SLW-YOLO: A Hybrid Soybean Parent Phenotypic Consistency Detection Model Based on Deep Learning

Chuntao Yu, Jinyang Li, Wenqiang Shi, Liqiang Qi, Zheyun Guan, Wei Zhang () and Chunbao Zhang ()
Additional contact information
Chuntao Yu: College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
Jinyang Li: College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
Wenqiang Shi: College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
Liqiang Qi: College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
Zheyun Guan: Key Laboratory of Hybrid Soybean Breeding of the Ministry of Agriculture and Rural Affairs/Soybean Research Institute, Jilin Academy of Agricultural Sciences (Northeast Agricultural Research Center of China), Changchun 130033, China
Wei Zhang: College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
Chunbao Zhang: Key Laboratory of Hybrid Soybean Breeding of the Ministry of Agriculture and Rural Affairs/Soybean Research Institute, Jilin Academy of Agricultural Sciences (Northeast Agricultural Research Center of China), Changchun 130033, China

Agriculture, 2025, vol. 15, issue 19, 1-25

Abstract: During hybrid soybean seed production, the parents’ phenotypic consistency is assessed by breeders to ensure the purity of soybean seeds. Detection traits encompass the hypocotyl, leaf, pubescence, and flower. To achieve the detection of hybrid soybean parents’ phenotypic consistency in the field, a self-propelled image acquisition platform was used to obtain soybean plant image datasets. In this study, the Large Selective Kernel Network (LSKNet) attention mechanism module, the detection layer Small Network (SNet), dedicated to detecting small objects, and the Wise Intersection over Union v3 (WIoU v3) loss function were added into the YOLOv5s network to establish the hybrid soybean parent phenotypic consistency detection model SLW-YOLO. The SLW-YOLO achieved the following: F1 score: 92.3%; mAP: 94.8%; detection speed: 88.3 FPS; and model size: 45.1 MB. Compared to the YOLOv5s model, the SLW-YOLO model exhibited an improvement in F1 score by 6.1% and in mAP by 5.4%. There was a decrease in detection speed by 42.1 FPS, and an increase in model size by 31.4 MB. The parent phenotypic consistency detected by the SLW-YOLO model was 98.9%, consistent with manual evaluation. Therefore, this study demonstrates the potential of using deep learning technology to identify phenotypic consistency in the seed production of large-scale hybrid soybean varieties.

Keywords: hybrid soybean; phenotypic consistency; deep learning; object detection; YOLO (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/2077-0472/15/19/2001/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/19/2001/ (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:2001-:d:1757833

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 ().