基于目标检测的农业害虫计数方法综述
(湖南农业大学 信息与智能科学技术学院,湖南 长沙 410128)
摘要
随着智慧农业的发展,深度学习驱动的计算机视觉方法在农业害虫检测与计数中得到广泛应用。文章综述了目标检测在该领域的研究进展,比较了单阶段检测器(YOLO系列、SSD)与两阶段检测器(Faster R-CNN)在精度、速度与部署上的差异,并评述了典型改进策略及其在AgriPest、IP102、PestImgData、Pest24等数据集上的表现。同时,总结了常用评价指标(mAP、Precision、Recall、MAE、RMSE、R2)及其在检测与计数中的适用性,归纳了当前面临的小目标密集、复杂背景、数据不平衡和边缘部署等挑战。最后,提出多模态与时空建模、生成模型驱动的数据增强、统一化评价体系及轻量化优化等未来方向,为农业智能监测的研究与应用提供参考。
关键词
农业害虫;目标检测;计数;深度学习;数据集;评价指标
参考文献
- [1] VISHNOI V K,KUMAR K,KUMAR B,et al. Detection of Apple Plant Diseases Using Leaf Images through Convolutional Neural Network [J].IEEE Access,2022,11:6594-6609.
- [2] XIA C L,CHON T-S,REN Z M,et al. Automatic Identification and Counting of Small Size Pests in Greenhouse Conditions with Low Computational Cost [J].Ecological Informatics,2015,29:139-146.
- [3] YAO Q,LYU J,YANG B J,et al. Progress in Research on Digital Image Processing Technology for Automatic Insect Identification and Counting [J].Scientia Agricultura Sinica,2011,44(14):2886-2899.
- [4] 贾少鹏,高红菊,杭潇.基于深度学习的农作物病虫害图像识别技术研究进展 [J].农业机械学报,2019,50(S1):313-317.
- [5] TERVEN J,CÓRDOVA-ESPARZA D M,ROMERO-GONZÁLEZ J-A. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS [J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716.
- [6] CHEN J,FAN Y Y,WANG T,et al. Automatic Segmentation and Counting of Aphid Nymphs on Leaves Using Convolutional Neural Networks [J/OL].Agronomy,2018,8(8):129(2018-07-13)[2025-06-16].https://doi.org/10.3390/agronomy8080129.
- [7] BERECIARTUA-PÉREZ A,GÓMEZ L,PICÓN A,et al. Insect Counting through Deep Learning-based Density Maps Estimation [J/OL].Computers and Electronics in Agriculture,2022,197:106933[2025-06-14].https://doi.org/10.1016/j.compag.2022.106933.
- [8] HU H Y,SU C,YU P. Research on Pest and Disease Recognition Algorithms Based on Convolutional Neural Network [C]//2019 International Conference on Virtual Reality and Intelligent Systems (ICVRIS).Jishou:IEEE,2019:166-168.
- [9] 戴鹏飞,邹京汕,杨柳,等.基于YOLOv5的无人机桥面病害检测算法研究 [J].现代电子技术,2025,48(16):7-12.
- [10] 佘金惠.融合光流法和深度学习算法的果园害虫实时检测与数量统计应用研究 [D].荆州:长江大学,2023.
- [11] LIU J,WANG X. Tomato Diseases and Pests Detection Based on Improved YOLO V3 Convolutional Neural Network [J/OL].Frontiers in Plant Science,2020,11:898[2025-06-15].https://doi.org/10.3389/fpls.2020.00898.
- [12] 陈梅香,杨信廷,石宝才,等.害虫自动识别与计数技术研究进展与展望 [J].环境昆虫学报,2015,37(1):176-183.
- [13] KANG H W,ZHOU H Y,WANG X,et al. Real-time Fruit Recognition and Grasping Estimation for Robotic Apple Harvesting [J/OL].Sensors,2020,20(19):5670[2025-06-15].https://doi.org/10.3390/s20195670.
