智能化农业装备学报（中英文）

基于改进YOLOv8n的苹果采摘机器人识别算法研究

预览PDF | 下载PDF

门晓龙 ¹^,²^,³ , 何义川 ¹^,²^,³^,^*^,^* , 汤智辉 ²^,³ , 刘湛 ¹^,² , 潘思祺 ¹^,³ , 姚欢杰 ⁴

智能化农业装备学报（中英文） | 2026,7(1): 52-62

收起

智能化农业装备学报（中英文） | 2026 , 7 (1) : 52 -62

基于改进YOLOv8n的苹果采摘机器人识别算法研究

全屏

门晓龙¹^,²^,³, 何义川¹^,²^,³^,^*^,^*, 汤智辉²^,³, 刘湛¹^,², 潘思祺¹^,³, 姚欢杰⁴

作者信息

^1.塔里木大学机械电气化工程学院，新疆阿拉尔，843300

^2.南疆特色农林产物利用与装备兵团重点实验室，新疆阿拉尔，843300

^3.新疆维吾尔自治区教育厅普通高等学校现代农业工程重点实验室，新疆阿拉尔，843300

^4.阿拉尔市疆田果将香梨种植农民专业合作社，新疆阿拉尔，843300

通讯作者:

^* 何义川，男，1984年生，甘肃秦安人，硕士，教授，博导；研究方向为南疆智能农业机械装备。E-mail：hyc2003@163.com

作者简介:

门晓龙，男，1995年生，内蒙古呼和浩特人，硕士研究生；研究方向为南疆智能农业机械装备。E-mail：2879955207@qq.com

Research on apple picking robot recognition algorithm based on improved YOLOv8n

Xiaolong MEN¹^,²^,³, Yichuan HE¹^,²^,³, Zhihui TANG²^,³, Zhan LIU¹^,², Siqi PAN¹^,³, Huanjie YAO⁴

Affiliations

^1.College of Mechanical and Electrical Engineering, Tarim University, Alar 843300, China

^2.Xinjiang Production and Construction Corps (XPCC) Key Laboratory of Utilization and Equipment of Special Agricultural and Forestry Products in Southern Xinjiang, Alar 843300, China

^3.Modern Agricultural Engineering Key Laboratory at Universities of Education Department of Xinjiang Uygur Autonomous Region, Alar 843300, China

^4.The Farmers' Professional Cooperative of Jiangtian guojiang of Alar City for Fragrant Pear Planting, Alar 843300, China

Corresponding Author:

^* HE Yichuan, E-mail: hyc2003@163.com

MEN Xiaolong, E-mail: 2879955207@qq.com

出版时间: 2026-02-15 doi: 10.12398/j.issn.2096-7217.2026.01.006

文章导航

摘要

收起

针对果园内枝叶遮挡、光照不均等复杂环境因素导致采摘机器人对苹果的检测精度低、鲁棒性差等问题。研究提出一种改进YOLOv8n网络轻量化模型的苹果检测算法，旨在提升复杂场景下果实检测的准确性与可靠性。首先，在主干网络末端加入多尺度位置注意力机制（multi-scale position-channel attention，MPCA），通过对不同尺度下苹果位置信息的精准捕捉，增强模型对目标位置特征的感知能力，有效降低复杂果园环境对检测结果的干扰；其次，在颈部网络中引入“FocusFeature”特征融合模块，借助多尺度深度可分离卷积实现信息融合与特征增强，提升模型的检测能力。最后，将损失函数CIoU替换为WIoUv3，依据预测框与真实框的匹配质量，动态调整样本在损失计算中的权重，有效提升了模型的定位精度。试验表明，改进模型在复杂果园环境下精确率达92.2%、召回率86.4%，mAP@0.5与mAP@[0.5：0.95]分别为94.4%、72.4%，相较原始算法提升3.4%、6%、3.9%、2.8%。消融试验显示，WIoUv3、MPCA、FocusFeature特征融合模块分别使mAP@0.5提升0.3%、0.9%、1.1%，多模块协同实现性能叠加。模型大小为6.69 MB，较原始模型仅增加0.74 MB，未显著增加计算负载。与YOLOv5n、YOLOv7-tiny、YOLOv11n等主流算法相比，改进模型在精确率上分别提高3.9%、7.6%、5.7%，mAP@[0.5：0.95]指标分别提升2.5%、9.9%、13%，在检测精度与泛化能力方面展现出显著优势。可见，提出的改进YOLOv8n算法通过多模块协同作用，显著提升了复杂果园环境下苹果检测的精度与鲁棒性，为采摘机器人的实际应用提供了有效技术方案，对推动苹果采收智能化发展具有重要意义。

