YOLO系列模型在麦穗检测中的演进规律、应用效能与未来展望

doi:10.14088/j.cnki.issn0439-8114.2025.12.037

摘要/Abstract

摘要： 通过梳理国内外YOLO系列模型及其在麦穗监测中的应用研究,发现该类模型凭借出色的实时性与高精度优势,已成为农业智能感知领域的研究热点。通过持续的模型优化与改进,麦穗检测的精度与效率不断提升,为小麦产量的智能化预测和农业现代化发展提供了有力支撑。尽管YOLO系列模型在麦穗监测中已取得显著进展,但在轻量化部署、多模态数据融合及跨场景泛化能力等方面仍存在提升空间。未来研究应聚焦上述方向,进一步增强模型的实用性与鲁棒性,为智慧农业提供更高效、可靠的技术支持。

关键词: YOLO系列模型, 麦穗, 目标检测, 特征提取, 检测精度, 演进规律, 应用效能, 未来展望

Abstract: By reviewing YOLO series models and their application research in wheat ear monitoring at home and abroad, it was found that these models, with their excellent real-time performance and high precision advantages, had become a research hotspot in the field of agricultural intelligent perception.Through continuous model optimization and improvement, the accuracy and efficiency of wheat ear detection were continuously improved, providing strong support for the intelligent prediction of wheat yield and the development of agricultural modernization. Although YOLO series models had made significant progress in wheat ear monitoring, there was still room for improvement in lightweight deployment, multi-modal data fusion, and cross-scene generalization ability. Future research should focus on the above directions to further enhance the practicality and robustness of the models, providing more efficient and reliable technical support for smart agriculture.

Key words: YOLO series models, wheat ear, object detection, feature extraction, detection accuracy, evolution rules, application efficiency, future prospects

中图分类号:

王青, 王智强, 刘鸿, 梁敏, 张雨晨, 林宇. YOLO系列模型在麦穗检测中的演进规律、应用效能与未来展望[J]. 湖北农业科学, 2025, 64(12): 218-227.

WANG Qing, WANG Zhi-qiang, LIU Hong, LIANG Min, ZHANG Yu-chen, LIN Yu. Evolution, application efficiency, and future prospects of YOLO series models in wheat ear detection[J]. HUBEI AGRICULTURAL SCIENCES, 2025, 64(12): 218-227.

