Study on Wheat Spike Automatic Detection Method Based on Improved YOLOv8n

doi:10.15933/j.cnki.1004-3268.2025.07.017

Abstract

Abstract: In wheat breeding，spike number is the key index to evaluate wheat yield.Timely and accurate detection of wheat spike number has important practical significance for early prediction of yield.In actual production，the method of artificial field investigation and statistics of wheat spikes is time‑consuming and laborious. Therefore，this paper proposed an automatic wheat spike detection method based on improved YOLOv8n. Firstly，HGNetV2 was used to improve the network structure to enhance the expression ability of small target wheat spike feature；Secondly，deep separable convolution and pointwise convolution were introduced to improve the computational efficiency and counting performance of the model；Finally，the loss function was improved to optimize the model，accurate determination of wheat ear position and category information was achieved.The test results showed that the accuracy of the improved YOLOv8n in wheat spike detection task was 93.7%，which was 6.5 percentage points higher than that of YOLOv8n.Compared with YOLOv5s and YOLOv8x，the improved YOLOv8n increased by 9.7 percentage point and 0.5 percentage point，which could detect wheat spike images in field complex situations，and had better computer vision processing effect and performance evaluation detection effect.This method can accurately detect the number of small target wheat spikes，and better solve the problem of occlusion and overlapping of wheat spikes.

Key words: Wheat, Spike count, Field phenotype, Target detection, YOLOv8n

摘要： 在小麦育种中，穗数是评估小麦产量的关键指标，及时准确检测小麦穗数对产量早期预测具有重要的实际意义。在实际生产中，采用人工田间调查统计麦穗的方法费时费力。因此，提出了基于改进YOLOv8n的麦穗自动检测方法。首先，利用HGNetV2改进网络结构，增强了小目标麦穗特征的表达能力；其次，引入深度可分离卷积和逐点卷积，提高了模型的计算效率和计数性能；最后，改进损失函数，对模型进行优化，实现了麦穗位置和类别信息的精准判断。结果表明，改进YOLOv8n在麦穗检测任务中的准确率为93.7%，比YOLOv8n提高6.5百分点，与YOLOv5s、YOLOv8x相比，改进YOLOv8n分别提高9.7、0.5百分点，可以在田间复杂情况下检测麦穗图像，具有较好的计算机视觉处理和性能评估检测效果。该方法能够准确地检测出小目标小麦穗数，较好地解决了小麦穗数的遮挡和交叉重叠等问题。

关键词: 小麦, 麦穗计数, 田间表型, 目标检测, YOLOv8n

CLC Number:

S126

ZANG Hecang, ZHOU Meng, WANG Yahui, PENG Yilong, ZHAO Qing, ZHANG Jie, LI Guoqiang. Study on Wheat Spike Automatic Detection Method Based on Improved YOLOv8n[J]. Journal of Henan Agricultural Sciences, 2025, 54(7): 162-169.

臧贺藏, 周萌, 王亚辉, 彭一龙, 赵晴, 张杰, 李国强. 基于改进YOLOv8n 的麦穗自动检测方法研究[J]. 河南农业科学, 2025, 54(7): 162-169.

Figures/Tables 7

References

［1］CHAUHAN S，DARVISHZADEH R，BOSCHETTI M，et al.Discriminant analysis for lodging severity classification in wheat using RADARSAT‑2 and Sentinel‑1 data［J］. ISPRS Journal of Photogrammetry and Remote Sensing2020，164：138‑151.

［2］MADEC S，JIN X L，LU H，et al. Ear density estimation from high resolution RGB imagery using deep learning technique［J］. Agricultural and Forest Meteorology，2019，264：225‑234.

［3］HE M X，HAO P，XIN Y Z. A robust method for wheatear detection using UAV in natural scenes［J］.IEEE Access，2020，8：189043‑189053.

［4］KHOROSHEVSKY F，KHOROSHEVSKY S，BAR‑HILLEL A. Parts‑per‑object count in agricultural images：Solving phenotyping problems via a single deep neural network［J］.Remote Sensing，2021，13（13）：2496.

［5］LU H，LIU L，LI Y N，et al. TasselNetV3：Explainable plant counting with guided upsampling and background suppression［J］. IEEE Transactions on Geoscience and Remote Sensing，2021，60：4700515.

［6］WANG D Y，ZHANG D Y，YANG G J，et al. SSRNet：In‑field counting wheat ears using multi‑stage convolutional neural network［J］.IEEE Transactions on Geoscience and Remote Sensing，2021，60：4403311.

［7］LIU W，ANGUELOV D，ERHAN D，et al. SSD：Single shot MultiBox detector［C］//Computer Vision-ECCV 2016. Cham：Springer，2016：21‑37.

［8］REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：Unified，real‑time object detection［C］//Computer Vision and Pattern Recognition（CVPR）.Las Vegas，NV，USA：IEEE，2016：779‑788.

［9］REDMON J，FARHADI A. YOLO9000：Better，faster，stronger［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. Honolulu，HI，USA：IEEE，2017：6517‑6525.

