A field rice panicle detection model based on improved YOLOv11x

Abstract

Rice serves as the staple food for over 50% of the world's population, making its yield prediction crucial for food security. The number of panicles per unit area is a core parameter for estimating rice yield. However, traditional manual counting methods suffer from low efficiency and significant subjective bias, while unmanned aerial vehicle (UAV) images used for panicle detection face challenges such as densely distributed panicles, large scale variations, and severe occlusion. To address the above challenges, this paper proposes a rice panicle detection model based on an improved You Only Look Once version 11x (YOLOv11x) architecture. The main improvements include: 1) Introducing a Bi-level Routing Attention (BRA) mechanism into the backbone network to improve the feature representation capability for small objects; 2) Adopting a Transformer-based detection head (TransHead) to capture long-term spatial dependencies; 3) Integrating a Selective Kernel (SK) Attention module to achieve dynamic multi-scale feature fusion; 4) Designing a multi-level feature fusion architecture to enhance multi-scale adaptability. Experimental results demonstrate that the improved model achieves an mAP@0.5 of 89.4% on our self-built dataset, representing a 3% improvement over the baseline YOLOv11x model. It also achieves a Precision of 87.3% and an F1-score of 84.1%, significantly outperforming mainstream algorithms such as YOLOv8 and Faster R-CNN. Additionally, panicle counting tests conducted on 300 rice panicle images show that the improved model achieves R 2 = 0.85, RMSE = 2.33, and rRMSE = 0.13, indicating a good fitting effect. The proposed model provides a reliable solution for intelligent in-field rice panicle detection using UAV images and holds significant importance for precise rice yield estimation.

Plant phenotyping relevance

UAV画像からイネ穂数を検出・計数する深層学習手法を開発し、データセット上で性能検証しており、植物形質取得が研究の中心である。

Code and data availability

The paper uses a self-built UAV rice panicle dataset (4545 images) and an improved YOLOv11x model, but no public deposit of the dataset, images, annotations, trained weights, or author analysis code is stated. The only URL present (github.com/ultralytics/ultralytics) is a footnote to the generic YOLOv11 framework, nota

No evidence-backed public reproduction asset is currently recorded.