Promising real-time fruit and vegetable quality detection technologies applicable to manipulator picking process

In recent years,worldwide research on fruit and vegetable quality detection technology includes machine vision,spectroscopy,acoustic vibration,tactile sensors,etc.These technologies have also been gradually applied to fruit and vegetable grading and sorting lines in recent years,greatly improving the income of farmers.There have been numerous reviews of these techniques.Most of the published research on fruit and vegetable quality detection technology is still carried out in the laboratory.The emphases have been on quality feature extraction,model establishment and experimental verification.The successful application in the fruit and vegetable sorting production line proves that these studies have high application potential and value,and we look forward to the performance of these sensing technologies in the fruit and vegetable picking field.Therefore,in this paper,based on the future highly automated fruit and vegetable picking mode,we will focus on three kinds of fruit and vegetable quality detection technologies including machine vision,tactile sensor and spectroscopy,to provide some reference for future research.Since there are currently limited cases of detecting quality during the fruit and vegetable picking,experiments performed on prototypes of manipulator,or devices such as Nanocilia sensors,portable spectrometers,etc.,which are compact and convenient to mount on manipulator will be reviewed.Several tables and mosaics showing the performance of the three technologies in the detection of fruit and vegetable quality over the past five years have been listed.The performance of each sensing technology was relatively satisfactory in the laboratory in general.However,in the picking scenario,there are still many challenges to be solved.Different from industrial environments,agricultural scenarios are complex and changeable.Fragile and vulnerable agricultural products pose another challenge.The development of portable devices and nanomaterials have become important breakthroughs.Optical and tactile detection methods,as well as the integration of different quality detection methods,are expected to be the trends of research and development.

Using an improved lightweight YOLOv8 model for real-time detection of multi-stage apple fruit in complex orchard environments

For the purpose of monitoring apple fruits effectively throughout the entire growth period in smart orchards.A lightweight model named YOLOv8n-ShuffleNetv2-Ghost-SE was proposed.The ShuffleNetv2 basic modules and down-sampling modules were alternately connected,replacing the Backbone of YOLOv8n model.The Ghost modules replaced the Conv modules and the C2fGhost modules replaced the C2f modules in the Neck part of the YOLOv8n.ShuffleNetv2 reduced the memory access cost through channel splitting operations.The Ghost module combined linear and non-linear convolutions to reduce the network computation cost.The Wise-IoU(WIoU)replaced the CIoU for calculating the bounding box regression loss,which dynamically adjusted the anchor box quality threshold and gradient gain allocation strategy,optimizing the size and position of predicted bounding boxes.The Squeeze-and-Excitation(SE)was embedded in the Backbone and Neck part of YOLOv8n to enhance the representation ability of feature maps.The algorithm ensured high precision while having small model size and fast detection speed,which facilitated model migration and deployment.Using 9652 images validated the effectiveness of the model.The YOLOv8n-ShuffleNetv2-Ghost-SE model achieved Precision of 94.1%,Recall of 82.6%,mean Average Precision of 91.4%,model size of 2.6 MB,parameters of 1.18 M,FLOPs of 3.9 G,and detection speed of 39.37 fps.The detection speeds on the Jetson Xavier NX development board were 3.17 fps.Comparisons with advanced models including Faster R-CNN,SSD,YOLOv5s,YOLOv7‑tiny,YOLOv8s,YOLOv8n,MobileNetv3_small-Faster,MobileNetv3_small-Ghost,ShuflleNetv2-Faster,ShuflleNetv2-Ghost,ShuflleNetv2-Ghost-CBAM,ShuflleNetv2-Ghost-ECA,and ShuflleNetv2-Ghost-CA demonstrated that the method achieved smaller model and faster detection speed.The research can provide reference for the development of smart devices in apple orchards.

A systematic review of real-time detection and classification of power quality disturbances

This paper offers a systematic literature review of real-time detection and classification of Power Quality Disturbances(PQDs).A particular focus is given to voltage sags and notches,as voltage sags cause huge economic losses while research on voltage notches is still very incipient.A systematic method based on scientometrics,text similarity and the analytic hierarchy process is proposed to structure the review and select the most relevant literature.A biblio-metric analysis is then performed on the bibliographic data of the literature to identify relevant statistics such as the evolution of publications over time,top publishing countries,and the distribution by relevant topics.A set of articles is subsequently selected to be critically analyzed.The critical review is structured in steps for real-time detection and classification of PQDs,namely,input data preparation,preprocessing,transformation,feature extraction,feature selec-tion,detection,classification,and characterization.Aspects associated with the type of disturbance(s)addressed in the literature are also explored throughout the review,including the perspectives of those studies aimed at multiple PQDs,or specifically focused on voltage sags or voltage notches.The real-time performance of the reviewed tools is also examined.Finally,unsolved issues are discussed,and prospects are highlighted.

Application of droplet digital PCR in detection of seed-transmitted pathogen Acidovorax citrulli

Bacterial fruit blotch caused by Acidovorax citrulli is a serious threat to cucurbit industry worldwide.The pathogen is seedtransmitted,so seed detection to prevent distribution of contaminated seed is crucial in disease management.In this study,we adapted a quantitative real-time PCR(qPCR)assay to droplet digital PCR(ddPCR)format for A.citrulli detection by optimizing reaction conditions.The performance of ddPCR in detecting A.citrulli pure culture,DNA,infested watermelon/melon seed and commercial seed samples were compared with multiplex PCR,qPCR,and dilution plating method.The lowest concentrations detected(LCD)by ddPCR reached up to 2 fg DNA,and 102 CFU mL–1 bacterial cells,which were ten times more sensitive than those of the qPCR.When testing artificially infested watermelon and melon seed,0.1%infestation level was detectable using ddPCR and dilution plating method.The 26 positive samples were identified in 201 commercial seed samples through ddPCR,which was the highest positive number among all the methods.High detection sensitivity achieved by ddPCR demonstrated a promising technique for improving seed-transmitted pathogen detection threshold in the future.

深度学习在林果品质无损检测中的研究进展

林果品质与消费者和果农密切相关,在保障消费者安全、优化运输贮藏、改善后续分级、实现优质优价、提高果农收益等方面均有重要作用,然而传统的林果品质检测方法存在效率低、检测范围有限和鲁棒性差等问题。近年来,随着深度学习的迅猛发展,林果品质无损检测技术也取得了突破性的进步。该研究梳理了目前主流的深度学习模型及其作用,然后从林果安全品质、外部品质和内部品质3个方面阐述了深度学习的研究进展,发现卷积神经网络是林果品质无损检测领域应用最广泛的深度学习模型。同时结合深度学习应用现状与模型不足分析了该领域仍存在数据质量低、模型泛化能力差、实际部署困难等问题,提出未来应围绕数据增强与评价指标、建立公共数据集、多模态融合、模型融合、元学习、拓展应用、模型压缩等方面展开研究。该文旨在为深度学习在林果品质无损检测中的进一步发展提供参考,以加快林果产业的数字化、信息化进程。

基于可见-近红外光谱技术的果蔬品质检测方法

可见-近红外光谱技术利用波长在380~2 500 nm的电磁波获取果蔬中有机分子含氢基团的特征信息,根据样品对不同波长光的吸收信息,实现果蔬的外部、内部缺陷及营养成分定性、定量分析,是目前主流的果蔬内外部品质快速无损检测技术。综述了目前基于吸光度谱和能量谱对果蔬营养物质含量定量分析及缺陷定性分析,所使用的检测模型和变量筛选模型及其检测准确性,为相关研究人员选择高效准确的检测模型提供技术支撑。

‘阳光玫瑰’葡萄病毒病症状差异及其对品质的影响

针对‘阳光玫瑰’葡萄病毒病普遍发生的情况,检测了田间植株的病毒种类及其对葡萄产量和品质的影响。结果显示,在显症叶片和健康叶片中均检测到葡萄卷叶相关病毒3(GLRaV-3)、葡萄病毒A(GVA)、葡萄病毒B(GVB)和沙地葡萄茎痘病毒(GRSPaV)4种病毒。对重症、轻症和无症植株的产量和果实品质进行分析发现,重症植株的产量显著低于无症和轻症植株。玫瑰香味有关的橙花醇和香叶醇2种香气物质在3类不同症状表现的植株果实中无显著性差异,而重症植株果实中芳樟醇含量显著高于无症和轻症植株果实。针对病毒病对‘阳光玫瑰’生产造成的严重危害,根据生产经验总结出了两种缓解病毒病的方法可用于指导生产。