［10］REDMON J，FARHADI A. YOLOv3：An incremental improvement［C］//Computer Vision and Pattern Recognition（CVPR）. Salt Lake City，UT，USA：IEEE，2018：1804. 02767.

［11］BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：Optimal speed and accuracy of object detection［C］//Computer Vision and Pattern Recognition （CVPR）. Seattle，WA，USA：IEEE，2020：2004. 10934.

［12］ULTRALYTICS. YOLOv5 ［EB/OL］.（2022‑04‑04）［2025‑02‑18］.https：//github.com/ultralytics/yolov5.

［13］ZHAO J Q，ZHANG X H，YAN J W，et al. A wheat spike detection method in UAV images based on improved YOLOv5［J］.Remote sensing，2021，13（16）：3095.

［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，2018，14：22.

［15］LU J，HU J，ZHAO G N，et al. An in‑field automatic wheat disease diagnosis system［J］.Computers and Electronics in Agriculture，2017，142：369‑379.

［16］鲍文霞，张鑫，胡根生，等.基于深度卷积神经网络的田间麦穗密度估计及计数［J］.农业工程学报，2020，36（21）：186‑193，323.

BAO W X，ZHANG X，HU G S，et al. Estimation and counting of wheat ears density in field based on deep

convolutional neural network［J］.Transactions of the Chinese Society of Agricultural Engineering，2020，36（21）：186‑193，323.

［17］HASAN M M，CHOPIN J P，LAGA H，et al. Detection and analysis of wheat spikes using Convolutional Neural Networks［J］.Plant Methods，2018，14：100.

［18］ZHANG Y，LI M Z，MA X X，et al. High‑precision wheat head detection model based on one‑stage network and GAN model［J］. Frontiers in Plant Science，2022，13：787852.

［19］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.

［20］FERNANDEZ‑GALLEGO J A，BUCHAILLOT M L，APARICIO GUTIÉRREZ N，et al. Automatic wheat ear counting using thermal imagery［J］.Remote Sensing，2019，11（7）：751.

［21］KHAKI S，SAFAEI N，PHAM H，et al. WheatNet：A lightweight convolutional neural network for high‑throughput image‑based wheat head detection and counting［J］. Neurocomputing，2022，489：78‑89.

［22]孙月平，刘勇，郭佩璇，等. 基于改进YOLOv8n‑seg的蟹塘水草区域分割与定位方法［J］.农业工程学报，2024，40（17）：224‑233.

SUN Y P，LIU Y，GUO P X，et al. Region segmentation and localization method of water plants in crab pond based on improved YOLOv8n‑seg［J］.Transactions of the Chinese Society of Agricultural Engineering，2024，40（17）：224‑233.

［23］赵鑫，马双宝. 改进YOLOv8n的织物疵点检测算法［J/OL］. 哈尔滨理工大学学报，2025：1‑12.（2025‑03‑19）.https：//kns.cnki.net/kcms/detail/23.1404.N.20250318.1537.008.html.

ZHAO X，MA S B. Fabric defect detection algorithm based on improved YOLOv8n［J/OL］.Journal of Harbin University of Science and Technology，2025：1‑12（2025-03-19）. https：//kns.cnki.net/kcms/detail/23.1404.N.20250318.1537.008.html.

［24］文韬，王天一.基于改进YOLOv8n的玉米地杂草检测［J］.软件工程，2025，28（3）：6‑10.

WEN T，WANG T Y. Weed detection in corn fields based on improved YOLOv8n［J］. Software engineering，2025，28（3）：6‑10.

［25］高云鹏.基于深度神经网络的大田小麦麦穗检测方法研究［D］.北京：北京林业大学，2019.

GAO Y P.Study on detection method of wheat ear in field based on deep neural network［D］.Beijing：Beijing Forestry University，2019.

［26］谢元澄，何超，于增源，等. 复杂大田场景中麦穗检测级联网络优化方法［J］.农业机械学报，2020，51（12）：212‑219.

XIE Y C，HE C，YU Z Y，et al. Optimization method for cascade network of wheat ear detection in complex filed scene［J］.Transactions of the Chinese Society for Agricultural Machinery，2020，51（12）：212‑219.

［27］ALKHUDAYDI T，ZHOU J，DE LA LGLESIA B.SpikeletFCN：Counting spikelets from infield wheat crop images using fully convolutional networks［C］//Artificial Intelligence and Soft Computing. Cham：Springer，2019：3‑13.

