou. 2025

[6]基于改进YOLOv8的自然环境下柑橘果实识别. 余圣新,韦莹莹,方辉,李敏,柴秀娟,曾志康,覃泽林. 2024

[7]基于改进YOLOv8模型的冬小麦穗识别技术. 宫志宏,闫锦涛,于红,刘涛,刘布春,李树岩. 2026

[8]基于改进实例分割算法的区域养殖生猪计数系统. 张岩琪,周硕,张凝,柴秀娟,孙坦. 2024

[9]Evaluating the Canopy Chlorophyll Density of Maize at the Whole Growth Stage Based on Multi-Scale UAV Image Feature Fusion and Machine Learning Methods. Lili Zhou,Chenwei Nie,Tao Su,Xiaobin Xu,Yang Song,Dameng Yin,Shuaibing Liu,Yadong Liu,Yi Bai,Xiao Jia,Xiuliang Jin. 2023

[10]End-to-end stereo matching network with two-stage partition filtering for full-resolution depth estimation and precise localization of kiwifruit for robotic harvesting. Xudong Jing,Hanhui Jiang,Shiao Niu,Haosen Zhang,Bryan Gilbert Murengami,Zhenchao Wu,Rui Li,Chengquan Zhou,Hongbao Ye,Jinyong Chen,Yaqoob Majeed,Longsheng Fu. 2024

[11]GVC-YOLO: A Lightweight Real-Time Detection Method for Cotton Aphid-Damaged Leaves Based on Edge Computing. Zhenyu Zhang,Yunfan Yang,Xin Xu,Liangliang Liu,Jibo Yue,Ruifeng Ding,Yanhui Lu,Jie Liu,Hongbo Qiao. 2024

[12]ACCURATE NON-DESTRUCTIVE TESTING METHOD FOR POTATO SPROUTS FOCUSING ON DEFORMABLE ATTENTION. Geng, Binxuan,Dai, Guowei,Zhang, Huan,Qi, Shengchun,Dewi, Christine. 2024

[13]Xoo-YOLO: a detection method for wild rice bacterial blight in the field from the perspective of unmanned aerial vehicles. Pan Pan,Wenlong Guo,Xiaoming Zheng,Lin Hu,Guomin Zhou,Jianhua Zhang. 2023

[14]A Method of Grape Cluster Target Detection and Picking Point Location Based on Improved YOLOv8. Liu, Huaiyang,Liu, Wanfu,Wang, Wenhao,Li, Huibin,Geng, Changxing. 2025

[15]Field Obstacle Detection and Location Method Based on Binocular Vision. Yuanyuan Zhang,Kunpeng Tian,Jicheng Huang,Zhenlong Wang,Bin Zhang,Qing Xie. 2024

[16]FEL-YoloV8: A New Algorithm for Accurate Monitoring Soybean Seedling Emergence Rates and Growth Uniformity. Yu, Xun,Jiang, Tiantian,Zhu, Yanqin,Li, Liming,Fan, Fan,Jin, Xiuliang. 2025

[17]B-FLACS: blockchain-based flexible lightweight access control scheme for data sharing in cloud. Tao, Qi,Cui, Xiaohui. 2022

[18]Lightweight Fruit-Detection Algorithm for Edge Computing Applications. Wenli Zhang,Yuxin Liu,Kaizhen Chen,Huibin Li,Yulin Duan,Wenbin Wu,Yun Shi,Wei Guo. 2021

[19]A lightweight tea bud detection model based on Yolov5. Gui, Zhiyong,Chen, Jianneng,Li, Yang,Chen, Zhiwei,Wu, Chuanyu,Dong, Chunwang. 2023

[20]A Non-Destructive Method for Identification of Tea Plant Cultivars Based on Deep Learning. Yi Ding,Haitao Huang,Hongchun Cui,Xinchao Wang,Yun Zhao. 2023

作者其他论文 更多>>