杂草计算机识别系统的研制

系统包括杂草鉴定、杂草信息、系统维护等模块,用户采用“人机对话式鉴定”模式,系统给出鉴定结果并列出其性状描述以及彩色图像,供用户对照确认。采用Visual FoxPro 6．0编程,利用可视与面向对象编程技术得到良好的界面．系统操作简便,调试和维护方便。     

Potential of a terrestrial LiDAR-based system to characterise weed vegetation in maize crops

LiDAR (Light Detection And Ranging) is a remote-sensing technique for the measurement of the distance between the sensor and a target. A LiDAR-based detection procedure was tested for characterisation of the weed vegetation present in the inter-row area of a maize field. This procedure was based on the hypothesis that weed species with different heights can be precisely detected and discriminated using non-contact ranging sensors such as LiDAR. The sensor was placed in the front of an all-terrain vehicle, scanning downwards in a vertical plane, perpendicular to the ground, in order to detect the profile of the vegetation (crop and weeds) above the ground. Measurements were taken on a maize field on 3 m wide (0.45 m²) plots at the time of post-emergence herbicide treatments. Four replications were assessed for each of the four major weed species: Sorghum halepense, Cyperus rotundus, Datura ferox and Xanthium strumarium. The sensor readings were correlated with actual, manually determined, height values (r² = 0.88). With canonical discriminant analysis the high capabilities of the system to discriminate tall weeds (S. halepense) from shorter ones were quantified. The classification table showed 77.7% of the original grouped cases (i.e., 4800 sampling units) correctly classified for S. halepense. These results indicate that LiDAR sensors are a promising tool for weed detection and discrimination, presenting significant advantages over other types of non-contact ranging sensors such as a higher sampling resolution and its ability to scan at high sampling rates.     

Modelling Wild-Oat Density in Terms of Soil Factors: A Machine Learning Approach

In crop fields, weed density varies spatially in non-random patterns. Initial knowledge of weed distribution would greatly improve weed management for Precision Agriculture operations. Site properties could be correlated to weed distribution, since the former vary among crop fields and also certain factors such as soil texture or nitrogen may condition the weed growth. This paper presents a method, based on artificial intelligence techniques, for inducing a model that appropriately predicts the heterogeneous distribution of wild-oat (Avena sterilis L.) in terms of some environmental variables. From several experiments, distinct rule sets have been found by applying a genetic algorithm to carry out the automatic learning process. The best rule set extracted was able to explain about 88% of weed variability.     

Identification of broad-leaved dock (Rumex obtusifolius L.) on grassland by means of digital image processing

Digital image processing has the potential to support the identification of plant species required for site-specific weed control in grassland swards. The present study focuses on the identification of one of the most invasive and persistent weed species on European grassland, the broad-leaved dock (Rumex obtusifolius L., R.o.), in complex mixtures of perennial ryegrass with R.o. and other herbs.A total of 108 digital photographs were obtained from a field experiment under constant recording geometry and illumination conditions. An object-oriented image classification was performed. Image segmentation was done by transforming the red, green, blue (RGB) colour images to greyscale intensity images. Based on that, local homogeneity images were calculated and a homogeneity threshold (0.97) was applied to derive binary images. Finally, morphological opening was performed. The remaining contiguous regions were considered to be objects. Features describing shape, colour and texture were calculated for each of these objects. A Maximum-likelihood classification was done to discriminate between the weed species. In addition, rank analysis was used to test how combinations of features influenced the classification result.The detection rate of R.o. varied with the training dataset used for classification. Average R.o. detection rates ranged from 71 to 95% for the 108 images, which included more than 3,600 objects. Misclassifications of R.o. occurred mainly with Plantago major (P.m.). Between 9 and 16% R.o. objects were classified incorrectly as P.m. and 17–24% P.m. objects were misclassified as R.o. The classification result was influenced by the defined object classes (R.o., P.m., T.o., soil, residue vs. R.o., residue). For instance, classification rates were 86–91% and 65–82% for R.o. exclusively and R.o. against the remaining herb species, respectively.     

