基于YOLOv10n-MCS的野生秋子梨叶片识别

Identification of leaves of wild Ussurian Pear () based on YOLOv10n-MCS.

作者信息

Li Niman, Dong Xingguang, Wu Yongqing, Tian Luming, Zhang Ying, Huo Hongliang, Qi Dan, Xu Jiayu, Liu Chao, Chen Zhiyan, Mou Yulu

机构信息

Research Institute of Pomology, Chinese Academy of Agricultural Sciences (CAAS), Key Laboratory of Horticulture Crops Germplasm Resources Utilization, Ministry of Agriculture and Rural Affairs, Xingcheng, China.

School of Software, Liaoning Technical University, Huludao, China.

出版信息

Front Plant Sci. 2025 Jul 3;16:1588626. doi: 10.3389/fpls.2025.1588626. eCollection 2025.

DOI:10.3389/fpls.2025.1588626

PMID:40678552

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12267203/

Abstract

INTRODUCTION

Wild Ussurian Pear germplasm resource has rich genetic diversity, which is the basis for genetic improvement of pear varieties. Accurately and efficiently identifying wild Ussurian Pear accession is a prerequisite for germplasm conservation and utilization.

METHODS

We proposed YOLOv10n-MCS, an improved model featuring: (1) Mixed Local Channel Attention (MLCA) module for enhanced feature extraction, (2) Simplified Spatial Pyramid Pooling-Fast (SimSPPF) for multi-scale feature capture, and (3) C2f_SCConv backbone to reduce computational redundancy. The model was trained on a self-made dataset of 16,079 wild Ussurian Pear leaves images.

RESULTS

Experiment results demonstrate that the precision, recall, mAP50, parameters, FLOPs, and model size of YOLOv10n-MCS reached 97.7(95% CI: 97.18 to 98.16)%, 93.5(95% CI: 92.57 to 94.36)%, 98.8(95% CI: 98.57 to 99.03)%, 2.52M, 8.2G, and 5.4MB, respectively. The precision, recall, and mAP50 are significant improved of 2.9%, 2.3%, and 1.5% respectively over the YOLOv10n model (p<0.05). Comparative experiments confirmed its advantages in precision, model complexity, model size, and other aspects.

DISCUSSION

This lightweight model enables real-time wild Ussurian Pear identification in natural environments, providing technical support for germplasm conservation and crop variety identification.

摘要

引言

野生秋子梨种质资源具有丰富的遗传多样性，这是梨品种遗传改良的基础。准确、高效地鉴定野生秋子梨种质是种质保存和利用的前提。

方法

我们提出了YOLOv10n-MCS，这是一种改进模型，其特点包括：（1）用于增强特征提取的混合局部通道注意力（MLCA）模块；（2）用于多尺度特征捕获的简化空间金字塔池化快速版（SimSPPF）；（3）用于减少计算冗余的C2f_SCConv主干。该模型在一个由16079张野生秋子梨叶片图像组成的自制数据集上进行训练。

结果

实验结果表明，YOLOv10n-MCS的精度、召回率、mAP50、参数、浮点运算次数和模型大小分别达到了97.7（95%置信区间：97.18至98.16）%、93.5（95%置信区间：92.57至94.36）%、98.8（95%置信区间：98.57至99.03）%、252万个、8.2千兆次和5.4兆字节。与YOLOv10n模型相比，精度、召回率和mAP50分别显著提高了2.9%、2.3%和1.5%（p<0.05）。对比实验证实了其在精度、模型复杂度、模型大小等方面的优势。