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

Salvato in:
Dettagli Bibliografici
Pubblicato in:Agriculture vol. 15, no. 19 (2025), p. 2025-2056
Autore principale: Fang Huimin
Altri autori: Xu Quanwang, Chen Xuegeng, Wang, Xinzhong, Yan, Limin, Zhang, Qingyi
Pubblicazione:
MDPI AG
Soggetti:
Accesso online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3261049500
003 UK-CbPIL
022 |a 2077-0472 
024 7 |a 10.3390/agriculture15192025  |2 doi 
035 |a 3261049500 
045 2 |b d20250101  |b d20251231 
084 |a 231331  |2 nlm 
100 1 |a Fang Huimin  |u School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China; fanghuimin@ujs.edu.cn (H.F.); 2212316015@stmail.ujs.edu.cn (Q.X.); chenxg130@sina.com (X.C.); xzwang@ujs.edu.cn (X.W.) 
245 1 |a An Instance Segmentation Method for Agricultural Plastic Residual Film on Cotton Fields Based on RSE-YOLO-Seg 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
651 4 |a China 
653 |a Random errors 
653 |a Machine learning 
653 |a Accuracy 
653 |a Remote sensing 
653 |a Datasets 
653 |a Agricultural production 
653 |a Cotton 
653 |a Artificial intelligence 
653 |a Loam soils 
653 |a Root-mean-square errors 
653 |a Neural networks 
653 |a Labeling 
653 |a Agricultural land 
653 |a Instance segmentation 
653 |a Drones 
653 |a Modules 
653 |a Receptive field 
653 |a Statistical analysis 
653 |a Object recognition 
653 |a Polymer films 
653 |a Environmental 
700 1 |a Xu Quanwang  |u School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China; fanghuimin@ujs.edu.cn (H.F.); 2212316015@stmail.ujs.edu.cn (Q.X.); chenxg130@sina.com (X.C.); xzwang@ujs.edu.cn (X.W.) 
700 1 |a Chen Xuegeng  |u School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China; fanghuimin@ujs.edu.cn (H.F.); 2212316015@stmail.ujs.edu.cn (Q.X.); chenxg130@sina.com (X.C.); xzwang@ujs.edu.cn (X.W.) 
700 1 |a Wang, Xinzhong  |u School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China; fanghuimin@ujs.edu.cn (H.F.); 2212316015@stmail.ujs.edu.cn (Q.X.); chenxg130@sina.com (X.C.); xzwang@ujs.edu.cn (X.W.) 
700 1 |a Yan, Limin  |u College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, China; yanlm@shzu.edu.cn 
700 1 |a Zhang, Qingyi  |u School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China; fanghuimin@ujs.edu.cn (H.F.); 2212316015@stmail.ujs.edu.cn (Q.X.); chenxg130@sina.com (X.C.); xzwang@ujs.edu.cn (X.W.) 
773 0 |t Agriculture  |g vol. 15, no. 19 (2025), p. 2025-2056 
786 0 |d ProQuest  |t Agriculture Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3261049500/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3261049500/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3261049500/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch