USU-Corn-WeedDB: A UAV RGB Image Dataset for Multi-Species Weed Detection in Forage Corn
Quick Answer
This paper shows that The USU-Corn-WeedDB dataset, featuring 8,800 UAV RGB images, enables effective multi-species weed detection in forage corn, achieving mAP@0.5 scores between 0.773 and 0.840 across various YOLO models.
Quick Take
The USU-Corn-WeedDB dataset, featuring 8,800 UAV RGB images, enables effective multi-species weed detection in forage corn, achieving mAP@0.5 scores between 0.773 and 0.840 across various YOLO models. This publicly available resource addresses the critical need for training data in site-specific weed management systems, significantly impacting agricultural yield loss management.
Key Points
- Dataset includes 8,800 UAV RGB images from a commercial corn field.
- 366 full-resolution images were annotated for three weed species.
- Redroot pigweed accounts for 53.86% of annotated instances.
- 28 object detection models were tested, achieving competitive mAP scores.
- Dataset is publicly available for advancing weed detection research.
Article Content
From source RSS / original summaryarXiv:2606. 06709v1 Announce Type: new Abstract: Weed pressure in forage corn production causes yield losses of up to 31. 5%, yet site-specific weed management (SSWM) systems built on UAV imagery and deep learning remain constrained by the scarcity of field-representative training datasets.
We present USU-Corn-WeedDB, a publicly available UAV RGB image dataset collected from a commercial forage corn field in Cache Valley, Utah, designed to support multi-class weed detection under both supervised and semi-supervised learning frameworks. RGB imagery was acquired on 27 June 2025 using an Autel EVO II Dual 640T V2 drone at ~10m above ground level, yielding a ground sampling distance of approximately 0. 48 cm/pixel.
A total of 366 full-resolution images were tiled into 8,800 patches at 640 x 640-pixel resolution. Of these, 800 images were manually annotated for three weed species; common lambsquarters (Chenopodium album), redroot pigweed (Amaranthus retroflexus), and green foxtail (Setaria viridis) comprising 10,539 bounding-box instances, with the remaining 8,000 tiles retained as an unlabeled pool for semi-supervised experiments. This dataset reflects a natural class imbalance where redroot pigweed constitutes 53.
86% of annotated instances, which was preserved intentionally to mirror real field conditions. To validate dataset utility, we trained 28 object detection models spanning five architecture families including YOLOv8, YOLOv9, YOLOv10, YOLO11, YOLO26, and RT-DETR under identical conditions without hyperparameter tuning. Test set mAP@0. 5 ranged from 0. 773 to 0. 840, with lightweight models achieving competitive performance relevant to edge-deployed UAV systems. USU-Corn-WeedDB is publicly available at https://doi.
org/10. 5281/zenodo. 20044178.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.