- [14] 郭庭航,李晓寒,张瑞,等.面向机器人感知的CoppeliaSim-YOLOv8目标检测仿真 [J].软件,2025,46(7):19-24.
- [15] 孙珊珊.基于深度学习的复杂背景下昆虫图像目标检测方法研究 [D].长春:长春工业大学,2025.
- [16] 姚青,吕军,杨保军,等.基于图像的昆虫自动识别与计数研究进展 [J].中国农业科学,2011,44(14):2886-2899.
- [17] 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(CVPR).Las Vegas:IEEE,2016:779-788.
- [18] LAW H,DENG J. CornerNet: Detecting Objects as Paired Keypoints [J].International Journal of Computer Vision,2020,128(3):642-656.
- [19] 方帅,沈岳,龙强,等.基于YOLO算法的鸟类检测技术研究综述 [J].农业与技术,2025,45(3):56-62.
- [20] REDMON J,FARHADI A. YOLOv3: An Incremental Improvement [J/OL].arXiv:1804.02767 [cs.CV].(2018-04-08).https://arxiv.org/abs/1804.02767.
- [21] BOCHKOVSKIY A,WANG C-Y,LIAO H-Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection [J/OL].arXiv:2004.10934 [cs.CV].(2020-04-23).https://arxiv.org/abs/2004.10934.
- [22] 蒋心璐,陈天恩,王聪,等.大田环境下的农业害虫图像小目标检测算法 [J].计算机工程,2024,50(1):232-241.
- [23] VARGHESE R,SAMBATH M. YOLOv8: A Novel Object Detection Algorithm With Enhanced Performance and Robustness [C]//2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS).Chennai:IEEE,2024:1-6.
- [24] PANG H T,ZHANG Y T,CAI W M,et al. A Real-time Object Detection Model for Orchard Pests Based on Improved YOLOv4 Algorithm [J/OL].Scientific Reports,2022,12(1):13557[2025-06-15].https://pubmed.ncbi.nlm.nih.gov/35941200/.
- [25] ZHONG Y H,GAO J Y,LEI Q L,et al. A Vision-based Counting and Recognition System for Flying Insects in Intelligent Agriculture [J/OL].Sensors,2018,18(5):1489(2018-05-09)[2025-07-03].https://doi.org/10.3390/s18051489.
- [26] FOTOUHI F,MENKE K,PRESTHOLT A,et al. Persistent Monitoring of Insect-pests on Sticky Traps through Hierarchical Transfer Learning and Slicing-aided Hyper Inference [J/OL].Frontiers in Plant Science,2024,15:1484587(2024-11-22)[2025-06-20].https://doi.org/10.3389/fpls.2024.1484587.
- [27] LIU W,ANGUELOV D,ERHAN D,et al. SSD: Single Shot MultiBox Detector [C]//Computer Vision-ECCV 2016:14th European Conference.Amsterdam:Springer International Publishing,2016:21-37.
- [28] JEONG J,PARK H,KWAK N. Enhancement of SSD by Concatenating Feature Maps for Object Detection [J/OL].arXiv:1705.09587 [cs.CV].(2017-05-26).https://arxiv.org/abs/1705.09587.
- [29] WANG L H,SHI W P,TANG Y H,et al. Transfer Learning-based Lightweight SSD Model for Detection of Pests in Citrus [J/OL].Agronomy,2023,13(7):1710(2023-06-26)[2025-06-16].https://doi.org/10.3390/agronomy13071710.
- [30] LYU Z W,JIN H F,ZHEN T,et al. Small Object Recognition Algorithm of Grain Pests Based on SSD Feature Fusion [J].IEEE Access,2021,9:43202-43213.
- [31] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
- [32] 姜晟,曹亚芃,刘梓伊,等.基于改进Faster RCNN的茶叶叶部病害识别 [J].华中农业大学学报,2024,43(5):41-50.
