A study on plant disease and pest detection and counting based on multi-scale enhancement and cross-scale fusion.

Abstract

This paper targets the practical needs of plant disease and pest object detection and counting in complex field environments and proposes a lightweight improved framework based on YOLOv10. A MEMBA-F multi-scale feature enhancement module is introduced on the Neck to strengthen representations of small targets and weak-texture lesions, and a CSCAF cross-scale context-aware fusion module is designed to adaptively align high-level semantics with low-level details via cross-scale attention and gated selection, suppress background interference, and improve localization stability. The proposed method is systematically compared with two-stage detectors, YOLO-series models, and Transformer-based detectors on three public datasets, and is further investigated through ablation studies, confusion matrix analysis, and Grad-CAM interpretability analysis. In addition, a density-binned counting evaluation is conducted to validate robustness from sparse to dense scenarios. Experimental results demonstrate that the proposed method achieves superior performance in Precision, Recall, mAP@50, and mAP@50-95, and significantly reduces counting errors in dense scenes under deployable inference cost, providing reliable support for precision plant protection monitoring and decision making.

Code and data availability

The supplied blocks describe a YOLOv10-based plant disease/pest detection and counting method evaluated on three public datasets (including PlantDoc), but no authors' public code, trained model checkpoints, dataset deposit links, or data availability URLs are present in the supplied text. No paper-specific, publicly, 3

No evidence-backed public reproduction asset is currently recorded.