Imagen de Portada

An Instance Segmentation Method for Agricultural Plastic Residual Film on Cotton Fields Based on RSE-YOLO-Seg

Guardado en:
Publicado en:Agriculture vol. 15, no. 19 (2025), p. 2025-2056
Autor principal: Fang Huimin
Otros Autores: Xu Quanwang, Chen Xuegeng, Wang, Xinzhong, Yan, Limin, Zhang, Qingyi
Publicado:
MDPI AG
Materias:
China
Random errors
Machine learning
Accuracy
Remote sensing
Datasets
Agricultural production
Cotton
Artificial intelligence
Loam soils
Root-mean-square errors
Neural networks
Labeling
Agricultural land
Instance segmentation
Drones
Modules
Receptive field
Statistical analysis
Object recognition
Polymer films
Environmental
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:To address the challenges of multi-scale missed detections, false positives, and incomplete boundary segmentation in cotton field residual plastic film detection, this study proposes the RSE-YOLO-Seg model. First, a PKI module (adaptive receptive field) is integrated into the C3K2 block and combined with the SegNext attention mechanism (multi-scale convolutional kernels) to capture multi-scale residual film features. Second, RFCAConv replaces standard convolutional layers to differentially process regions and receptive fields of different sizes, and an Efficient-Head is designed to reduce parameters. Finally, an NM-IoU loss function is proposed to enhance small residual film detection and boundary segmentation. Experiments on a self-constructed dataset show that RSE-YOLO-Seg improves the object detection average precision (mAP50(B)) by 3% and mask segmentation average precision (mAP50(M)) by 2.7% compared with the baseline, with all module improvements being statistically significant (p < 0.05). Across four complex scenarios, it exhibits stronger robustness than mainstream models (YOLOv5n-seg, YOLOv8n-seg, YOLOv10n-seg, YOLO11n-seg), and achieves 17/38 FPS on Jetson Nano B01/Orin. Additionally, when combined with DeepSORT, compared with random image sampling, the mean error between predicted and actual residual film area decreases from 232.30 cm2 to 142.00 cm2, and the root mean square error (RMSE) drops from 251.53 cm2 to 130.25 cm2. This effectively mitigates pose-induced random errors in static images and significantly improves area estimation accuracy.
ISSN:2077-0472
DOI:10.3390/agriculture15192025
Fuente:Agriculture Science Database