Camera steered mechanical weed control in sugar beet,maize and soybean

In sugar beet, maize and soybean, weeds are usually controlled by herbicides uniformly applied across the whole field. Due to restrictions in herbicide use and negative side effects, mechanical weeding plays a major role in integrated weed management (IWM). In 2015 and 2016, eight field experiments were conducted to test the efficacy of an OEM Claas 3-D stereo camera^® in combination with an Einböck Row-Guard^® hoe for controlling weeds. Ducks-foot blades in the inter-row were combined with four different mechanical intra-row weeding elements in sugar beet, maize and soybean and a band sprayer in sugar beet. Average weed densities in the untreated control plots were from 12 to 153 plants m^?2 with Chenopodium album, Polygonum convolvulus, Thlapsi arvense being the most abundant weed species. Camera steered hoeing resulted in 78% weed control efficacy compared to 65% using machine hoeing with manual guidance. Mechanical intra-row elements controlled up to 79% of the weeds in the crop rows. Those elements did not cause significant crop damage except for the treatment with a rotary harrow in maize in 2016. Weed control efficacy was highest in the herbicide treatments with almost 100% followed by herbicide band-applications combined with inter-row hoeing. Mechanical weed control treatments increased white sugar yield by 39%, maize biomass yield by 43% and soybean grain yield by 58% compared to the untreated control in both years. However, yield increase was again higher with chemical weed control. In conclusion, camera guided weed hoeing has improved efficacy and selectivity of mechanical weed control in sugar beet, maize and soybean.     

Identifying the challenges of promoting ecological weed management (EWM) in organic agroecosystems through the lens of behavioral decision making

Ecological weed management (EWM) is a scientifically established management approach that uses ecological patterns to reduce weed seedbanks. Such an approach can save organic farmers time and labor costs and reduce the need for repeated cultivation practices that may pose risks to soil and water quality. However, adoption of effective EWM in the organic farm community is perceived to be poor. In addition, communication and collaboration between the scientific community, extension services, and the organic farming community in the US is historically weak. In order to uncover the most persistent obstacles to promoting effective weed management in organic agroecosystems, we use the mental models approach to generate an expert model based on interviews with experts (e.g., weed scientists, weed ecologists, and extension personnel) and theories from the behavioral sciences. The expert model provides two main insights: (1) EWM is a complex strategy that may cause farmers to use heuristics in management decisions and (2) the long-term benefits of EWM, rather than the risks, need to be emphasized in communication with and outreach to organic farmers. The basis for new research topics and outreach material that incorporates these insights from the expert model are discussed. We briefly explain how the expert model is an incomplete picture of on-farm practices, but provides the basis for the second step of our mental models research, the farmer interviews and farmer decision model development.     

Performance evaluation of a crop/weed discriminating microsprayer

An intelligent real-time microspraying weed control system was developed. The system distinguishes between weed and crop plants and a herbicide (glyphosate) is selectively applied to the detected weed plants. The vision system captures 40 RGB images per second, each covering 140 mm by 105 mm with an image resolution of 800 × 600 pixels. From the captured images the forward velocity is estimated and the spraycommands for the microsprayer are calculated. Crop and weed plants are identified in the image, and weed plants are sprayed. Performance of the microsprayer system was evaluated under laboratory conditions simulating field conditions. A combination of maize (Zea mays L.), oilseed rape (Brassica napus L.) and scentless mayweed (Matricaria inodora L.) plants, in growth stage BBCH10, was placed in pots, which were then treated by the microspray system. Maize simulated crop plants, while the other species simulated weeds. The experiment were conducted at a velocity of 0.5 m/s. Two weeks after spraying, the fraction of injured plants was determined visually. None of the crop plants were harmed while 94% of the oilseed rape and 37% of the scentless mayweed plants were significantly limited in their growth. Given the size and shape of the scentless mayweed plants and the microsprayer geometry it was calculated that the microsprayer could only hit 64% of the scentless mayweed plants. The system was able to effectively control weeds larger than 11 mm × 11 mm.     

