Weed Control System Research Articles

Farmers’ motivations for landrace cereal cultivation in Sweden

ABSTRACTThe interest in landrace cereals, i.e. genetically diverse varieties with historical origin, has increased in recent decades. While several studies exist on farmer’s motivations to grow landraces in a Global South context, investigations are much less common in the Global North. Through an interview study with 32 Swedish farmers that cultivate landrace cereals on a commercial scale, farmers’ motivations to grow landrace cereals were explored. The farms in the study ranged from medium sized to large. The majority were located in areas with marginal agricultural land and less fertile soil. All farms sold the landrace cereals at advantageous prices as niche products and all except one were certified organic. The farmers’ motivations for growing landraces were grouped around three themes: i) sustainable farming systems; ii) suitable agronomic traits; and iii) economic incentives. The first and overarching theme was that cultivation of landrace cereals fitted well with the farmers’ ideals on sustainable farming, with for example less intensive weed control and novel intercropping systems, as well as enabling production of wheat with baking quality on marginal agricultural land. Cultivation of landrace cereals was framed in contrast not only to conventional farming, but also to ‘conventionalised’ high input organic farming. The farmers regarded producing and marketing landrace cereals as an important foundation for more sustainable and multifunctional farming and food systems. This reflected the farmers’ perception of a lack of modern varieties suited for these systems as well as the ability of landraces to buffer risks of crop failure on marginal land.

Effect of Fertilization and Weed Management Practices on Weed Diversity and Hemp Agronomic Performance

The industrial hemp market is rapidly expanding, and best crop practices need to be assessed. This study aimed to determine the effect of fertilization and weed management on hemp crops and weed flora during the 2019 and 2020 growing seasons. Field experiments were laid out in a split–split plot design with three replicates: two hemp cultivars as main plots, three fertilization treatments as sub-plots, and three sub-sub-plots (weedy, weed-free, and herbicide application). For the computation of crop traits, 10 plants were randomly selected by each plot. Weed species were collected by quadrate for density and biomass weight determination. Increased fertilization rate positively affected plant height and dry biomass, while no impact was recorded on yield and yield components. The density and biomass of nitrophilous weeds were enhanced by fertilization, negatively affecting hemp growth. Marked differences were recorded on the competitive ability of cultivars since “Fedora 17” decreased the weed studied traits better than “Uso 31”. Herbicide application decreased the biomass of annual and perennial weeds by 38% and 13%, respectively, while it caused a reduction in hemp growth and yield of “Uso 31” plants. Further research should be conducted to address hemp yield losses under different cultural practices and weed control systems.

Weed Identification in Agricultural Fields Using Machine Learning Techniques

Weeds compete with crops for water, nutrients, and sunshine, which is one of the most detrimental restraints on crop development. They also constitute a danger to agricultural output. The loss of worldwide productivity due to weeds and pests is likely to rise over the next few years. Using herbicide spray particularly in the field where the weeds are present is an efficient technique to manage the problem. For the weed control system to be properly deployed, weeds must be accurately and precisely detected. Traditional weed management techniques, however, take a long time and a lot of human resources, and they may have an adverse effect on the environment. To overcome this a model called Automatic weed management, a potential remedy that makes use of deep learning and machine learning approaches, has emerged to deal with these issues. This method increases agricultural productivity and reduces herbicides.

Optimized Convolutional Neural Network for Robust Crop/Weed Classification

Precision farming makes extensive use of information technology, which also aids agronomists in their work. Weeds typically grow alongside crops, lowering the production of those crops. Weeds are eliminated with the aid of herbicides. Without knowing what kind of weed it is, the pesticide may also harm the crop. The weeds from the farms must be categorized and identified in order to be controlled. Automatic control of weeds is essential to enlarge crop production and also to avoid rigorous hand weeding as labor scarcity has led to a surge in food manufacturing costs, especially in the developed countries such as India. On the other hand, the advancement of an intelligent, reliable automatic system for weed control in real time is still challenging. This paper intends to introduce a new crop/ weed classification model that includes three main phases like pre-processing, feature extraction and classification. In the first phase, the input image is subjected to pre-processing, which deploys a contrast enhancement process. Subsequent to this, feature extraction takes place, where “the features based on gray-level co-occurrence matrix (GLCM) as well as gray-level run-length matrix (GLRM)” are extracted. Then, these extracted features along with the RGB image (totally five channels) are subjected to classification, where “optimized convolutional neural network” (CNN) is employed. In order to make the classification more accurate, the weight and the activation function of CNN are optimally chosen by a new hybrid model termed as the hybridized whale and sea lion algorithm (HW–SLA) model. Finally, the superiority of the adopted scheme is validated over other conventional models in terms of various measures.

