Real-time litchi detection in complex orchard environments: A portable, low-energy edge computing approach for enhanced automated harvesting

Litchi,a succulent and perishable fruit,presents a narrow annual harvest window of under two weeks.The advent of smart agriculture has driven the adoption of visually-guided,automated litchi harvesting techniques.However,conventional approaches typically rely on laboratory-based,high-performance computing equipment,which presents challenges in terms of size,energy consumption,and practical application within litchi orchards.To address these limitations,we propose a real-time litchi detection methodology for complex environments,utilizing portable,low-energy edge computing devices.Initially,the litchi orchard imagery is collected to enhance data generalization.Subsequently,a convolutional neural network(CNN)-based single-stage detector,YOLOx,is constructed to accurately pinpoint litchi fruit locations within the images.To facilitate deployment on portable,low-energy edge devices,we employed channel pruning and layer pruning algorithms to compress the trained model,reducing its size and parameters.Additionally,the knowledge distillation technique is harnessed to fine-tune the network.Experimental findings demonstrated that our proposed method achieved a 97.1%compression rate,yielding a compact litchi detection model of a mere 6.9 MB,while maintaining 94.9%average precision and 97.2%average recall.Processing 99 frames per second(FPS),the method exhibited a 1.8-fold increase in speed compared to the unprocessed model.Consequently,our approach can be readily integrated into portable,low-computational automatic harvesting equipment,ensuring real-time,precise litchi detection within orchard settings.

Method for the multi-view estimation of fish mass using a two-stage neural network with edge-sensitive module

The estimation of fish mass is one of the most basic and important tasks in aquaculture.Acquiring the mass of fish at different growth stages is of great significance for feeding,monitoring the health status of fish,and making breeding plans to increase production.The existing estimation methods for fish mass often stay in the 2D plane,and it is difficult to obtain the 3D information on fish,which will lead to the error.To solve this problem,a multi-view method was proposed to obtain the 3D information of fish and predict the mass of fish through a two-stage neural network with an edge-sensitive module.In the first stage,the side-and downward-view images of the fish and some 3D information,such as side area,top area,length,deflection angle,and pitch angle,were captured to estimate the size of the fish through two vertically placed cameras.Then the area of the fish at different views was estimated accurately through the pre-trained image segmentation neural network with an edgesensitive module.In the second stage,a fully connected neural network was constructed to regress the fish mass based on the 3D information obtained in the previous stage.The experimental results indicate that the proposed method can accurately estimate the fish mass and outperform the existing estimation methods.

Accurate and rapid image segmentation method for bayberry automatic picking via machine learning

Due to the short ripening period and complex picking environment,bayberry generally relies on mechanical equipment for picking,especially the automatic picking system guided by vision.Thus,it is crucial to locate the bayberry in the view accurately and rapidly.Although efforts have been made,the existing methods are difficult to implement due to the limited amount of data and the processing speed.In this study,an accurate and rapid segmentation method based on machine learning was proposed to address this problem.First,the images collected by the visual guidance system were pre-processed by contrast-limited adaptive histogram equalization(CLAHE)based on the Y component of the YUV color space.Taking advantage of the color difference map of RB and RG for the segmentation of different colors,an adaptive color difference map foreground segmentation method was then adopted for bayberry region foreground segmentation.Finally,distance transforms and marking control watershed methods were exploited to achieve single bayberry fruit segmentation.Furthermore,with the help of the convex hull theory and fruit shape characteristics,the irregular background interference areas were filtered out,which improved the accuracy of bayberry segmentation performance.The experimental results show that this method can achieve better segmentation of bayberry in complex orchard environment with an accuracy of 97.4%and only takes 0.136 s to calculate once.

