CEDL_YOLO：多尺度轻量化棉田杂草检测方法

doi:10.3778/j.issn.1002-8331.2507-0265

摘要/Abstract

摘要： 针对棉田杂草检测中存在的模型计算量大、部署困难和识别率低问题，提出一种基于YOLO11n改进的轻量化目标检测模型CEDL_YOLO。在C3k2中集成星星模块（star block，Star）和改进的变异星星模块（variant star block，VStar）构成新的C3k2_S和C3k2_VS，防止过度依赖复杂结构和超参数，同时加强可扩展感受野中特征提取。提出通道混合功能（shift channel mix，SCM）改进了一种高效上采样模块（efficient up-convolution block_shift channel mix，EUCB_S），消除上采样后的特征冗余，增强对细节的感知。提出轻量化共享深度检测头（lightweight shared depthwise separable convolutional detection，LSDSCD），降低模型体积，同时增强多任务协同性和适应性。引入深度卷积（depthwise convolution，DWConv)替换主干网络卷积，增强模型的轻量化特性。结果表明，改进的CEDL_YOLO模型在准确率、召回率、F1分数和mAP50分别增加至95.84%、88.72%、92.06%和94.60%，与原YOLO11n模型对比，浮点数、模型大小和参数量分别减少33.3%、21.2%和32.4%，准确率、召回率、F1分数和mAP50分别提升0.45、2.18、1.47和1.05个百分点。该方法满足杂草检测在移动端部署的轻量化和精准要求，为棉田杂草检测及模型在移动端的部署提供参考。

关键词: 深度学习, 棉田, 杂草检测, YOLO11n, 轻量化

Abstract: In order to solve the problems of large model calculation, difficult deployment and low recognition rate in cotton field weed detection, this study proposes a lightweight target detection model CEDL_YOLO based on the improvement of YOLO11n. The star block (Star) and the improved variant star block (VStar) are integrated in C3k2 to form the new C3k2_S and C3k2_VS, which prevents over-reliance on complex structures and hyperparameters, and strengthens feature extraction in scalable receptive fields. A channel mixing function (shift channel mix, SCM) is proposed to improve an efficient up-sampling module (efficient up-convolution block_shift channel mix, EUCB_S), eliminating feature redundancy after upsampling and enhancing the perception of details. A lightweight shared depth detection head (lightweight shared depthwise separable convolutional detection, LSDSCD) is proposed to reduce the model size and enhance multi-task collaboration and adaptability. DWConv (depthwise convolution) is introduced to replace the backbone network convolution to enhance the lightweight characteristics of the model. The results show that the improved CEDL_YOLO model has increased accuracy, recall, F1 score and mAP50 to 95.84%, 88.72%, 92.06% and 94.60% respectively. Compared with the original YOLO11n model, the floating point number, model size and parameter amount are reduced by 33.3%, 21.2% and 32.4% respectively, and the accuracy, recall, F1 score and mAP50 are increased by 0.45, 2.18, 1.47 and 1.05 percentage points respectively. This method meets the lightweight and accurate requirements of weed detection on mobile terminals, and provides a reference for cotton field weed detection and model deployment on mobile terminals.

Key words: deep learning, cotton field, weed detection, YOLO11n, lightweight

段盛茂, 章翔峰, 姜宏, 孙凯歌. CEDL_YOLO：多尺度轻量化棉田杂草检测方法[J]. 计算机工程与应用, 2025, 61(24): 261-272.

DUAN Shengmao, ZHANG Xiangfeng, JIANG Hong, SUN Kaige. CEDL_YOLO：Multi-Scale Lightweight Cotton Field Weed Detection Method[J]. Computer Engineering and Applications, 2025, 61(24): 261-272.

