[1]张耀军,吴桂玲,沈剑波.基于无人机遥感与改进YOLO 11的水稻病害检测模型[J].江苏农业科学,2025,53(20):219-231.
Zhang Yaojun,et al.A rice disease detection model based on UAV remote sensing and improved YOLO 11[J].Jiangsu Agricultural Sciences,2025,53(20):219-231.
点击复制
基于无人机遥感与改进YOLO 11的水稻病害检测模型(
)
《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]
- 卷:
-
第53卷
- 期数:
-
2025年第20期
- 页码:
-
219-231
- 栏目:
-
病虫害智能检测
- 出版日期:
-
2025-10-20
文章信息/Info
- Title:
-
A rice disease detection model based on UAV remote sensing and improved YOLO 11
- 作者:
-
张耀军1; 吴桂玲1; 沈剑波2
-
1.信阳农林学院信息工程学院,河南信阳 464000; 2.温州科技职业学院智慧农业工程学院/温州农业具身智能体重点实验室,浙江温州 325006
- Author(s):
-
Zhang Yaojun; et al
-
-
- 关键词:
-
YOLO 11-RGL模型; YOLO 11模型; 无人机遥感; 水稻病害检测
- Keywords:
-
-
- 分类号:
-
S126;TP391.41
- DOI:
-
-
- 文献标志码:
-
A
- 摘要:
-
细菌性叶枯病(BLB)、褐斑病(BS)和叶黑粉病(LS)是水稻作物的严重病害,检测是有效管理的第一步。当前检测方法面临着检测背景复杂、检测目标较小和模型参数较大等问题。针对这些问题,提出了一种基于无人机遥感和改进YOLO 11的水稻病害检测模型。首先,在骨干网络中融入RevCol模块,同时用ConvNeXt的层级结构替换YOLO 11的C3K2模块,该主干网络不仅有效降低了模型复杂度,同时确保了检测精度,提升了无人机场景下的实时性和适应性。其次,在颈部网络中引入GradDynFPN模块,该模块通过优化特征交互方式,减少了多尺度特征融合过程中的信息丢失或模糊问题,确保了上层特征在下层特征融合时能够保持其语义信息的完整性,同时避免了下层特征对上层特征的干扰,从而提高了模型的整体检测性能。最后,在检测头部分采用了LSCD-Head轻量检测头,该结构通过引入GroupNorm卷积和共享卷积设计,减少了参数量,并提升了分类和回归精度。结果表明,在无人机航拍的自建水稻病害数据集上,YOLO 11-RGL模型与YOLO 11模型相比平均识别精度mAP提高了4百分点,识别速度提高了12%,浮点运算数FLOPs降低了11.3%、参数量降低了34.4%。通过最终实际检测发现YOLO 11-RGL模型检测精度更高、速度更快且降低了小目标漏检率。
- Abstract:
-
-
参考文献/References:
[1]Roy N,Debnath P,Gaur H S. Adoption of multi-omics approaches to address drought stress tolerance in rice and mitigation strategies for sustainable production[J]. Molecular Biotechnology,2025:1-13.
[2]陈文博. 基于CNN和FPGA的稻米品种识别与质量检测研究[D]. 武汉:武汉轻工大学,2024:1-55.
[3]Conde S,Catarino S,Ferreira S,et al. Rice pests and diseases around the world:literature-based assessment with emphasis on Africa and Asia[J]. Agriculture,2025,15(7):667.
[4]de Clercq D,Mahdi A. Feasibility of machine learning-based rice yield prediction in India at the district level using climate reanalysis and remote sensing data[J]. Agricultural Systems,2024,220:104099.
[5]Nie L,Peng S. Rice production in China[J]. Rice production worldwide,2017:33-52.
[6]Lienhart R,Maydt J. An extended set of haar-like features for rapid object detection[C]//Proceedings of the international conference on image processing. Piscataway:IEEE,2002:900-903.
[7]Tomasi C. Histograms of oriented gradients[J]. Computer Vision Sampler,2012,1:1-6.
[8]Ren S,He K,Girshick R,J Sun. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell,2017,39:1137-1149.
[9]Diwan T,Anirudh G,Tembhurne J V. Object detection using YOLO:Challenges,architectural successors,datasets and applications[J]. Multimedia Tools and Applications,2023,82(6):9243-9275.
