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

Huimin Fang, Quanwang Xu, Xuegeng Chen, Xinzhong Wang, Limin Yan and Qingyi Zhang ()
Additional contact information
Huimin Fang: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Quanwang Xu: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Xuegeng Chen: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Xinzhong Wang: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
Limin Yan: College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, China
Qingyi Zhang: School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China

Agriculture, 2025, vol. 15, issue 19, 1-31

Abstract: 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 cm 2 to 142.00 cm 2 , and the root mean square error (RMSE) drops from 251.53 cm 2 to 130.25 cm 2 . This effectively mitigates pose-induced random errors in static images and significantly improves area estimation accuracy.

Keywords: agricultural plastic film; residual membrane recognition; instance segmentation; YOLO11-seg; SegNext attention; NM-IoU; multi-scale attention (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/19/2025/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/19/2025/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:19:p:2025-:d:1759453

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().