电子鼻在果蔬贮藏保鲜中应用的研究进展

果蔬采后变化是一个复杂的生物学过程,涉及成熟、衰老和死亡等多个阶段,导致果蔬内部物质发生一系列生理、生化和微生物变化,从而影响果蔬的品质和风味。气味是果蔬品质和风味的重要指标之一,与果蔬品种、成熟度、新鲜度和采后病害等因素具有密切关系。传统的气味分析方法主要包括仪器分析(如气相色谱-质谱联用)和感官分析,但这些方法存在局限性,如气相色谱-质谱联用不能全面反映样品的整体风味,且样品前处理复杂、检测耗时长、技术成本高等;而感官分析受主观因素影响较大。电子鼻作为一种模拟生物嗅觉系统的仪器,能够快速、客观和准确地检测和识别气味信号,逐渐成为果蔬贮藏保鲜领域的研究热点。综述电子鼻在果蔬品种与产地鉴定、成熟度判断、新鲜度检测、采后病害监测、果蔬农药残留和品质评价等方面的应用进展,并分析电子鼻在实际应用中面临的挑战和问题,展望果蔬采后精准化检测的未来发展趋势,以及提出了电子鼻向专一化、智能化、实用化方向改进的可能途径,为实现果蔬品质精准化检测提供参考和技术支持。

Design of the real-time detection system based on LabVIEW for no-till seeder working performance

In order to ensure the working performance of the seeder,reduce the labor intensity of manual testing,and improve the efficiency and accuracy of the detection,a real-time detection system for detecting the performance of no-till seeders was designed based on the LabVIEW software platform of virtual instrument technology and the MCC USB-231 data acquisition card.The detection system can be used to detect the seeding quality index and residue cover index.The detection of the seeding quality index included the middle detection between the metering device and the opener,the end detection between the opener and the furrow.The result of the field test showed that the detection accuracies of seed quantity,multiple index,and miss index were 94.51%,92.83%,and 91.81%,respectively.The fault position can be accurately determined,and the measurement accuracy of residue cover index was 94.54%.The working performance of the no-tillage seeder can be monitored by the detection system to avoid the occurrence of reseeding and miss-seeding and improve production efficiency.

High performance ethylene sensor based on palladium-loaded tin oxide:Application in fruit quality detection

Ethylene(C2 H4),as a plant hormone,its emission can be served as an indicator to measure fruit quality.Due to the limited physiochemical reactivity of C2 H4,it is a challenge to develop high performance C2 H4 sensors for fruit detection.Herein,this paper presents a resistive-type C2 H4 sensor based on Pd-loaded tin oxide(SnO2).The C2 H4 sensing performance of proposed sensor are tested at optimum operating temperature(250℃)with ambient relative humidity(51.9%RH).The results show that the response of Pd-loaded SnO2 sensor(11.1,Ra/Rg)is about 3 times higher than that of pristine SnO2(3.5)for 100 ppm C2 H4.The response time is also significantly shortened from 7 s to 1 s compared with pristine SnO2.Especially,the Pd-loaded SnO2 sensor possesses good sensitivity(0.58 ppm 1)at low concentration(0.05-1 ppm)with excellent linearity(R2=0.9963)and low detection limit(50 ppb).The high sensing performance of Pd-loaded SnO2 are attributed to the excellent adsorption and catalysis effects of Pd nanoparticle.Meaningfully,the potential applications of C2 H4 sensor are performed for monitoring the maturity and freshness of fruits,which presents a promising prospect in fruit quality evaluation.

蔬菜和水果农药残留检测的质量控制措施探讨

农药的大量使用在提高农产品产量的同时,也引发了严重的农药残留问题,给食品安全及公众健康带来巨大的潜在威胁。因此,构建科学、完善、高效、系统的农药残留检测质量控制体系是势在必行之举。基于此,本文探讨了蔬菜和水果农药残留检测的质量控制措施,以期保证检测结果的准确性、可靠性,为公众食品安全提供保障。

水果农药残留检测技术及质量安全管理

水果农药残留检测对于保障食品安全和消费者健康意义重大。水果农药残留检测时,检测技术是否先进,应用是否合规,直接影响着水果农药残留检测精准性。为保障水果质量安全,做好农药残留检测技术应用管理工作具有重要的现实意义。基于此,本文分析了水果农药残留检测技术类型,同时对水果质量安全管理对策进行探讨,以供参考。

高光谱成像在水果内部品质无损检测中的研究进展

随着高光谱成像技术的日趋成熟与高光谱成像硬件、软件成本的不断下降,以及高光谱图像数据处理算法的不断改进,应用高光谱成像技术对水果品质进行无损检测成为当前研究热点之一。为了能跟踪国内外的最新研究成果,对高光谱成像在水果内部品质(成熟度、坚实度、可溶性固形物、水分)检测研究进行综述,以期对我国相关研究人员的研究工作提供参考。