Pengaruh Ekstrak Biji Durian dan Oksifluogen 240 g/L Terhadap Kematian Gulma di Perkebunan Kelapa Sawit

This study aims: (1) to determine the effect of crude extract of durian seeds on weed control in oil palm plantations, (2) to determine the effect of the herbicide oxyfluogen 240 g/L which is effective on weed control in oil palm plantations, (3) to determine the effect of interaction of crude extract of durian seeds and oxyfluogen herbicide on weeds in oil palm plantations. The method used in this study was a randomized block design with a factorial pattern. The first factor was durian seed extract (D) with a concentration consisting of 4 levels, namely: control (D0), 100 ml/L (D1), 200 ml/L (D2), 400 ml/L (D3). The second factor is the herbicide oxyfluogen (O) with a concentration consisting of 4 levels, namely: control (o0), 1 ml/L (O1), 2 ml/L (O2), 3 ml/L (O3). From these 2 factors, 16 treatments were obtained with 2 replications, and the number of samples was 32 sample plots, plot area 1 m2, distance between replicates 1 m from 2 factors. The results of data analysis showed that administration of durian seed extract and administration of oxyfluogen had a very significant effect on the percentage of weed mortality in oil palm plantations, but the interaction had no significant effect on the first week and second week after application. The best treatment was the application of a combination of 400 ml/L of durian seed extract with 3 ml/L of oxyfluogen which killed the highest weeds around 81% after two weeks of application. Durian seed extract has potential as a bioherbicide, which can be used as an alternative technique in weed control systems in oil palm plantations.

Efficiency for combinations of rimsulfuron with adhesives in maize crops

Topicality. Adhesives are an integral part of the weed control system in the maize crops, because they increase the efficiency of herbicide application. They significantly reduce the cost of plant protection products and increase their efficiency, as well as increase the adhesive properties of the herbicide solution to prevent its runoff and prolong its action. Development of new herbicides, constant weather and climate changes require to study further the effectiveness of the combined action of herbicides and adhesives. Among the adhesives for maize, it is generated interest such products as Synergent SOC, Eco Oil Spray, Esterlip, etc. Purpose. To reveal the effectiveness for combinations of herbicides with adhesives in the maize crops, as well as their impact on plant growth and development. Materials and Methods. The experimental scheme included the following combinations of rimsulfuron with adhesives: 1. Control (Rimsulfuron without adhesive); 2. Rimsulforon (40 g/ha) + Trend 90 (0.15 % working solution); 3. Rimsulforon (40 g/ha) + Synergent (0.15 % working solution); 4. Rimsulforon (40 g/ha) + Eco Oil Spray (0.15 % working solution); 5. Rimsulforon (40 g/ha) + Esterlip (0.15 % working solution); 6. Rimsulforon (35 g/ha) + Esterlip (0.15 % working solution); 7. Rimsulforon (25 g/ha) + Esterlip (0.15 % working solution). Results. The combination of rimsulfuron with adhesive Esterlip had the highest technical efficiency compared to other adhesives, in particular, on the redroot pigweed (Amaranthus retroflexus L.) was 75–100% (complete destruction) and lamb’s quarters (Chenopodium album L.) – 85.7–92.9 %, slightly less on common ragweed (Ambrosia arte-misiifolia L.) – 83.3%. Common purslane (Portulaca oleracea L.) was highly resistant to almost all combinations of rimsulfuron with adhesives. The highest maize yield of 8.99 t/ha was in the variant with Rimsulfuron (40 g/ha) + Esterlip. Reduced application rate of Esterlip to 25–35 g/ha decreased the maize yield to 7.34–7.65 t/ha, or by 1.34–1.65 t/ha (14.9–18.3 %) due to increased weed infestation of crops. The application of adhesives Trend 90, Synergen, Eco Oil Spray also decreased maize yields to 8.48 t/ha, 8.07 t/ha and 8.62 t/ha, respectively, which was less by 0.51 t/ha (5.6 %), 0.92 t/ha (10.2 %) and 0.37 t/ha (4.1 %). The lowest yield was in the control – 5.30 t/ha due to significant weed infestation of grain crops, which decreased by 3.69 t/ha (41.0 %) compared to the best variant (Rimsulfuron (40 g/ha) + Esterlip). Conclusions. Considering the ongoing development of new adhesives and herbicides for maize, as well as climate changes, it is necessary to continue research in this area to determine the most optimal ratio of herbicide rates with adhesives. Key words: maize, weeds, herbicides, adhesives, yield, technical efficiency