Species diversity of thrips (Thysanoptera) in selected avocado orchards from Mexico based on morphology and molecular data

Avocado is one of the most important crops in the world, and Mexico is the largest producer of this fruit. Several insect pests affect its production, and thrips are amongst the most important. A key step in the design of control methods is accurate species identification. Despite this, formal reports on species diversity of thrips in Mexico are very scarce. Morphological identification can sometimes be time-consuming and inconclusive. Therefore, we explored the species diversity of thrips in Mexican avocado orchards(Michoacan state) based on partial sequences of the mitochondrial gene cytochrome oxidase subunit Ⅰ(COⅠ). Forty-four specimens were analysed, which represented approximately 8% of all individuals collected from five localities distributed in three Municipalities. All specimens were analysed using the COⅠ marker, and specimens within the genera Frankliniella were also analysed using a marker within the D2 domain of the 28 S(28 SD2) nuclear ribosomal DNA. Molecular identifications were confirmed using morphological taxonomy. Overall, six genera were found(Neohydatothrips, Scirtothrips, Frankliniella, Arorathrips, Caliothrips and Leptothrips). All genera contained only one species, except Frankliniella, for which there were six species. Data from the two molecular markers suggest the existence of cryptic species within Mexican F. occidentalis populations.     

苜蓿病虫草鼠害防治专家系统模块架构

通过总结我国西北地区苜蓿病虫草鼠害防治的专家经验,建立了基于单机和网络运行的苜蓿病虫草鼠害防治专家系统。该系统由系统管理模块等八大模块构成,可对苜蓿病虫草鼠害的识别、查询及防治技术进行远程检索和辅助决策,初步建立了苜蓿病虫草鼠害综合治理的专家决策体系。     

农牧一体化下杂草生物多样性及玉米生产效益研究

为研究农牧一体化对杂草生物多样性的影响,通过延军农场农牧一体化长期定位试验,采用田间对比试验方法,对放牧前后田间杂草种类、密度、盖度和地上生物量以及玉米产量进行调查研究,分析农牧一体化生产方式对杂草生物多样性及玉米生产效益的影响。结果表明:放牧前,农牧一体化(API)理杂草总密度是对照(CK)的1.41倍,且杂草优势种单一且相对多度分配不均匀;API杂草地上生物量比CK高出18.12kg/hm2;API杂草群落的Shannon-Wiener多样性指数(H′)、Pielou均匀度指数(E)、Simpson优势度指数(D)和Margalef丰富度指数(DMG)分别是CK的1.09、0.92、1.05和1.08倍。放牧后,API和CK杂草总密度分别减少77.00%和23.10%,杂草群落地上生物量依次分别下降94.18%和78.17%,故田间放养鹅可将田间16.01%杂草资源化,提高杂草生产力;API玉米产量是CK的0.92倍,减产所带来的经济损失达2 443.51元/hm2,鹅肉产品输出对经济总收入的贡献率高达48.74%,折合为25 922.80元/hm2;API的产投比(2.87)是CK(2.49)的1.15倍,API能够提高生产效益。因此,API处理使用鹅来控制杂草并将杂草资源化,提高生产力和生物多样性,可实现较高经济效益。     

Automatic identification of crop and weed species with chlorophyll fluorescence induction curves