中国麋鹿种群重建35年:历程、成就与挑战

迁地保护是《生物多样性公约》的重要内容,是"爱知生物多样性目标"的目标之一,也是《中国生物多样性保护战略与行动计划》(2011-2030)的战略任务和优先行动。麋鹿(Elaphurus davidianus)是国家I级重点保护野生动物。中国麋鹿经历了本土野外灭绝、圈养种群引至国外、国外圈养种群重引入国内、种群复壮、迁地保护、放归野外,最终建立野生种群的历程。北京麋鹿苑自1985年重引入38只后,于1991年就已恢复到60-80只的麋鹿基础种群。种群扩大后,逐年向外输出,35年来共计输出546只,苑内数量维持在150只左右。江苏大丰1986年引入麋鹿39只,于1990年达到78只的基础种群,2019年底种群数量发展至5,016只,是建群时的129倍。大丰自1995年开始向外输出麋鹿,至2020年底共计输出164只。麋鹿分布点从重引入时的2个发展至2020年的81个,已几乎全面覆盖麋鹿灭绝前原有的栖息地。其中野生种群分布在6处,数量总计达2,855只。中国麋鹿野生种群的重建是野生动物迁地保护和回归自然的典范,为全球野外灭绝野生动物种的保护贡献了中国智慧。然而,当前麋鹿保护也遇到诸多挑战:(1)尚没有国家层级的麋鹿保护整体规划,缺乏统一的监测平台与规范;(2)麋鹿遗传多样性匮乏,种群抗风险能力差;(3)野生种群分布不广,且数量较小,不利于野生种群的稳定性;(4)麋鹿种群与环境承载力的矛盾凸显,不利于麋鹿种群的健康发展;(5)麋鹿保护缺乏国际交流机制,不利于麋鹿相关研究的国际交流。因此,麋鹿的保护和研究仍任重道远,今后需加强各地麋鹿种群生态监测,建立麋鹿共享数据库;采用技术手段增加遗传多样性,建立麋鹿种质资源库;建立更多野生种群,以增加麋鹿野生种群的稳定性,使这一野外灭绝物种能够真正实现自然回归。

主要利益相关方在履行《名古屋议定书》中的关系与义务

生物遗传资源及其相关传统知识的获取与惠益分享(Access and Benefit Sharing,ABS)涉及三个主要利益相关方,即提供方、使用方和监管方。在我国履行《名古屋议定书》的过程中,需深刻理解《名古屋议定书》中对于提供方、使用方和监管方的相关规定,分析三方关系内涵及各自义务,对有效履行《名古屋议定书》具有重要意义。本文提出,为促进公平和公正的惠益分享,提供方有义务明确生物遗传资源的原产地并保护和可持续利用原产的生物遗传资源,确定生物遗传资源的原始持有社区和相关传统知识的原始持有人(或地方社区);通过调查、登记和编目,分析遗传资源的起源、形成及利用历史,建立当地生物遗传资源及相关传统知识的档案;通过ABS知识培训,提高参与"获取与惠益分享"事务的能力,特别是与使用方谈判ABS协议的能力。使用方有义务履行国际公约规定的"事先知情同意"和"共同商定条件"原则,在征得土著和地方社区的事先知情同意和实质性参与下,与土著和地方社区经共同商定条件,签订体现公平惠益分享的ABS协议;使用方要尊重土著和地方社区对保护和提供生物遗传资源的贡献,制定行为守则,履行社会责任;还要在论文发表及专利申请时披露所使用遗传资源及相关传统知识的来源和原产地。监管方有责任建立完善的ABS政策和法规体系;建立ABS信息交换机制,发布ABS相关信息;规定提交获取申请所要求的材料,提供"ABS协议"的模本,并审查和批准"ABS协议",签发"合法来源证书";并通过建立检查点,监督和监测ABS协议的履行。

Zn/Sr dual ions-collagen co-assembly hydroxyapatite enhances bone regeneration through procedural osteo-immunomodulation and osteogenesis

The immune microenvironment induced by biomaterials played vital roles in bone regeneration.Hydroxyapatite(HA)and its ion-substituted derivates represent a large class of core inorganic materials for bone tissue engineering.Although ion substitution was proved to be a potent way to grant HA more biological functions,few studies focused on the immunomodulatory properties of ion-doped HA.Herein,to explore the potential osteoimmunomodulatory effects of ion-doped HA,zinc and strontium co-assembled into HA through a collagen template biomimetic way(ZnSr-Col-HA)was successfully achieved.It was found that ZnSr-Col-HA could induce a favorable osteo-immune microenvironment by stimulating macrophages.Furthermore,ZnSr-Col-HA demonstrated a procedural promoting effect on osteogenic differentiation of bone marrow mesenchymal stem cells(BMSCs)in vitro.Specifically,the osteo-immune microenvironment acted as a dominant factor in promoting osteogenic gene expressions at the early stage through OSM signal pathway.Whereas the direct stimulating effects on BMSCs by Zn^(2+)/Sr^(2+) were more effectively at the later stage with Nfatc1/Maf and Wnt signals activated.In vivo study confirmed strong promoting effects of ZnSr-Col-HA on critical-sized cranial defect repair.The current study indicated that such a combined biomaterial design philosophy of dual ion-doping and biomimetic molecular co-assembly to endow HA applicable osteoimmunomodulatory characteristics might bring up a new cutting-edge concept for bone regeneration study.

