[1]刘洋,毛典辉,徐忠涛,等.基于FDP-YOLO的复杂环境下苹果蛾虫害检测方法[J].江苏农业学报,2026,42(08):1542-1553.[doi:doi:10.3969/j.issn.1000-4440.2026.08.004]
　LIU Yang,MAO Dianhui,XU Zhongtao,et al.Detection method of apple moth pest in complex environments based on FDP-YOLO[J].,2026,42(08):1542-1553.[doi:doi:10.3969/j.issn.1000-4440.2026.08.004]
点击复制

基于FDP-YOLO的复杂环境下苹果蛾虫害检测方法()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2026年08期
页码:
1542-1553
栏目:
植物保护
出版日期:
2026-08-31

文章信息/Info

Title:
Detection method of apple moth pest in complex environments based on FDP-YOLO
作者:
刘洋1; 毛典辉1; 2; 徐忠涛1; 马华宜1; 吴建伟3; 4
(1.北京工商大学计算机与人工智能学院,北京100048；2.北京工商大学食品安全大数据技术北京市重点实验室,北京100048；3.北京市农林科学院信息技术研究中心,北京100097；4.北京派得伟业科技发展有限公司,北京100097)
Author(s):
LIU Yang1; MAO Dianhui1; 2; XU Zhongtao1; MA Huayi1; WU Jianwei3; 4
(1.School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048,China;2.Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Beijing 100048,China;3.Research Center of Information Technology,Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097,China;4.Beijing PAIDE Science and Technology Development Co. Ltd., Beijing 100097, China)
关键词:
苹果; 蛾虫害; 复杂环境; 目标检测; YOLOv8
Keywords:
apple; moth pest; complex environments; target detection; YOLOv8
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2026.08.004
文献标志码:
A
摘要:
复杂环境下的苹果蛾虫害检测面临着多重挑战:小目标尺寸导致特征信息稀少、严重遮挡造成目标不完整、光照条件多变引起图像质量差异大,以及实际部署对模型轻量化的严格要求。针对这些复杂环境因素带来的难题,本研究提出了轻量级高精度目标检测模型(FDP-YOLO)。首先,在主干网络部分设计细粒度通道注意力跨阶段融合机制,通过全局与局部特征交互增强小目标在复杂光照条件下的特征表达能力；其次,在颈部网络部分引入基于混合专家思想的动态卷积方法,在保持轻量化的同时提升复杂场景下的特征融合效果；最后,在头部网络部分利用PIoU损失函数,专门优化遮挡严重等复杂情况下的困难样本回归性能。研究结果表明,FDP-YOLO相比基线模型YOLOv8n,准确率提升了2.9个百分点,召回率提升了1.5个百分点,mAP50(交并比阈值为0.5时的平均精度均值)提升了1.7个百分点,同时维持轻量化特性；此外,FDP-YOLO的mAP50显著优于YOLOv10n和RT-DETR-R50,充分验证了模型在复杂环境下对小目标检测、遮挡处理、光照差异大等方面的技术优势,为农业复杂环境下的虫害智能监测提供了有效的技术解决方案。
Abstract:
There are many difficulties in detecting apple moth pests in complex environments: the small size of the targets leads to a lack of features, severe occlusion of pests causes incomplete targets, and variable lighting affects imaging quality. At the same time, practical deployment has high requirements for model lightweight. To address the above issues, this study proposed a lightweight high-precision object detection model, FDP-YOLO. Firstly, a fine-grained channel attention cross-stage fusion mechanism was designed in the backbone network to enhance the feature expression ability of small targets under complex lighting conditions through the interaction of global and local features. Secondly, a dynamic convolution method based on the idea of hybrid experts was introduced in the neck network to improve the feature fusion effect in complex scenes under the premise of maintaining lightweight. Finally, the PIoU loss function was adopted in the detection head to optimize the regression performance of difficult samples under complex conditions such as severe occlusion. Experimental results show that FDP-YOLO maintained lightweight characteristics while the detection accuracy improved by 2.9 percentage points, the recall improved by 1.5 percentage points, and the mAP0.5(mean average precision at an intersection over union threshold of 0.5) improved by 1.7 percentage points compared to the baseline model YOLOv8n. Its mAP50 was significantly better than models such as YOLOv10n and RT-DETR-R50, effectively validated the technical advantages in detection performance of small targets, occluded targets, and variable lighting scenes in complex environments. It can provide technical support for intelligent monitoring of pests in complex agricultural scenes.