[1]	WANG Haiyang, JIN Haiyang, SONG Hang, PAN Xiuyan, YAN Yaqian, YANG Xiwen, ZENG Zhaohai, ZANG Huadong, ZHENG Nian, LI Xiangdong, HE Dexian. Effects of Different Preceding Crops on Dry Matter Accumulation and Transportation，Nitrogen Absorption and Utilization and Yield of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(6): 1-10.
[2]	LI Shihang, GAO Wei, LI Yangyang, SUN Shilong, BAN Jiahao, NIE Zhaojun, GENG Yuehua, WANG Min, ZHAO Peng. Screening of Cd‐tolerant Fungi with High Cd Removal Ability and Their Effects on Wheat Growth and Cd Accumulation [J]. Journal of Henan Agricultural Sciences, 2025, 54(5): 59-67.
[3]	LI Xiaode, BAI Xintong, WU Enzhao, LÜ Chunlei, CHEN Shulin, YIN Guihong, WANG Daowen, ZHANG Kunpu. Composition Analysis of Vernalization and Photoperiod Genes in Varieties（lines）Derived from Core Wheat Parent Zhou 8425B [J]. Journal of Henan Agricultural Sciences, 2025, 54(5): 23-30.
[4]	ZHAO Lishang 1, YANG Tiancong 2, ZHANG Xiaomei2, SONG Quanhao 1, MA Zhiyao 2, FENG Wei 2, DUAN Jianzhao2. Effects of Tillage and Straw Returning Methods on Yield and N₂O Emission of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(4): 27-36.
[5]	GAO Cuimin, TIAN Yuan, ZHANG Ruiqing, HE Fang, HAN Weifeng, ZHANG Yunhong, PAN Xiaoying, YANG Yonghui. Effects of Irrigation Methods on Crop Yield and Water⁃Nitrogen Use Efficiency under Wheat⁃Peanut Rotation System [J]. Journal of Henan Agricultural Sciences, 2025, 54(3): 31-39.
[6]	ZHANG Bowen, JIN Haiyang, XU Haixia, ZHENG Fei, HE Ning, SU Yazhong, ZHAO Guojian, CHENG Hongjian, CHENG Xiyong, LI Xiangdong. Effect of Spraying Amino Acid Chelated Zinc after Anthesis on Synthesis and Accumulation of Starch and Protein in Wheat Grains [J]. Journal of Henan Agricultural Sciences, 2025, 54(3): 8-19.
[7]	PENG Chaojun, HUA Xia, WANG Songfeng, GAO Chong, DONG Haibin, HU Lin. Effect of Drought Stress on Photosynthetic and Physiological Characteristics of Flag Leaves of Different Wheat Varieties at Filling Stage [J]. Journal of Henan Agricultural Sciences, 2025, 54(2): 40-47.
[8]	HAN Ruifeng, REN Rongkui, DONG Xiangyang, HU Zebin, GUO Fangjun, FANG Tiantian, MA Wenhao, ZHANG Shuhong. Effects of Application Depth and Amount of Different Types of Fertilizers on Growth and Development of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(2): 30-39.
[9]	ZHANG Fuyan, SUN Congwei, CHEN Xiaojie, WANG Jiahuan, CHENG Zhongjie, ZHAO Wan, MA Xuhui, ZHANG Jianwei, FAN Jialin. Phenotypic Analysis and Preliminary Mapping of Wheat Dwarf Small⁃Kernel Mutant smk56 [J]. Journal of Henan Agricultural Sciences, 2025, 54(2): 21-29.
[10]	JIANG Guofei, WANG Xuqin, ZHANG Lingyuan, BAI Yutao, ZHANG Ping, LIU Junna, LI Li, LI Hanxue, QIN Peng. Evaluation of Adaptability of Dianmai 7 and Dianmai 12 and Detection of Stripe Rust Resistant Genes at Adult Plant Stage [J]. Journal of Henan Agricultural Sciences, 2025, 54(1): 9-20.
[11]	ZHANG Haoran, LIU Xiaoying, ZHOU Fenglong, XU Mingchen, GUO Zhengzheng, CHENG Jiayu, ZHANG Kunpu, WANG Daowen, SHI Cuilan. Creation and Phenotypic Analysis of TaGW2‑A1‑Overexpression Transgenic Wheat Germplasm [J]. Journal of Henan Agricultural Sciences, 2025, 54(1): 1-8.
[12]	DAI Ziju, LI Wenxu, YANG Huimin, ZHU Xiuhua, WANG Yahuan, XU Fuxin, LIU Dongyang, HOU Jinna, QIN Maomao, WU Zhengqing, ZHOU Zhengfu, LEI Zhensheng. Identification and Evaluation of Resistance to Stripe Rust of 480 Wheat Germplasms [J]. Journal of Henan Agricultural Sciences, 2024, 53(9): 1-15.
[13]	GUO Hui, LIAN Yanhao, ZHAO Zhibo, REN Yongzhe, WANG Zhiqiang, LIN Tongbao. Effects of Soybean and Maize Stubbles on Bacterial Community Structure and Function in Winter Wheat Rhizosphere Soil [J]. Journal of Henan Agricultural Sciences, 2024, 53(7): 79-89.
[14]	ZHANG Huifang, YAN Zhaoling, LIU Haijiao, DUAN Junzhi, CHEN Haiyan, GUO Yan, WANG Nan, YANG Cuiping, QI Hongzhi. Analysis and Evaluation of Comprehensive Traits of Wheat Varieties in Henan Province Consortium Experiment [J]. Journal of Henan Agricultural Sciences, 2024, 53(7): 35-43.
[15]	WANG Jingying, WANG Jiaxu, CHEN Lina, WANG Xiuping. Effect of Halloysite Nanotubes on Growth of Wheat under Copper Stress [J]. Journal of Henan Agricultural Sciences, 2024, 53(7): 28-34.