参考文献

[1] LIU Q H, ZHANG Y, YANG G P. Small unopened cotton boll counting by detection with MRF-YOLO in the wild[J]. Computers and Electronics in Agriculture, 2023, 204: 107576.
[2] SAINI P, NAGESH D S. CottonWeeds: empowering precision weed management through deep learning and comprehensive dataset[J]. Crop Protection, 2024, 181: 106675.
[3] NALINI K, MURHUKRISHNAN P, CHINNUSAMY C, et al. Weeds of cotton a review[J]. Agricultural Reviews, 2015, 36(2): 140.
[4] MZOUGHI O, YAHIAOUI I. Deep learning-based segmentation for disease identification[J]. Ecological Informatics, 2023, 75: 102000.
[5] CHEN D, LU Y Z, LI Z J, et al. Performance evaluation of deep transfer learning on multi-class identification of common weed species in cotton production systems[J]. Computers and Electronics in Agriculture, 2022, 198: 107091.
[6] DARBYSHIRE M, COUTTS S, BOSILJ P, et al. Review of weed recognition: a global agriculture perspective[J]. Computers and Electronics in Agriculture, 2024, 227: 109499.
[7] 何全令, 杨静文, 梁晋欣, 等. 面向嵌入式除草机器人的玉米田间杂草识别方法[J]. 计算机工程与应用, 2024, 60(2): 304-313.
HE Q L, YANG J W, LIANG J X, et al. Weed identification method in corn fields applied to embedded weeding robots[J]. Computer Engineering and Applications, 2024, 60(2): 304-313.
[8] GUO Z H, CAI D D, BAI J C, et al. Intelligent rice field weed control in precision agriculture: from weed recognition to variable rate spraying[J]. Agronomy, 2024, 14(8): 1702.
[9] 胡冬, 吴敏琪, 施莲莉, 等. 基于机器视觉技术的农田杂草识别研究进展[J]. 上海农业科技, 2025(3): 182-184.
HU D, WU M Q, SHI L L, et al. Research progress of weed identification in farmland based on machine vision technology[J]. Shanghai Agricultural Science and Technology, 2025(3): 182-184.
[10] 疏雅丽, 张国伟, 王博, 等. 基于深层连接注意力机制的田间杂草识别方法[J]. 计算机工程与应用, 2022, 58(6): 271-277.
SHU Y L, ZHANG G W, WANG B, et al. Field weed identification method based on deep connection attention mechanism[J]. Computer Engineering and Applications, 2022, 58(6): 271-277.
[11] HU K, WANG Z Y, COLEMAN G, et al. Deep learning techniques for in-crop weed identification: a review[J]. arXiv:2103.14872, 2021.
[12] XIANG W T, WU D C, WANG J. Enhancing stem localization in precision agriculture: a two-stage approach combining YOLOv5 with EffiStemNet[J]. Computers and Electronics in Agriculture, 2025, 231: 109914.
[13] LI S Z, CHEN Z H, XIE J L, et al. PD-YOLO: a novel weed detection method based on multi-scale feature fusion[J]. Frontiers in Plant Science, 2025, 16: 1506524.
[14] XU K, ZHU Y, CAO W X, et al. Multi-modal deep learning for weeds detection in wheat field based on RGB-D images[J]. Frontiers in Plant Science, 2021, 12: 732968.
[15] RAI N, ZHANG Y, RAM B G, et al. Applications of deep learning in precision weed management: a review[J]. Computers and Electronics in Agriculture, 2023, 206: 107698.
[16] 朱养鑫, 郝珊珊, 郑伟健, 等. 基于知识蒸馏的多教师棉田杂草检测模型[J]. 农业工程学报, 2025, 41(7): 200-210.
ZHU Y X, HAO S S, ZHENG W J, et al. Multi-teacher cotton field weed detection model based on knowledge distillation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(7): 200-210.
[17] 徐可, 谢奇, 宋明翰, 等. 基于多模态信息融合的麦田杂草检测与管理系统设计与开发[J]. 农业工程学报, 2025, 41(8): 175-182.
XU K, XIE Q, SONG M H, et al. Development of weed detection and management system using multimodal information fusion for wheat fields[J]. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(8): 175-182.
[18] ZHENG L, ZHU C G, LIU L, et al. Star-YOLO: a lightweight and efficient model for weed detection in cotton fields using advanced YOLOv8 improvements[J]. Computers and Electronics in Agriculture, 2025, 235: 110306.
[19] ZHANG W X, SHI X W, JIANG M L, et al. Improved you only look once for weed detection in soybean field under complex background[J]. Engineering Applications of Artificial Intelligence, 2025, 151: 110762.
[20] ZHANG Y J, XU Y, HOU J, et al. LMS-YOLO11n: a lightweight multi-scale weed detection model[J]. International Journal of Advanced Computer Science and Applications, 2025, 16(1): 1291.
[21] BAJRAKTARI A, TOYLAN H. Autonomous agricultural robot using YOLOv8 and ByteTrack for weed detection and des-truction[J]. Machines, 2025, 13(3): 219.
[22] MA X, DAI X Y, BAI Y, et al. Rewrite the stars[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 5694-5703.
[23] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 1800-1807.
[24] 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.
[25] OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2023: 1-5.
[26] RAHMAN M M, MUNIR M, MARCULESCU R. EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation[C]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 11769-11779.
[27] GAO T, ZHANG Y, ZHANG Z Y, et al. BHViT: binarized hybrid vision transformer[C]//Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2025: 3563-3572.
[28] WANG X P, WAN S T, LI Z H, et al. ECL-Tear: lightweight detection method for multiple types of belt tears[J]. Measurement, 2025, 251: 117269.
[29] DANG F Y, CHEN D, LU Y Z, et al. YOLOWeeds: a novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems[J]. Computers and Electronics in Agriculture, 2023, 205: 107655.
[30] RAHMAN A, LU Y, WANG H. Deep neural networks for weed detections towards precision weeding[C]//Proceedings of the 2022 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, 2022.
[31] ZHU M L, KONG E. Multi-scale fusion uncrewed aerial vehicle detection based on RT-DETR[J]. Electronics, 2024, 13(8): 1489.
[32] FENG Y F, HUANG J G, DU S Y, et al. Hyper-YOLO: when visual object detection meets hypergraph computation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(4): 2388-2401.