YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping

To address the issues of low efficiency and large errors in traditional manual cucumber fruit phenotyping methods, this paper proposes the application of keypoint detection technology for cucumber phenotyping and designs an improved lightweight model called YOLO11m-SCFPose. Based on YOLO11m-pose, th...

Full description

Saved in:
Bibliographic Details
Main Authors: Huijiao Yu, Xuehui Zhang, Jun Yan, Xianyong Meng
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Horticulturae
Subjects:
Online Access:https://www.mdpi.com/2311-7524/11/7/858
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406518793863168
author Huijiao Yu
Xuehui Zhang
Jun Yan
Xianyong Meng
author_facet Huijiao Yu
Xuehui Zhang
Jun Yan
Xianyong Meng
author_sort Huijiao Yu
collection DOAJ
description To address the issues of low efficiency and large errors in traditional manual cucumber fruit phenotyping methods, this paper proposes the application of keypoint detection technology for cucumber phenotyping and designs an improved lightweight model called YOLO11m-SCFPose. Based on YOLO11m-pose, the original backbone network is replaced with the lightweight StarNet-S1 backbone, reducing model complexity. Additionally, an improved C3K2_PartialConv neck module is used to enhance information interaction and fusion among multi-scale features while maintaining computational efficiency. The Focaler-IoU loss function is employed to improve keypoint localization accuracy. Results show that the improved model achieves an mAP50-95 of 0.924, with a floating-point operation count (GFLOPs) of 32.1, and reduces the model size to 1.229 × 10<sup>7</sup> parameters. This model demonstrates better computational efficiency and lower resource consumption, providing an effective lightweight solution for crop phenotypic analysis.
format Article
id doaj-art-b62f38c67fa64bd1913999150e81fffa
institution Kabale University
issn 2311-7524
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Horticulturae
spelling doaj-art-b62f38c67fa64bd1913999150e81fffa2025-08-20T03:36:21ZengMDPI AGHorticulturae2311-75242025-07-0111785810.3390/horticulturae11070858YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit PhenotypingHuijiao Yu0Xuehui Zhang1Jun Yan2Xianyong Meng3College of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, ChinaTo address the issues of low efficiency and large errors in traditional manual cucumber fruit phenotyping methods, this paper proposes the application of keypoint detection technology for cucumber phenotyping and designs an improved lightweight model called YOLO11m-SCFPose. Based on YOLO11m-pose, the original backbone network is replaced with the lightweight StarNet-S1 backbone, reducing model complexity. Additionally, an improved C3K2_PartialConv neck module is used to enhance information interaction and fusion among multi-scale features while maintaining computational efficiency. The Focaler-IoU loss function is employed to improve keypoint localization accuracy. Results show that the improved model achieves an mAP50-95 of 0.924, with a floating-point operation count (GFLOPs) of 32.1, and reduces the model size to 1.229 × 10<sup>7</sup> parameters. This model demonstrates better computational efficiency and lower resource consumption, providing an effective lightweight solution for crop phenotypic analysis.https://www.mdpi.com/2311-7524/11/7/858cucumber fruit phenotypingkeypoint detectionlightweight modelYOLO11m-SCFPose
spellingShingle Huijiao Yu
Xuehui Zhang
Jun Yan
Xianyong Meng
YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
Horticulturae
cucumber fruit phenotyping
keypoint detection
lightweight model
YOLO11m-SCFPose
title YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
title_full YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
title_fullStr YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
title_full_unstemmed YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
title_short YOLO11m-SCFPose: An Improved Detection Framework for Keypoint Extraction in Cucumber Fruit Phenotyping
title_sort yolo11m scfpose an improved detection framework for keypoint extraction in cucumber fruit phenotyping
topic cucumber fruit phenotyping
keypoint detection
lightweight model
YOLO11m-SCFPose
url https://www.mdpi.com/2311-7524/11/7/858
work_keys_str_mv AT huijiaoyu yolo11mscfposeanimproveddetectionframeworkforkeypointextractionincucumberfruitphenotyping
AT xuehuizhang yolo11mscfposeanimproveddetectionframeworkforkeypointextractionincucumberfruitphenotyping
AT junyan yolo11mscfposeanimproveddetectionframeworkforkeypointextractionincucumberfruitphenotyping
AT xianyongmeng yolo11mscfposeanimproveddetectionframeworkforkeypointextractionincucumberfruitphenotyping