参考文献

[1] 何中虎,庄巧生,程顺和,等.中国小麦产业发展与科技进步[J].农学学报,2018,8(1):99-106.
[2] MA J C, LI Y X, DU K M, et al.Segmenting ears of winter wheat at flowering stage using digital images and deep learning[J]. Computers and electronics in agriculture, 2020, 168: 105159.
[3] 陈森,徐伟峰,王洪涛,等.基于改进YOLOv7的麦穗检测算法[J].吉林大学学报(理学版),2024,62(4):886-894.
[4] CHEN Y, ZHANG Z, TAO F L, et al.Spatio-temporal patterns of winter wheat yield potential and yield gap during the past three decades in North China[J]. Field crops research, 2017, 206: 11-20.
[5] FERNANDEZ-GALLEGO J A, LOOTENS P, BORRA-SERRANO I, et al. Automatic wheat ear counting using machine learning based on RGB UAV imagery[J]. The plant journal,2020,103(4): 1603-1613.
[6] HASAN M M, CHOPIN J P, LAGA H, et al.Detection and analysis of wheat spikes using convolutional neural networks[J]. Plant methods, 2018, 14(1): 100.
[7] NAJAFIAN K, GHANBARI A, STAVNESS I, et al.A semi-self-supervised learning approach for wheat head detection using extremely small number of labeled samples[A].2021 IEEE/CVF international conference on computer vision workshops (ICCVW)[C]. Montreal, BC, Canada: IEEE, 2021.1342-1351.
[8] ZHU G C, ZHAO C X, ZHOU L L, et al.Winter wheat yield prediction at a county scale using time series variation features of remote sensing spectra and machine learning[J]. European journal of agronomy, 2025, 170: 127751.
[9] ZHU Y J, CAO Z G, LU H, et al.In-field automatic observation of wheat heading stage using computer vision[J]. Biosystems engineering, 2016, 143: 28-41.
[10] ALHARBI N, ZHOU J, WANG W.Automatic counting of wheat spikelets from time-lapse wheat plant growth images[J]. IEEE journal of pattern analysis and applications,2018,10: 346-355.
[11] QIU R C,HE Y,ZHANG M.Automatic detection and counting of wheat spikelet using semi-automatic labeling and deep learning[J]. Frontiers in plant science, 2022, 13: 872555.
[12] GANEVA D, ROUMENINA E, DIMITROV P, et al.Phenotypic traits estimation and preliminary yield assessment in different phenophases of wheat breeding experiment based on UAV multispectral images[J]. Remote sensing, 2022, 14(4): 1019.
[13] PRAKASH K, SARAVANAMOORTHI P, SATHISHKUMAR R, et al.A study of image processing in agriculture[J]. International journal of advanced networking and applications, 2017, 9(1): 3311.
[14] FERNANDEZ-GALLEGO J A, KEFAUVER S C, GUTIÉRREZ N A, et al. Wheat ear counting in-field conditions: High throughput and low-cost approach using RGB images[J]. Plant methods, 2018, 14(1): 22.
[15] TAN C W, ZHANG P P, ZHANG Y J, et al.Rapid recognition of field-grown wheat spikes based on a superpixel segmentation algorithm using digital images[J]. Frontiers in plant science, 2020, 11: 259.
[16] SADEGHI-TEHRAN P, VIRLET N, AMPE E M, et al.DeepCount: In-field automatic quantification of wheat spikes using simple linear iterative clustering and deep convolutional neural networks[J]. Frontiers in plant science, 2019, 10: 1176.
[17] ZHOU C Q, LIANG D, YANG X D, et al.Recognition of wheat spike from field based phenotype platform using multi-sensor fusion and improved maximum entropy segmentation algorithms[J]. Remote sensing, 2018, 10(2): 246.
[18] MISRA T, ARORA A, MARWAHA S, et al.SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging[J]. Plant methods, 2020, 16(1): 40.
[19] LI L, HASSAN M A, YANG S R, et al.Development of image-based wheat spike counter through a Faster R-CNN algorithm and application for genetic studies[J]. The crop journal,2022,10(5): 1303-1311.
[20] XIONG H P, CAO Z G, LU H, et al.TasselNetv2: In-field counting of wheat spikes with context-augmented local regression networks[J]. Plant methods, 2019, 15(1): 150.
[21] BHAGAT S, KOKARE M, HASWANI V, et al.WheatNet-lite: A novel light weight network for wheat head detection[A].2021 IEEE/CVF international conference on computer vision workshops (ICCVW)[C]. Montreal, BC, Canada:IEEE, 2021.1332-1341.
[22] LU H, CAO Z G.TasselNetV²+: A fast implementation for high-throughput plant counting from high-resolution RGB imagery[J]. Frontiers in plant science, 2020, 11: 541960.
[23] SANAEIFAR A, GUINDO M L, BAKHSHIPOUR A, et al.Advancing precision agriculture: The potential of deep learning for cereal plant head detection[J]. Computers and electronics in agriculture, 2023, 209: 107875.
[24] ZHAO J Q, YAN J W, XUE T J, et al.A deep learning method for oriented and small wheat spike detection (OSWSDet) in UAV images[J]. Computers and electronics in agriculture, 2022, 198: 107087.
[25] 王琳毅,白静,李文静,等.YOLO系列目标检测算法研究进展[J].计算机工程与应用,2023,59(14):15-29.
[26] JIANG P Y, ERGU D, LIU F Y, et al.A review of yolo algorithm developments[J]. Procedia computer science, 2022, 199: 1066-1073.
[27] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once: Unified, real-time object detection[A].2016 IEEE conference on computer vision and pattern recognition (CVPR)[C]. Las Vegas, NV, USA: IEEE, 2016.779-788.