果蔬产品品质无损检测技术的研究进展

该文较为全面地介绍了国内外基于果蔬产品物理特性的无损检测技术的研究现状及方法,如电学特性检测技术、光学特性检测技术、声波振动特性检测技术、核磁共振(NMR)技术、电子鼻技术、撞击技术以及一些其他技术与方法,并对未来的发展方向予以了展望,认为综合应用多种高科技技术进行果蔬产品的无损检测与分选是未来发展的趋势。

基于机器视觉的荔枝果实采摘时品质检测技术

为了在荔枝采摘时实时判断果实的品质状态,通过分析自然环境中荔枝不同生长期的图像,对荔枝果实未成熟、成熟、成熟后外表腐烂变质的3种情况进行了图像数据分析。选取了YCbCr颜色模型,利用探索性分析法对荔枝不同部位、不同光照、不同生长期的荔枝图像的Cr分量进行了数据分析与统计,确定了辨识荔枝果实未成熟与成熟的Cr分量的阈值范围;对于成熟的荔枝,采用边缘提取与Hough圆拟合方法对其Cr分量图进行处理,标记出图像的荔枝果实,然后利用纹理统计法、颜色特征与果实不同部分面积比值相结合的方法进行果实变质的判断,最终实现了未成熟、成熟以及腐烂变质的荔枝果实的视觉智能判断,建立了荔枝果实品质辨识的智能系统。试验结果表明,辨识荔枝品质状态的正确率达93%。

高光谱图像技术在水果无损检测中的研究进展

为保证水果质量,满足企业与消费者的需求,势必要对水果进行品质检测和分级处理。高光谱图像作为一种新型的无损检测技术,融合了图像学和光谱学的优点,可以快速、无损地获取水果的空间和光谱图像信息,从而全方位的反映水果内外部的品质信息。因此,该技术在水果品质无损检测领域具有巨大的发展前景。该文主要介绍了高光谱图像系统的基本原理、图像的采集和分析方法、国内外水果无损检测的应用以及未来的发展前景。

水果品质无损检测方法研究进展

我国是水果生产大国,提高水果品质检测技术水平有助于提升我国水果产业的竞争力。食品农产品无损检测方法以其无损、快速、准确的特性,广泛应用于农产品品质检测,尤其是水果的检测研究中。该文综述了基于声学、电学等基本特性、基于智能感官仿生技术、光谱分析技术及高光谱成像新技术等的主要无损检测方法的研究进展,展望了无损检测方法在水果品质检测中的应用前景。

果蔬品质手持式近红外光谱检测系统设计与试验

为满足果蔬加工过程快速检测和质量控制的实际需求,研发近红外光谱技术的低成本、实用化、小型化的果蔬品质手持式检测系统。在分析当前近红外光谱实用化过程的瓶颈问题的基础上,提出果蔬品质的手持式检测系统设计方案,阐述了硬件系统选择和软件系统构建,介绍了检测系统的工作原理;选用近红外微机电系统的数字微镜器件作为分光元件,以单点探测器获取检测信息,从而实现光谱检测系统的微型化设计和系统成本的显著降低。以检测番茄为例,利用设计的手持式检测系统,获取番茄900~1 700 nm范围的近红外光谱,利用先选择特征波段再优选波长的建模策略,分别建立了番茄中番茄红素和可溶性固形物含量的定量检测模型;可溶性固形物含量模型的预测相关系数和预测均方根误差分别为0.899和0.133%;番茄红素模型的预测相关系数和预测均方根误差分别为0.886和2.508 mg/kg。研究表明该系统能够满足果蔬品质的快速无损检测要求,可为实用化、小型化的手持式光谱检测仪设计和开发提供参考。

高光谱图像技术在水果品质检测中的研究进展

高光谱图像技术结合了光谱技术和图像技术两者的优点,可实现水果内外品质同时检测,是水果品质无损检测的发展趋势。本文介绍了高光谱图像技术的基本原理,高光谱图像数据处理方法,在水果内外品质无损检测方面的国内外研究现状,分析了高光谱图像技术在水果品质检测中存在的问题及未来的研究方向。

电子鼻在果蔬品质检测中的研究进展

介绍了电子鼻的工作原理及组成,简述了电子鼻在检测苹果、梨、番茄、桃、柑橘等7种果蔬品质中的应用,总结了电子鼻在检测果蔬品质方面存在的问题,并对其发展方向和应用前景作了展望。