Comprehensive evaluation of heavy metal contamination of sediment in Lake Dianchi by using modified AHP method and ^(137)Cs dating

Through the use of general sampling and measurement by ^(137)Cs dating,problems regarding the absence of monitoring data can easily be resolved.Further,weighted values need to be determined while Environment Quality Comprehensive Index(EQCI)is commonly used as applied in environmental quality comprehensive evaluation.In order to overcome the subjectivity in determining weights,the modified Analytical Hierarchy Process(AHP)method was designed.The modified AHP method involved the following key procedures:First,the parameters y_(i1) and y_(i2) were calculated based on the monitoring data;second,the factors were put in order according to the symbol and value of y_(i1) and y_(i2);third,the continuous odd integers,which represented the importance of factors,were given to factors according to their seating order;and,fourth,the factor weights were determined from the pair-wise comparison matrix calculated by the ratio of the given odd integers.Therefore,the weights were completely based on the monitoring data.In the present study,the comprehensive quality of sediments in five sections of Lake Dianchi were evaluated and the results indicated that the current contamination of sediments in each lake section is much more serious than at any other time in history.

No correlation between neonatal fitness and heterozygosity in a reintroduced population of P^re David＇s deer

Considering the severe impacts of genetic bottlenecks and small numbers of founders in populations of reintroduced animals, it is necessary to study inbreeding and its effect on fitness in species of conservation concern. Pere David＇s deer is one of few large mammal species extinct in the wild but safely preserved in captivity. Its specific background gives us the opportunity to study the relationships between heterozygosity and neonatal fitness in relocated populations. We employed five microsatellite loci to explore heterozygosity-fitness correlations in a population of Pere David＇s deer at the Beijing Milu Ecological Research Center. We observed associations between microsatellite-based variables sMLH, IR, MD^2 and HL, and two components of fitness ex- pressed early in life （birth weight and the neonatal mortality of 123 Pere David＇s deer calves born over six consecutive years）. We found that neonatal mortality was 19.1% - 7.6%, not higher than the 19% or 18% reported in other ungulates. The heterozygosity of calves was not associated with neonatal mortality, nor birth weight. Our study implies that low genetic variability of microsa- l：ellite loci has no overt effect on birth weight and neonatal mortality in reintroduced populations of P^re David＇s deer [Current Zoology 59 （2）： 249-256, 2013].

Albumin-assembled copper-bismuth bimetallic sulfide bioactive nanosphere as an amplifier of oxidative stress for enhanced radio-chemodynamic combination therapy

The tumor microenvironment with overexpressed hydrogen peroxide(H_(2)O_(2))and reinforced antioxidative system(glutathione,GSH)becomes a double-edged sword for the accessibility of nano-therapy.Since reactive oxygen species(ROS)are easily quenched by the developed antioxidative network,ROS-based treatments such as chemodynamic therapy(CDT)and radiotherapy(RT)for killing cancer cells are severely attenuated.To overcome such limitations,a bioactive nanosphere system is developed to regulate intracellular oxidative stress for enhanced radio-chemodynamic combination therapy by using bovine serum albumin(BSA)based bioactive nanospheres that are BSA assembled with in situ generated copper-bismuth sulfide nanodots and diallyl trisulfide(DATS).The copper-bismuth sulfide nanodots react with H_(2)O_(2)to produce·OH and release Cu^(2+).Then,the Cu^(2+)further depletes GSH to generate Cu^(+)for more·OH generation in the way of Fenton-like reaction.Such a cascade reaction can initiate·OH generation and GSH consumption to realize CDT.The elevation of ROS triggered by the DATS from BBCD nanospheres further augments the breaking of redox balance for the increased oxidative stress in 4T1 cells.With the sensitization of increased oxidative stress and high Z element Bi,an enhanced radio-chemodynamic combination therapy is achieved.The current work provides an enhanced radio-chemodynamic combination treatment for the majority of solid tumors by using the co-assembled bioactive nanospheres as an amplifier of oxidative stress.