参考文献/References:

[1]Damos P, Colomar L E, Ioriatti C. Integrated fruit production and pest management in Europe:the apple case study and how far we are from the original concept?[J]. Insects,2015,6(3):626-657.
[2]Ju D, Mota-Sanchez D, Fuentes-Contreras E, et al. Insecticide resistance in the Cydia pomonella (L.):global status,mechanisms,and research directions[J]. Pesticide Biochemistry and Physiology,2021,178:104925.
[3]Whitfield E C, Fountain M T. Future semiochemical control of codling moth,Cydia pomonella[J]. Frontiers in Horticulture,2024,3:1446806.
[4]Shaw B, Nagy C, Fountain M T. Organic control strategies for use in IPM of invertebrate pests in apple and pear orchards[J]. Insects,2021,12(12):1106.
[5]Valiukaité A, Uselis N, Kviklys D, et al. The effect of sustainable plant protection and apple tree management on fruit quality and yield[J]. Zemdirbyste-Agriculture,2017,104(4):353-358.
[6]Albanese A, nardello M, Brunelli D. Automated pest detection with DNN on the edge for precision agriculture[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2021,11(3):458-467.
[7]Alam A, Abbas S, Abbas A, et al. Emerging trends in insect sex pheromones and traps for sustainable management of key agricultural pests in Asia:beyond insecticides:a comprehensive review[J]. International Journal of Tropical Insect Science,2023,43(6):1867-1882.
[8]Wu J X, Zhang Y, Hu P F, et al. A review of the application of hyperspectral imaging technology in agricultural crop economics[J]. Coatings,2024,14(10):1285.
[9]Van Klink R, August T, Bas Y, et al. Emerging technologies revolutionise insect ecology and monitoring[J]. Trends in Ecology & Evolution,2022,37(10):872-885.
[10]Chen Y C, Wang J C, Lee M H, et al. Enhanced detection of mango leaf diseases in field environments using MSMP-CNN and transfer learning[J]. Computers and Electronics in Agriculture,2024,227:109636.
[11]Meng K X, Xu K X, Cattani P, et al. Camouflaged cotton bollworm instance segmentation based on PVT and Mask R-CNN[J]. Computers and Electronics in Agriculture,2024,226:109450.
[12]Ren S Q, He K M, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence. June 6,2016,Montreal,Canada:IEEE,2016.
[13]Redmon J, Divvala S, Girshick R, et al. You only look once:unified,real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. June 27-30,2016,Las Vegas,NV,USA:IEEE,2016.
[14]Zhang Y J, Ma B X, Hu Y T, et al. Accurate cotton diseases and pests detection in complex background based on an improved YOLOX model[J]. Computers and Electronics in Agriculture,2022,203:107484.
[15]Tian Y N, Wang S H, Li E, et al. MD-YOLO:multi-scale dense YOLO for small target pest detection[J]. Computers and Electronics in Agriculture,2023,213:108233.
[16]Xu W Y, Xu T, Thomasson J A, et al. A lightweight SSV2-YOLO based model for detection of sugarcane aphids in unstructured natural environments[J]. Computers and Electronics in Agriculture,2023,211:107961.
[17]Li K S, Wang J C, Jalil H, et al. A fast and lightweight detection algorithm for passion fruit pests based on improved YOLOv5[J]. Computers and Electronics in Agriculture,2023,204:107534.