- [33] 王宁,智敏.深度学习下的单阶段通用目标检测算法研究综述 [J].计算机科学与探索,2025,19(5):1115-1140.
- [34] 肖德琴,黄一桂,张远琴,等.基于改进Faster R-CNN的田间黄板害虫检测算法 [J].农业机械学报,2021,52(6):242-251.
- [35] SIMONYAN K,ZISSERMAN A. Very Deep Convolutional Networks for Large-scale Image Recognition [J/OL].arXiv:1409.1556 [cs.CV].(2014-09-04).https://arxiv.org/abs/1409.1556.
- [36] HONG S-J,NAM I,KIM S-Y,et al. Automatic Pest Counting from Pheromone Trap Images Using Deep Learning Object Detectors for Matsucoccus Thunbergianae Monitoring [J/OL].Insects,2021,12(4):342(2021-04-12)[2025-06-16].https://doi.org/10.3390/insects12040342.
- [37] LI W Y,WANG D J,LI M,et al. Field Detection of Tiny Pests from Sticky Trap Images Using Deep Learning in Agricultural Greenhouse [J/OL].Computers and Electronics in Agriculture,2021,183:106048[2025-07-10].https://doi.org/10.1016/j.compag.2021.106048.
- [38] 黄成龙,张忠福,华向东,等.基于改进Faster R-CNN和Deep Sort的棉铃跟踪计数 [J].农业机械学报,2023,54(6):205-213.
- [39] WANG R J,LIU L,XIE C J,et al. AgriPest: A Large-scale Domain-specific Benchmark Dataset for Practical Agricultural Pest Detection in the Wild [J/OL].Sensors,2021,21(5):1601(2021-02-25)[2025-05-16].https://doi.org/10.3390/s21051601.
- [40] WU X,ZHAN C,LAI Y K,et al. IP102: A Large-scale Benchmark Dataset for Insect Pest Recognition [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019:8779-8788.
- [41] WANG Q-J,ZHANG S-Y,DONG S-F,et al. Pest24: A Large-scale very Small Object Data Set of Agricultural Pests for Multi-target Detection [J/OL].Computers and Electronics in Agriculture,2020,175:105585[2025-06-21].https://doi.org/10.1016/j.compag.2020.105585.
- [42] ZAIDI S S A,ANSARI M S,ASLAM A,et al. A Survey of Modern Deep Learning Based Object Detection Models [J/OL].arXiv:2104.11892 [cs.CV].(2021-04-24).https://arxiv.org/abs/2104.11892.
- [43] EVERINGHAM M,GOOL L V,WILLIAMS C K I,et al. The PASCAL Visual Object Classes (VOC) Challenge [J].International Journal of Computer Vision,2010,88(2):303-338.
- [44] BELL S,ZITNICK C L,BALA K,et al. Inside-outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:2874-2883.
- [45] RUSSAKOVSKY O,DENG J,SU H,et al. ImageNet Large Scale Visual Recognition Challenge [J].International Journal of Computer Vision,2015,115(3):211-252.
- [46] HOIEM D,CHODPATHUMWAN Y,DAI Q. Diagnosing Error in Object Detectors [C]//Computer Vision-ECCV 2012:12th European Conference on Computer Vision.Florence:Springer Nature Link,2012:340-353.
基金项目
国家社科基金青年项目(CIA240281);湖南省教育厅科研项目(24B0226)
作者简介
熊顺(2000—),男,汉族,湖南益阳人,硕士在读,研究方向:计算机视觉、农业信息技术;周瑞(2003—),男,汉族,湖南邵阳人,硕士在读,研究方向:计算机视觉、图像处理;邓涛(2001—),男,汉族,湖南永州人,硕士在读,研究方向:计算机科学与技术,生物信息;通信作者:李东晖(1973—),男,汉族,湖南邵阳人,副教授,博士,研究方向:软件工程、人工智能、农业信息技术与生物信息技术。