[Poster Presentation]Wheat-YOLOv11 A Lightweight Detection Algorithm for Wheat Heads under Growth Light Interference

Wheat-YOLOv11 A Lightweight Detection Algorithm for Wheat Heads under Growth Light Interference
ID:93 Submission ID:98 View Protection:ATTENDEE Updated Time:2025-10-11 22:51:31 Hits:221 Poster Presentation

Start Time:2025-11-09 09:07 (Asia/Shanghai)

Duration:1min

Session:[P] Poster presentation » [P5] 5.Wireless power transfer technology

No files

Abstract
针对生长光干扰导致的小麦穗头识别率降低的问题,我们提出了一种名为Wheat-YOLOv11的轻量级目标检测算法。该模型将CSP结构与DCNv4可变形卷积集成以加强几何建模,引入SSFF(多尺度顺序特征融合)模块以增强小目标特征提取,并采用具有双分支解耦结构的LiteShiftHead轻量级检测头,在减少计算的同时提高
特征表示。实验结果表明,与基线模型相比,Wheat-YOLOv11 实现了 81.2% 的精度和 85.9% 的 mAP,同时减少了 18.8% 的参数数量。消融和比较实验验证了各模块的有效性,结果表明所提算法结合了强大的检测性能和高计算效率,适合在资源有限的环境中部署。

 
Keywords
small object detection; YOLOv11; wheat; multi-scale feature fusion; lightweight detection head
Speaker
Haitao Yu
student Anhui Agricultural University

Submission Author
Haitao Yu Anhui Agricultural University
Weibin Guo Chinese Academy of Science;Hefei Institutes of physical science
Lifu Gao Chinese Academy of Sciences;Hefei Institutes of physical science
Huibin Cao Hefei Institutes of Physical Science Chinese Academy of Sciences
Comment submit
Verification code Change another
All comments

Contact us

CIYCEE 2025 Official E-mail:

ciycee2025@163.com

 

WeChat public account: 

IEEE IAS SWJTU Student Branch