摘要
【目的】准确获取和分析西瓜果实表型信息,为西瓜新品种选育提供支持。【方法】针对西瓜不同表型特征,综合利用图像处理、深度学习、三维重构技术,实现西瓜果实果皮厚度、瓤面积、瓤色、果实长宽、剖面籽粒数及纹理占比等表型性状自动提取和分析。【结果】所提出的方法能够有效地提取西瓜表型性状,图像测量值与人工测量值无显著差异(P>0.05),均方根百分比误差RMSPE(Root Mean Square Percentage Error)和平均绝对百分比误差MAPE(Mean Absolute Percentage Error)均小于0.03,决定系数(R-squared)R2均大于0.94,籽粒数识别mAP值为0.936。【结论】本研究提出的方法可以快速、便捷、准确地提取西瓜果实表型性状,解决目前西瓜表型信息获取不全、数据不够准确和过于依赖经验判断等问题。该技术将有助于提高西瓜育种工作和种质资源评价的自动化水平,并为新品种选育提供可靠的数据支持。
【Objective】Accurately acquire and analyze watermelon fruit phenotype information to support the breeding of new watermelon varieties.【Methods】For different phenotypic features of watermelon,a combination of image processing,deep learning,and 3D reconstruction techniques was employed to automatically extract and analyze phenotypic traits such as fruit peel thickness,pulp area,pulp color,fruit length and width,cross-sectional seed count,and texture percentage.【Results】The proposed method effectively extracts watermelon phenotypic traits,with no significant difference between image measurements and manual measurements(P>0.05).The average error RMSPE is<0.03,MAPE is<0.03,and the coefficient of determination R2 is all greater than 0.94.The seed count recognition mAP value is 0.936.【Conclusion】The method proposed in this study can rapidly,conveniently,and accurately extract watermelon fruit phenotypic traits,addressing current issues such as incomplete acquisition of watermelon phenotypic information,insufficiently accurate data,and excessive reliance on empirical judgment.This technology will contribute to the automation of watermelon breeding and germplasm resource evaluation,providing reliable data support for the breeding of new varieties.Moreover,it holds reference value for the analysis and application of fruit phenotypes in other crops.
作者
李彤
张蕾琛
张小斌
胡紫蔚
史骏
顾清
LI Tong;ZHANG Leichen;ZHANG Xiaobin;HU Ziwei;SHI Jun;GU Qing(College of Mathematics and Computer Science,Zhejiang Agriculture and Forestry University,Hangzhou 310021,China;Institute of Digital Agriculture,Zhejiang Academy of Agricultural Sciences,Hangzhou 310021,China;Ningbo Academy of Agricultural Sciences,Ningbo Zhejiang 315040,China;Ningbo Key Laboratory of Characteristic Horticultural Crops in Quality Adjustment and Resistance Breeding,Ningbo Zhejiang 315040,China)
出处
《新疆农业科学》
2025年第9期2331-2340,共10页
Xinjiang Agricultural Sciences
基金
国家西甜瓜产业技术体系(CARS-26)
宁波市重点研发计划暨“揭榜挂帅”项目(2023Z115)
浙江省西甜瓜良种育繁推科技创新平台(ZJ2019-80)。
关键词
图像处理
西瓜
表型提取
三维重构
形态学处理
image processing
watermelon
three-dimensional reconstruction
edge detection
morphological processing