关键词

YOLOv8n / 采摘机器人 / 目标检测 / 轻量化 / 模型改进 / 复杂果园环境

Abstract

收起

To address the issues of low detection accuracy and poor robustness of apple picking robots caused by complex environmental factors such as branch and leaf occlusion and uneven light distribution in orchards, this study proposes an apple fruit detection algorithm that improves the lightweight model of the YOLOv8n network, aiming to enhance the accuracy and reliability of apple detection in complex scenarios. Firstly, an “MPCA” (multi-scale position-channel attention) is added at the end of the backbone network to precisely capture the position information of apples at different scales, thereby enhancing the model's perception of target position features and effectively reducing the interference of complex orchard environments on detection results. Secondly, a “FocusFeature” feature fusion module is introduced in the neck network, which uses multi-scale depth wise separable convolution to achieve information fusion and feature enhancement, improving the model's detection capability. Finally, the loss function CIoU is replaced with WIoUv3 (WiseIoU), dynamically adjusting the weight of samples in the loss calculation based on the matching quality of predicted and ground truth boxes, effectively enhancing the model's localization accuracy. Experiments show that the improved model achieves an accuracy of 92.2%, a recall rate of 86.4%, and mAP@0.5 and mAP@[0.5: 0.95] of 94.4% and 72.4% respectively in complex orchard environments, representing improvements of 3.4%, 6%, 3.9%, and 2.8% compared to the original algorithm. Ablation experiments reveal that WIoUv3, MPCA, and FocusFeature feature fusion module increase mAP@0.5 by 0.3%, 0.9%, and 1.1% respectively, with performance enhancement achieved through the synergy of multiple modules. The model size is 6.69 MB, only 0.74 MB larger thanthe original model, without significantly increasing the computational load. Compared with mainstream algorithms such as YOLOv5n, YOLOv7-tiny, and YOLOv11n, the improved model increases the accuracy by 3.9%, 7.6%, and 5.7% respectively, and mAP@[0.5: 0.95] by 2.5%, 9.9%, and 13%, demonstrating significant advantages in detection accuracy and generalization ability. It is evident that the improved YOLOv8n algorithm proposed in this study significantly enhances the accuracy and robustness of apple detection in complex orchard environments through the collaborative effect of multiple modules, providing an effective technical solution for the practical application of picking robots and playing a crucial role in promoting the intelligent development of apple harvesting.

Key words

YOLOv8n / picking robot / object detection / lightweight / model improvement / complex orchard environment

引用本文

门晓龙, 何义川, 汤智辉, 刘湛, 潘思祺, 姚欢杰. 基于改进YOLOv8n的苹果采摘机器人识别算法研究. 智能化农业装备学报（中英文）, 2026 , 7 (1) : 52 -62 . DOI: 10.12398/j.issn.2096-7217.2026.01.006

Xiaolong MEN, Yichuan HE, Zhihui TANG, Zhan LIU, Siqi PAN, Huanjie YAO. Research on apple picking robot recognition algorithm based on improved YOLOv8n[J]. Journal of Intelligent Agricultural Mechanization, 2026 , 7 (1) : 52 -62 . DOI: 10.12398/j.issn.2096-7217.2026.01.006

基金

收起

新疆生产建设兵团科技计划(2024BA005)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

张静，张昊，聂尚卿，等．基于改进YOLOv8的苹果采摘机器人视觉算法[J]．液压气动与密封，2025，45（3）：36-43.

ZHANG Jing, ZHANG Hao, NIE Shangqing, et al. Vision algorithm for apple picking robot based on improved YOLOv8 [J]. Hydraulics Pneumatics & Seals, 2025, 45(3): 36-43.

[2]

ZHANG Y, LI N, ZHANG L, et al. Parallel depthwise separable multiscale information aggregation network for real-time fruit detection in trellis apple orchard [J]. Computers and Electronics in Agriculture, 2025, 237: 110503.

[3]

ZHAO Z, HICKS Y, SUN X, et al. A novel self-supervised method for in-field occluded apple ripeness determination [J]. Computers and Electronics in Agriculture, 2025, 234: 110246.

[4]

程浈浈，程一帆，缪百灵，等．基于YOLOv3的不同场景下苹果目标检测方法[J]．北方园艺，2024（22）：137-146.

CHENG Zhenzhen, CHENG Yifan, MIAO Bailing, et al. Apple target detection method in different scenarios based on YOLOv3 [J]. Northern Horticulture, 2024 (22): 137-146.