[28] REDMON J, FARHADI A.YOLO9000: Better, faster, stronger[A].2017 IEEE conference on computer vision and pattern recognition (CVPR)[C]. Honolulu,HI,USA:IEEE, 2017.6517-6525.
[29] REDMON J,FARHADI A. YOLOv3: An incremental improvement[EB/OL].(2018-04-08). https://arxiv.org/abs/1804.02767.
[30] 万应霞,燕振刚.基于YOLO算法的农作物病虫害识别研究综述[J].热带农业工程,2024,48(1):25-28.
[31] 陈丰,李娜,苏祥祥,等.YOLO系列算法在草莓识别领域中的应用[J].山东农业工程学院学报,2024,41(6):30-38.
[32] BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. (2020-04-23). https://arxiv.org/abs/2004.10934.
[33] 张立夫. 基于深度学习和图像处理的小麦穗部表型参数获取方法研究[D].合肥:安徽农业大学,2023.
[34] YANG B H, GAO Z W, GAO Y, et al.Rapid detection and counting of wheat ears in the field using YOLOv4 with attention module[J]. Agronomy, 2021, 11(6): 1202.
[35] ZHAO F K, XU L Z, LV L Y, et al.Wheat ear detection algorithm based on improved YOLOv4[J]. Applied sciences, 2022, 12(23): 12195.
[36] JAISWAL S K, AGRAWAL R.A comprehensive review of YOLOv5: Advances in real-time object detection[J]. International journal of innovative research in computer science and technology, 2024, 12(3): 75-80.
[37] LI R, WU Y P.Improved YOLOv5 wheat ear detection algorithm based on attention mechanism[J]. Electronics, 2022, 11: 1673.
[38] SHI L, SUN J Y, DANG Y B, et al.YOLOv5s-T: A lightweight small object detection method for wheat spikelet counting[J]. Agriculture, 2023, 13(4): 872.
[39] 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). https://arxiv.org/abs/2209.02976.
[40] LI Z P, ZHU Y J, SUI S S, et al.Real-time detection and counting of wheat ears based on improved YOLOv7[J]. Computers and electronics in agriculture, 2024, 218: 108670.
[41] WANG C Y, BOCHKOVSKIY A, LIAO H M.YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[A].2023 IEEE/CVF conference on computer vision and pattern recognition (CVPR)[C].Vancouver, BC, Canada:IEEE, 2023.7464-7475.
[42] XU X M, ZHOU L, YU H L, et al.Winter wheat ear counting based on improved YOLOv7x and Kalman filter tracking algorithm with video streaming[J]. Frontiers in plant science, 2024, 15: 1346182.
[43] WU T L, ZHONG S Y, CHEN H, et al.Research on the method of counting wheat ears via video based on improved YOLOv7 and DeepSort[J]. Sensors, 2023, 23(10): 4880.
[44] 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.
[45] LI R, MENG J Y, WU Y P, et al.Wheat ear detection based on FasterCANet-YOLOv8s algorithm[J]. New Zealand journal of crop and horticultural science, 2025, 53(4): 1205-1225.
[46] MA N, SU Y X, YANG L X, et al.Wheat seed detection and counting method based on improved YOLOv8 model[J]. Sensors, 2024, 24(5): 1654.
[47] WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: Learning what you want to learn using programmable gradient information[A].Computer vision ECCV[C]. Cham,Switzerland: Springer Nature,2024.
[48] CHEN H, CHEN K, DING G G, et al.YOLOv10: Real-time end-to-end object detection[A].Advances in neural information processing systems 37[C]. Vancouver, BC, Canada:NeurIPS, 2024. 107984-108011.
[49] GUAN S T, LIN Y M, LIN G Y, et al.Real-time detection and counting of wheat spikes based on improved YOLOv10[J]. Agronomy, 2024, 14(9): 1936.
[50] LIU L, SUN T, LIU D, et al.Deep learning-based wheat ear recognition and counting[A].2025 2nd international conference on computer and multimedia technology[C]. Fujian:IEEE,2025. 283-288.
[51] LI J B, LI C C, FEI S P, et al.Wheat ear recognition based on RetinaNet and transfer learning[J]. Sensors,2021,21(14): 4845.
[52] 郝王丽,尉培岩,韩猛,等.基于YOLOv3网络的小麦麦穗检测及计数[J].湖北农业科学,2021,60(2):158-160,183.
[53] GONG B, ERGU D,CAI Y,et al. A method for wheat head detection based on YOLOv4[EB/OL]. (2020-10-07).https://doi.org/10.21203/rs.3.rs-86158/v1.
[54] JIA Z W, SHAO Y, HOU Y J, et al.An improved YOLOv4 method for rapid detection of wheat ears in the field[J]. INMATEH agricultural engineering, 2023,69(1): 185-194.
[55] 黄硕,周亚男,王起帆,等.改进YOLOv5测量田间小麦单位面积穗数[J].农业工程学报,2022,38(16):235-242.
[56] 鲍文霞,谢文杰,胡根生,等.基于TPH-YOLO的无人机图像麦穗计数方法[J].农业工程学报,2023,39(1):155-161.
[57] SHEN X J, ZHANG C, LIU K, et al.A lightweight network for improving wheat ears detection and counting based on YOLOv5s[J]. Frontiers in plant science, 2023, 14: 1289726.
[58] 苑迎春,耿俊,许楠,等.基于YOLO v8-TRP模型的小麦麦穗识别方法研究[J/OL].农业机械学报,2025:1-14(2025-07-15). https://kns.cnki.net/kcms2/article/abstractv=uSrlZFhNZxJPEEN57bW5v6qx30_p1oa3Oq8AR9XE-DT-6huqVPKKiMxVCmmu3Fr9VKIhV90JpUnszOivTij_fMVMd9yuqbO-IbMWCsiIIWBYANyMveIgG2AMRiv8iotcgHItl6oSmH1uvyO-EiqdS3I3fxk1Ceic_GdFLPSdX5nYPIcczOh2QQ==&uniplatform=NZKPT&language=CHShttps://kns.cnki.net/KCMS/detail/detail.aspxfilename=NYJX2 0250714004&dbname=CJFD&dbcode=CJFQ.
[59] 韩桐鹤,张博涵,费帅鹏,等.基于无人机视频流的小麦穗数精准监测研究[J/OL].麦类作物学报,2025:1-12(2025-07-09). https://kns.cnki.net/KCMS/detail/detail.aspxfilename=MLZW202 50708003&dbname=CJFD&dbcode=CJFQ.