OTB-YOLO: An Enhanced Lightweight YOLO Architecture for UAV-Based Maize Tassel Detection.

Abstract

To tackle the challenges posed by substantial variations in target scale, intricate background interference, and the likelihood of missing small targets in multi-temporal UAV maize tassel imagery, an optimized lightweight detection model derived from YOLOv11 is introduced, named OTB-YOLO. Here, "OTB" is an acronym derived from the initials of the model's core improved modules: Omni-dimensional dynamic convolution (ODConv), Triplet Attention, and Bi-directional Feature Pyramid Network (BiFPN). This model integrates the PaddlePaddle open-source maize tassel recognition benchmark dataset with the public Multi-Temporal Drone Corn Dataset (MTDC). Traditional convolutional layers are substituted with omni-dimensional dynamic convolution (ODConv) to mitigate computational redundancy. A triplet attention module is incorporated to refine feature extraction within the backbone network, while a bidirectional feature pyramid network (BiFPN) is engineered to enhance accuracy via multi-level feature pyramids and bidirectional information flow. Empirical analysis demonstrates that the enhanced model achieves a precision of 95.6%, recall of 92.1%, and mAP@0.5 of 96.6%, marking improvements of 3.2%, 2.5%, and 3.1%, respectively, over the baseline model. Concurrently, the model's computational complexity is reduced to 6.0 GFLOPs, rendering it appropriate for deployment on UAV edge computing platforms.

Plant phenotyping relevance

UAV画像からトウモロコシ雄穂を検出する軽量モデルを開発し、ベンチマークデータセットで性能比較しているため、植物器官の表現型取得手法が中心である。

Code and data availability

The paper uses public datasets (PaddlePaddle maize tassel benchmark and MTDC) but these are cited prior-work resources, not author-deposited assets with URLs. No author analysis code, trained models, or supplementary data are publicly deposited; the Data Availability Statement says raw data are available only on author

No evidence-backed public reproduction asset is currently recorded.