[5]

武星，齐泽宇，王龙军，等．基于轻量化YOLOv3卷积神经网络的苹果检测方法[J]．农业机械学报，2020，51（8）：17-25.

WU Xing, QI Zeyu, WANG Longjun, et al. Apple detection method based on Light-YOLOv3 convolutional neural network [J] Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(8): 17-25.

[6]

岳琳茜，李文宽，杨晓峰，等．基于改进YOLOv4的苹果检测与果径估测方法[J]．激光杂志，2022，43（2）：58-65.

YUE Linxi, LI Wenkuan, YANG Xiaofeng, et al. Apple detection and fruit diameter estimation method based onimproved YOLOv4 [J]. Laser Journal, 2022, 43(2): 58-65.

[7]

周桂红，马帅，梁芳芳．基于改进YOLOv4模型的全景图像苹果识别[J]．农业工程学报，2022，38（21）：159-168.

ZHOU Guihong, MA Shuai, LIANG Fangfang. Recognition of the apple in panoramic images based on improved YOLOv4 model [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (21): 159-168.

[8]

刘子龙，张磊．自然环境下改进YOLOv5对小目标苹果的检测[J]．系统仿真学报，2025，37（8）：2124-2138.

LIU Zilong, ZHANG Lei. Detection of small apple targets based on improved YOLOv5 in natural environments [J]. Journal of System Simulation, 2025, 37(8): 2124-2138.

[9]

龙燕，杨智优，何梦菲．基于改进YOLOv7的疏果期苹果目标检测方法[J]．农业工程学报，2023，39（14）：191-199.

LONG Yan, YANG Zhiyou, HE Mengfei. Recognizing apple targets before thinning using improved YOLOv7 [J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(14): 191-199.

[10]

陈青，殷程凯，郭自良，等．基于改进YOLOv7的苹果生长状态及姿态识别[J]．农业工程学报，2024，40（6）：258-266.

CHEN Qing, YIN Chengkai, GUO Ziliang, et al. Apple growth status and posture recognition using improved YOLOv7 [J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(6): 258-266.

[11]

JRONDI Z, MOUSSAID A, HADI M Y. Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees [J]. Systems and Soft Computing, 2024, 6: 200103.

[12]

赵树恩，龚道元，田卓帅．基于改进YOLOv8模型的复杂交通场景目标检测算法[J]．重庆交通大学学报（自然科学版），2025，44（12）：33-41.

ZHAO Shuen, GONG Daoyuan, TIAN Zhuoshuai. Algorithm for object detection in complex traffic scenes based on improved YOLOv8 model [J]. Journal of Chongqing Jiaotong University (Natural Science), 2025, 44(12): 33-41.

[13]

宋奇恒，吴双，黄及远，等．基于YOLOv8改进算法的船体合拢焊缝外观缺陷检测系统设计[J]．制造业自动化，2025，47（5）：118-124.

SONG Qiheng, WU Shuang, HUANG Jiyuan, et al. Design of an appearance defect detection system for hull butt welds based on an improved YOLOv8 algorithm [J]. Manufacturing Automation, 2025, 47(5): 118-124.

[14]

JIA X, HUA Z, SHI H, et al. A soybean pod accuracy detection and counting model based on improved YOLOv8[J]. Agriculture, 2025, 15(6): 617.

[15]

DEWI C, MANONGGA D, HENDRY, et al. Deep learning and YOLOv8 utilized in an accurate face mask detection system [J]. Big Data and Cognitive Computing, 2024, 8(1): 9.

[16]

罗友璐，潘勇浩，夏顺兴，等．基于改进YOLOv8的苹果叶病害轻量化检测算法[J]．智慧农业（中英文），2024，6（5）：128-138.

LUO Youlu, PAN Yonghao, XIA Shunxing, et al. Lightweight apple leaf disease detection algorithm based on improved YOLOv8 [J] Smart Agriculture, 2024, 6(5): 128-138.

[17]

魏堂伟，张津诚，王晶，等．基于改进YOLOv7的茶叶嫩芽识别模型研究[J]．智能化农业装备学报（中英文），2024，5（2）：42-50.

WEI Tangwei, ZHANG Jincheng, WANG Jing, et al. Study of tea buds recognition and detection based on improved YOLOv7 model [J]. Journal of Intelligent Agricultural Mechanization, 2024, 5(2): 42-50.

[18]

蔡家一，刘世伟，单龙祥，等．基于机器视觉与YOLO v5的裂纹蛋分拣机器人设计与试验[J]．智能化农业装备学报（中英文），2025，6（1）：41-50.