Automatic identification of crop and weed species is required for many precision farming practices. The use of chlorophyll fluorescence fingerprinting for identification of maize and barley among six weed species was tested. The plants were grown in outdoor pots and the fluorescence measurements were done in variable natural conditions. The measurement protocol consisted of 1 s of shading followed by two short pulses of strong light (photosynthetic photon flux density 1700 μmol m⁻² s⁻¹) with 0.2 s of darkness in between. Both illumination pulses caused the fluorescence yield to increase by 30–60% and to display a rapid fluorescence transient resembling transients obtained after long dark incubation. A neural network classifier, working on 17 features extracted from each fluorescence induction curve, correctly classified 86.7–96.1% of the curves as crop (maize or barley) or weed. Classification of individual species yielded a 50.2–80.8% rate of correct classifications. The best results were obtained if the training and test sets were measured on the same day, but good results were also obtained when the training and test sets were measured on different dates, and even if fluorescence induction curves measured from both leaf sides were mixed. The results indicate that fluorescence fingerprinting has potential for rapid field separation of crop and weed species.     

光和不同打破种子休眠方法对紫茎泽兰种子萌发及幼苗状态的影响

紫茎泽兰是著名的外来入侵植物,作为入侵的第一步,发芽及其幼苗生长应该与其强入侵能力有关.基于此,通过不同光照强度处理和不同打破休眠方法的双因素实验,旨在探讨紫茎泽兰种子是否具有需光萌发特性以及低温、水杨酸、聚乙二醇,硝酸钾等常规打破休眠方法和光照如何共同影响其萌发、幼苗生长等问题.结果表明:在全光照条件下,不同处理的紫茎泽兰种子的萌发率均大于63％,铝箔纸覆盖的遮光条件(0.23％光照)萌发率均大于60％,而在完全黑暗条件下,其萌发率较低(均小于30％),这表明紫茎泽兰种子具有需光萌发的特性.有别于以往对其它植物种子的报道,低温处理、水杨酸处理、聚乙二醇处理和硝酸钾处理不能代替光照打破种子休眠,显示紫茎泽兰种子可能处于一种强迫休眠状态(种子静态).全光照与水杨酸处理、PEG处理对幼苗生长具有交互影响:黑暗下水杨酸处理浓度与幼苗生物量成正相关(P＜0.05),但全光照和加铝箔下不相关(P＞0.05);全光照下PEG处理浓度与根长显著正相关(P＜0.05),而加铝箔和黑暗下不相关(P＞0.05).紫茎泽兰种子需光萌发特征及其幼苗生长特点是人为破坏表土壤、深层土壤种子库地表化导致快速入侵的基础.结果也为通过引入适宜树种造林来控制光照因子对紫茎泽兰进行生态控制提供了理论依据.     

A new vision-based approach to differential spraying in precision agriculture

One of the objectives of precision agriculture is to minimize the volume of herbicides by using site-specific weed management systems. To reach this goal, two major factors need to be considered: (1) the similarity of spectral signatures, shapes, and textures between weeds and crops and (2) irregular distribution of weeds within the crop. This paper outlines an automatic computer vision method for detecting Avena sterilis, a noxious weed growing in cereal crops, and differential spraying to control the weed. The proposed method determines the quantity and distribution of weeds in the crop fields and applies a decision-making strategy for selective spraying, which forms the main focus of the paper. The method consists of two stages: image segmentation and decision-making. The image segmentation process extracts cells from the image as the low-level units. The quantity and distribution of weeds in the cell are mapped as area and structural based attributes, respectively. From these attributes, a multicriteria decision-making approach under a fuzzy context allows us to decide whether any given cell needs to be sprayed. The method was compared with other existing strategies.     

杂草鉴别专家系统

杂草鉴别专家系统包括杂草鉴定、信息查询、杂草处方和系统维护等模块．用户可采用多种鉴定方式,系统给出鉴定结果并列出其性状描述以及彩色模式图,以资对照确认．用户还可以查询各种除草信息并输出最佳的除草处方．采用 Ｖｉｓｕａｌ Ｆｏｘｐｒｏ ５．０ 编程,利用可视化与面向对象编程技术得到良好的界面,操作方便,系统易于修改和扩充