[10]Qian H,Wang H,Feng S,et al. FESSD:SSD target detection based on feature fusion and feature enhancement[J]. Journal of Real-Time Image Processing,2023,20(1):2.
[11]Bari B S,Islam M N,Rashid M,et al. A real-time approach of diagnosing rice leaf disease using deep learning-based faster R-CNN framework[J]. PeerJ Computer Science,2021,7:e432.
[12]Zhou G,Zhang W,Chen A,et al. Rapid detection of rice disease based on FCM-KM and faster R-CNN fusion[J]. IEEE Access,2019,7:143190-143206.
[13]Tian L,Zhang H,Liu B,et al. VMF-SSD:A Novel v-space based multi-scale feature fusion SSD for apple leaf disease detection[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics,2022,20(3):2016-2028.
[14]Wang J,Yu L,Yang J,et al. DBA_SSD:A novel end-to-end object detection algorithm applied to plant disease detection[J]. Information,2021,12(11):474.
[15]Sangaiah A K,Yu F N,Lin Y B,et al. UAV T-YOLO-rice:an enhanced tiny YOLO networks for rice leaves diseases detection in paddy agronomy[J]. IEEE Transactions on Network Science and Engineering,2024,11(6):5201-5216.
[16]Pan P,Guo W,Zheng X,Hu L,Zhou G,Zhang J.Xoo-YOLO:a detection method for wild rice bacterial blight in the field from the perspective of unmanned aerial vehicles[J]. Frontiers in Plant Science,2023,14:1256545.
[17]Anandakrishnan J,Sangaiah A K,Son N K,et al. UAV-based deep learning with tiny-YOLO v9 for revolutionizing paddy rice disease detection[C]//2024 IEEE International Conference on Smart Internet of Things (SmartIoT).IEEE,2024:16-21.
[18]Liao Y,Li L,Xiao H,et al. YOLO-MECD:citrus detection algorithm based on YOLO v11[J]. Agronomy,2025,15(3):687.
[19]Khanam R,Hussain M. YOLO v11:an overview of the key architectural enhancements[EB/OL]. (2024-10-23)[2025-01-01]. http://doi.org/10.48550/arXiv. 2410.17725.
[20]Cai Y X,Zhou Y Z,Han Q. Reversible column networks[EB/OL]. (2022-12-22)[2025-01-01]. http://doi.org/10.48550/arXiv.2212.11696.
[21]Yu W,Zhou P,Yan S,Wang X. Inceptionnext:when inception meets convnext[C]//Proceedings of the IEEE/cvf conference on computer vision and pattern recognition.2024:5672-5683.
[22]Doherty J,Gardiner B,Kerr E,et al. BiFPN-yolo:one-stage object detection integrating bi-directional feature pyramid networks[J]. Pattern Recognition,2025,160:111209.
[23]Yang G,Lei J,Zhu Z,et al. AFPN:asymptotic feature pyramid network for object detection[C]//2023 IEEE International Conference on Systems,Man,and Cybernetics (SMC).IEEE,2023:2184-2189.
[24]李彦勤,王晓婷. 基于改进FPN模型的西瓜幼苗智能识别方法 [J]. 中国农机化学报,2024,45 (12):148-153.
[25]Wang J,Chen K,Xu R,et al. Carafe:content-aware reassembly of features[C]//Proceedings of the IEEE/CVF international conference on computer vision.2019:3007-3016.
[26]Li Y H,Yang W Z,Wang L J,et al. Hawkeye conv-driven YOLO v10 with advanced feature pyramid networks for small object detection in UAV imagery[J]. Drones,2024,8(12):2504-446X.
[27]Wu Y,He K. Group normalization[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:3-19.
备注/Memo
- 备注/Memo:
-
收稿日期:2025-05-11
基金项目:河南省科技攻关项目(编号:252102111173);河南省高等学校重点科研项目(编号:24B520035)
作者简介:张耀军(1979—),男,河南信阳人,博士,副教授,研究方向为机器学习与人工智能。E-mail:zyj@xyafu.edu.cn。
通信作者:吴桂玲,博士,讲师,研究方向为图像处理与模式识别。E-mail:guiling@xyafu.edu.cn。
更新日期/Last Update:
2025-10-20