CAI Jiayi, LIU Shiwei, SHAN Longxiang, et al. Design and experiment of cracked egg sorting robot based on machine vision and YOLO v5 [J]. Journal of Intelligent Agricultural Mechanization, 2025, 6(1): 41-50.

[19]

SUN Y, ZHANG D, GUO X, et al. Lightweight algorithm for apple detection based on an improved YOLOv5 model [J]. Plants, 2023, 12(17): 3032.

[20]

王鑫．苹果采摘末端执行器结构设计与柔顺控制研究[D]．杨凌：西北农林科技大学，2023.

WANG Xin. Research on structural design and compliancecontrol of apple picking end-effector [D]. Yangling: Northwest A&F University, 2023.

[21]

ZHANG X, LI D, LIU X, et al. Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM [J]. Frontiers in Plant Science, 2023, 14: 1175027.

[22]

WANG H, JU X, ZHU H, et al. SEFormer: A lightweight CNN-Transformer based on separable multiscale depthwise convolution and efficient self-attention for rotating machinery fault diagnosis [J]. Computers, Materials & Continua, 2025, 82(1).

[23]

JIANG L, JIN Q, HUA F, et al. Numerical investigation of the effective receptive field and its relationship with convolutional kernels and layers in convolutional neural network [J]. Frontiers in Marine Science, 2024, 11: 1492572.

[24]

周子渊，成苗，何莲，等．基于改进YOLOv8的小目标与细长目标检测模型[J]．计算机应用，2024，44（S2）：286-295.

ZHOU Ziyuan, CHENG Miao, HE Lian, et al. Small and elongated object detection model based on improved YOLOv8 [J]. Journal of Computer Applications, 2024, 44(S2): 286-295.

[25]

YU Q, HAN Y, HAN Y, et al. Enhancing YOLOv5 performance for small-scale corrosion detection in coastal environments using IoU-Based loss functions [J]. Journal of Marine Science and Engineering, 2024, 12(12): 2295.

[26]

CHEN X, JIAO Z, LIU Y. Improved YOLOv8n based helmet wearing inspection method [J]. Scientific Reports, 2025, 15(1): 1945.

[27]

郝博，徐新岩，赵玉欣，等．基于改进YOLOv8的铆接孔表面缺陷检测[J]．东北大学学报（自然科学版），2024，45（11）：1595-1603.

HAO Bo, XU Xinyan, ZHAO Yuxin, et al. Surface defect detection of riveting holes based on improved YOLOv8 [J]. Journal of Northeastern University (Natural Science), 2024, 45(11): 1595-1603.

[28]

李小祥，张洁，秦柯贝，等．基于改进YOLOv8的轻量级复杂环境苹果叶片病害检测方法[J]．南京农业大学学报，2025，48（3）：734-743.

LI Xiaoxiang, ZHANG Jie, QIN Kebei, et al. A lightweight method for apple leaf disease detection in complex environments based on improved YOLOv8 [J]. Journal of Nanjing Agricultural University, 2025, 48(3): 734-743.

[29]

李书贤．基于多传感器阵列的水果分类及新鲜度检测方法研究[D]．天津：天津职业技术师范大学，2024.

LI Shuxian. Research on fruit classification and freshness detection method based on multi-sensor array [D]. Tianjin: Tianjin University of Technology and Education, 2024.

2026年第7卷第1期

预览PDF | 下载PDF

引用本文

BibTeX

文章信息

doi: 10.12398/j.issn.2096-7217.2026.01.006

接收时间：2025-10-17
首发时间：2026-11-03
出版时间：2026-02-15

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2025-10-17
修回日期：2025-12-15

基金

Science and Technology Program of Xinjiang Production and Construction Corps (XPCC)(2024BA005)

新疆生产建设兵团科技计划(2024BA005)

作者信息

^1.塔里木大学机械电气化工程学院，新疆阿拉尔，843300

^2.南疆特色农林产物利用与装备兵团重点实验室，新疆阿拉尔，843300

^3.新疆维吾尔自治区教育厅普通高等学校现代农业工程重点实验室，新疆阿拉尔，843300

^4.阿拉尔市疆田果将香梨种植农民专业合作社，新疆阿拉尔，843300

通讯作者:

^* 何义川，男，1984年生，甘肃秦安人，硕士，教授，博导；研究方向为南疆智能农业机械装备。E-mail：hyc2003@163.com

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/znhnyzbxb/CN/10.12398/j.issn.2096-7217.2026.01.006

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT