Nondestructive perception of potato quality in actual online production based on cross-modal technology
作者机构：School of AutomationHangzhou Dianzi UniversityHangzhou 310018China School of Information Engineering and Internet of ThingsHuzhou Vocational and Technical CollegeHuzhou 313000ZhejiangChina Jinhua Academy of Agricultural SciencesJinhua 321017ZhejiangChina College of Biosystems Engineering and Food ScienceZhejiang UniversityHangzhou 310058China Fair Friend Institute of Intelligent ManufacturingHangzhou Vocational and Technical CollegeHangzhou 310018China
出 版 物：《International Journal of Agricultural and Biological Engineering》 (国际农业与生物工程学报（英文）)
年 卷 期：2023年第16卷第6期
页 面：280-290页
核心收录：
学科分类：0202[经济学-应用经济学] 02[经济学] 020205[经济学-产业经济学] 0828[工学-农业工程]
基 金：supported by the Zhejiang Province Key Research and Development Program(Grant No.2021C02011) Zhejiang Province Public Welfare Technology Application Research Project(Grant No.LGN18-F030002) Hangzhou Science and Technology Bureau(Grant No.20201203B116) Program of“Xinmiao”(Potential)Talents in Zhejiang Province(Grant Number:2022R4-07B055) the Graduate Scientific Research Foundation of Hangzhou Dianzi University(Grant No.CXJJ2022177) the Major Science and Technology Projects of Breeding New Varieties of Agriculture in Zhejiang Province(Grant No.2021C02074)
主 题：cross-modal technology potato quality YOLOv5s VIS/NIR spectroscopy online nondestructive detection
摘 要：Nowadays,China stands as the global leader in terms of potato planting area and total potato *** rapid and nondestructive detection of the potato quality before processing is of great significance in promoting rural revitalization and augmenting farmers’***,existing potato quality sorting methods are primarily confined to theoretical research,and the market lacks an integrated intelligent detection ***,there is an urgent need for a post-harvest potato detection method adapted to the actual production *** study proposes a potato quality sorting method based on cross-modal ***,an industrial camera obtains image information for external quality detection.A model using the YOLOv5s algorithm to detect external green-skinned,germinated,rot and mechanical damage ***/NIR spectroscopy is used to obtain spectral information for internal quality detection.A convolutional neural network(CNN)algorithm is used to detect internal blackheart disease *** mean average precision(mAP)of the external detection model is 0.892 when intersection of union(IoU)=*** accuracy of the internal detection model is 98.2%.The real-time dynamic defect detection rate for the final online detection system is 91.3%,and the average detection time is 350 ms per *** contrast to samples collected in an ideal laboratory setting for analysis,the dynamic detection results of this study are more applicable based on a real-time online working *** also provides a valuable reference for the subsequent online quality testing of similar agricultural products.
维普期刊数据库