[18]Zhu L Q, Li X M, Sun H M, et al. Research on CBF-YOLO detection model for common soybean pests in complex environment[J]. Computers and Electronics in Agriculture,2024,216:108515.
[19]Sun H, Wen Y, Feng H J, et al. Unsupervised bidirectional contrastive reconstruction and adaptive fine-grained channel attention networks for image dehazing[J]. Neural Networks,2024,176:106314.
[20]Han K, Wang Y H, Guo J Y, et al. ParameterNet: parameters are all you need[EB/OL]. （2024-01-14）
[2025-09-01]. https://arxiv.org/abs/2306.14525.
[21]Liu C, Wang K G, Li Q, et al. Powerful-IoU:more straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism[J]. Neural Networks,2024,170:276-284.
[22]Redmon J, Farhadi A. YOLOv3: an incremental improvement [EB/OL]. （2018-04-08）
[2025-09-01]. https://arxiv.org/abs/1804.02767.
[23]Li C Y, Li L L, Jiang H L, et al. YOLOv6: a single-stage object detection framework for industrial applications [ EB/OL]. （2022-09-07）
[2025-09-01]. https://arxiv.org/abs/2209.02976.
[24]Wang C Y, Yeh I H, Mark Liao H Y. YOLOv9:learning what you want toLearn using programmable gradient information[C]//Computer Vision-ECCV 2024,Cham:Springer,2025.
[25]Chen H, Chen K, Ding G G, et al. YOLOv10:real-time end-to-end object detection[C]//Advances in Neural Information Processing Systems,December 10-15,2024. Vancouver,BC,Canada:Neural Information Processing Systems Foundation,Inc.,2024. DOI:10.52202/079017-3429.
[26]Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]//Computer Vision-ECCV 2020. Cham:Springer,2020.
[27]Zhao Y A, Lv W Y, Xu S L, et al. DETRs beat YOLOs on real-time object detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-22,2024,Seattle,WA,USA:IEEE,2024.
[28]Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23,2018,Salt Lake City,UT,USA:IEEE,2018:7132-7141.
[29]Woo S, Park J, Lee J Y, et al. CBAM:convolutional block attention module[C]//Computer Vision-ECCV 2018. Cham:Springer,2018:3-19.
[30]Hou Q B, Zhou D Q, Feng J S. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 20-25,2021,Nashville,TN,USA:IEEE,2021.
[31]Wang Q L, Wu B G, Zhu P F, et al. ECA-net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 13-19,2020,Seattle,WA,USA:IEEE,2020.
[32]Cai X H, Lai Q X, Wang Y W, et al. Poly kernel inception network for remote sensing detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-22,2024,Seattle,WA,USA:IEEE,2024.
[33]Zheng Z H, Wang P, Liu W, et al. Distance-IoU loss:faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12993-13000.
[34]Rezatofighi H, Tsoi N, Gwak J, et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 15-20,2019,Long Beach,CA,USA:IEEE,2020.
[35]Zhang Y F, Ren W Q, Zhang Z, et al. Focal and efficient IoU loss for accurate bounding box regression[J]. Neurocomputing,2022,506:146-157.
[36]Gevorgyan Z. SIoU loss: more powerful learning for bounding box regression[EB/OL]. （2022-05-26）
[2025-09-01]. https://arxiv.org/pdf/2205.12740.
[37]Tong Z, Chen Y, Li H, et al. Wise-IoU: bounding box regressionloss with dynamic focusing mechanism[EB/OL]. （2023-04-08）
[2025-09-01]. https://arxiv.org/abs/2301.10051,2023.

相似文献/References:

[1]张丽颖,冯新新,高晶晶,等.根际浇灌ALA 溶液对苹果叶片生理特性与果实品质的影响[J].江苏农业学报,2015,(01):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
　ZHANG Li-ying,FENG Xin-xin,GAO Jing-jing,et al.Effects of rhizosphere-applied 5-aminolevulinic acid (ALA) solutions on leaf physiological characteristics and fruit quality of apples[J].,2015,(08):158.[doi:10.3969/j.issn.1000-4440.2015.01.025]
[2]牛鹏飞,申远,李帅,等.苹果中福美胂残留的RP-HPLC检测[J].江苏农业学报,2018,(03):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
　NIU Peng-fei,SHEN Yuan,LI Shuai,et al.Determination of residual asomate in apple by reversed-phase high-performance liquid chromatography (RP-HPLC)[J].,2018,(08):706.[doi:doi:10.3969/j.issn.1000-4440.2018.03.033]
[3]车金庆,王帆,王艺洁,等.基于视觉注意机制的黄绿色苹果图像分割[J].江苏农业学报,2018,(06):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
　CHE Jin-qing,WANG Fan,WANG Yi-jie,et al.A segmentation method of yellow and green apple images based on visual attention mechanism[J].,2018,(08):1347.[doi:doi:10.3969/j.issn.1000-4440.2018.06.021]
[4]车金庆,王帆,吕继东,等.重叠苹果果实的分离识别方法[J].江苏农业学报,2019,(02):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
　CHE Jin-qing,WANG Fan,LYU Ji-dong,et al.Separation and recognition method for overlapped apple fruits[J].,2019,(08):469.[doi:doi:10.3969/j.issn.1000-4440.2019.02.030]
[5]张永超,赵录怀,王昊,等.基于环境气体信息的BP神经网络苹果贮藏品质预测[J].江苏农业学报,2020,(01):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
　ZHANG Yong-chao,ZHAO Lu-huai,WANG Hao,et al.Prediction of apple storage quality using BP neural network based on environmental gas information[J].,2020,(08):194.[doi:doi:10.3969/j.issn.1000-4440.2020.01.027]
[6]徐臣善,徐爱红,萧蓓蕾,等.授粉品种对红富士苹果果实糖积累及其代谢相关酶活性的影响[J].江苏农业学报,2021,(01):121.[doi:doi:10.3969/j.issn.1000-4440.2021.01.016]
　XU Chen-shan,XU Ai-hong,XIAO Bei-lei,et al.Effects of pollination varieties on sugar accumulation and metabolism related enzyme activities in red Fuji apple fruit[J].,2021,(08):121.[doi:doi:10.3969/j.issn.1000-4440.2021.01.016]
[7]张俊娜,王冲,张东,等.小农户管理行为对苹果园郁闭度的影响[J].江苏农业学报,2021,(01):163.[doi:doi:10.3969/j.issn.1000-4440.2021.01.021]
　ZHANG Jun-na,WANG Chong,ZHANG Dong,et al.Effect of smallholder farmers’ management behavior on the canopy density of apple orchard[J].,2021,(08):163.[doi:doi:10.3969/j.issn.1000-4440.2021.01.021]
[8]王新亮,彭玲,王健,等.苹果Dof转录因子生物信息学及其表达分析[J].江苏农业学报,2021,(02):480.[doi:doi:10.3969/j.issn.1000-4440.2021.02.026]
　WANG Xin-liang,PENG Ling,WANG Jian,et al.Bioinformatics and expression analysis of the Dof transcription factors in apple[J].,2021,(08):480.[doi:doi:10.3969/j.issn.1000-4440.2021.02.026]
[9]陈光明,孔浩然,章永年,等.苹果机器人采摘存在的关键问题及对策[J].江苏农业学报,2022,38(06):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]
　CHEN Guang-ming,KONG Hao-ran,ZHANG Yong-nian,et al.Key problems and countermeasures of apple machine picking[J].,2022,38(08):1709.[doi:doi:10.3969/j.issn.1000-4440.2022.06.030]
[10]班兆军,高喧翔,马肄恒,等.基于高光谱和深度学习的苹果品质无损检测方法[J].江苏农业学报,2024,(08):1446.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]
　BAN Zhaojun,GAO Xuanxiang,MA Yiheng,et al.Non-destructive detection method of apple quality based on hyperspectral and deep learning[J].,2024,(08):1446.[doi:doi:10.3969/j.issn.1000-4440.2024.08.009]

备注/Memo

备注/Memo:
收稿日期:2025-09-25基金项目:北京市科学基金项目(9232005)作者简介:刘洋(2000-),男,湖南邵阳人,硕士研究生,研究方向为深度学习、目标检测。(E-mail)2330702050@st.btbu.edu.cn通讯作者:毛典辉,(E-mail)maodh@th.btbu.edu.cn
更新日期/Last Update: 2026-09-16