КОМПЛЕКСНАЯ СИСТЕМА ЗАЩИТЫ КАРТОФЕЛЯ ОТ СОРНЯКОВ, БОЛЕЗНЕЙ И ВРЕДИТЕЛЕЙ

Potatoes are among the crops that are heavily affected by diseases. To a large extent, this is due to the peculiarities of the biology of the potato plant. In the conditions of the North Caucasus region, the probability of the spread of late blight and various viral diseases is high. In addition, potatoes, like other crops, high-yielding varieties are most sensitive to climatic factors, their potential yield cannot be realized if they are not resistant to extreme conditions. In the southern regions of Russia, including in the Republic of Alania, such limiting factors should include, first of all, high summer temperatures and rather long dry or long rainy periods during the growing season of potatoes. Under the influence of high temperatures during the formation and growth of tubers, prolonged hot weather causes metabolic disorders, a decrease in yield; weakened plants are more affected by viral, viroid and mycoplasma diseases. In this regard, the most urgent issue is the identification of drought-resistant varieties and hybrids. In recent years, along with the immunological characteristics of varieties, more and more attention has been paid to their qualitative consumer properties, therefore, resistance to diseases, pests and weeds should be combined with the main economically useful qualities - yield, starchiness and others. The weed control system in landscape farming should be considered as an integral part of the management of the entire agricultural system. To build a weed control system, it is necessary, first of all, to know the actual and potential contamination of the object under examination (plot, field, crop rotation). The analysis of factors shows that one of the main reasons is a strong contamination of potato plantings with the floral composition of perennial, annual cereal and broad-leaved weeds, infestation with pests and diseases. Weeds, pests and diseases, having complex biological features, are characterized by strong adaptability to potato cultivation conditions, high competitive ability, harmfulness and on this basis reduce the yield of tubers, their quality in the absence of a scientifically-based comprehensive system for protecting plantings from them. In this regard, potato plants are characterized by low competitive ability compared to weeds, pests and diseases, and vulnerability to them, which necessitates the integrated use of protection methods at all stages of crop cultivation technology. At the same time, it is advisable to direct the agricultural technology of culture cultivation to create favorable conditions for the growth and development of potato plants, the dominant component of agrophytocenosis, increasing its competitive ability against harmful objects and reducing their harmfulness. Agroecological assessment of the conditions affecting the clogging of potato plantings, their infestation with pests and diseases allows us to note that this is facilitated by a decrease in the material and technical base and financial capabilities of agriculture, violation of farming systems, crop rotations, established technologies, lack of monitoring of the species composition of weeds, weak implementation of the results of scientific developments

Substantiation of the weed control system when placing grain production in microzones of the Central Chernozem region

The most important link in modern farming systems is the protection of crops from weeds. Only by taking effective measures to reduce the weediness of crops one can get a high yield of cultivated crops and high-quality products. On a field or plot with high weediness all other agricultural activities aimed at increasing crop yields will be ineffective. When planning for weed control, the grower must give priority to preventive and organizational measures. It is much easier to prevent weeding of agricultural land than to try to weed an already weeded area. Preventive measures include: seed cleaning; preparation of feed for feeding, allowing them to be cleaned of viable weed seeds; preparation of organic fertilizers (manure, composts) before applying them to the fields. An important measure that reduces the weediness of fields is the destruction of weeds on lands adjacent to fields: on unused plots, field edges, roadsides, edges of forest belts. Cleaning of weed seeds from wastes is necessary by means of agricultural machines and vehicles, as well as by means of containers.

Evaluation of weed control system using herbicides, for glyphosate-resistant Italian ryegrass in paddy levees in Aichi prefecture

Evaluation of weed control system using herbicides, for glyphosate-resistant Italian ryegrass in paddy levees in Aichi prefecture

Improved generalization of a plant-detection model for precision weed control

Lack of generalization in plant-detection models is one of the main challenges preventing the realization of autonomous weed-control systems. This paper investigates the effect of the train and test dataset distribution on the generalization error of a plant-detection model and uses incremental training to mitigate the said error. In this paper, we use the YOLOv3 object detector as plant-detection model. To train the model and test its generalization properties we used a broad dataset, consisting of 25 sub-datasets, sampled from multiple different geographic areas, soil types, cultivation conditions, containing variation in weeds, background vegetation, camera quality and variations in illumination. Using this dataset we evaluated the generalization error of a plant-detection model, assessed the effect of sampling training images from multiple arable fields on the generalization of our plant-detection model, we investigated the relation between the number of training images and the generalization of the plant-detection model and we applied incremental training to mitigate the generalization error of our plant-detection model on new arable fields. It was found that the average generalization error of our plant-detection model was 0.06 mAP. Increasing the number of sub-datasets for training, while keeping the total number of training images constant, increased the variation covered by the training set and improved the generalization of our plant-detection model. Adding more training images sampled from the same datasets increased the generalization further. However, this effect is limited and only holds when the new images cover new variation. Naively adding more images does not prepare the model for specific scenarios outside the training distribution. Using incremental training the model can be adapted to such scenarios and the generalization error can be mitigated. Depending on the discrepancy between the training set and the new field, finetuning on as little as 25 images can already mitigate the generalization error.

A Faster R-CNN-Based Model for the Identification of Weed Seedling

The accurate and rapid acquisition of crop and weed information is an important prerequisite for automated weeding operations. This paper proposes the application of a network model based on Faster R-CNN for weed identification in images of cropping areas. The feature pyramid network (FPN) algorithm is integrated into the Faster R-CNN network to improve recognition accuracy. The Faster R-CNN deep learning network model is used to share convolution features, and the ResNeXt network is fused with FPN for feature extractions. Tests using >3000 images for training and >1000 images for testing demonstrate a recognition accuracy of >95%. The proposed method can effectively detect weeds in images with complex backgrounds taken in the field, thereby facilitating accurate automated weed control systems.

Composition, structure, and level of weed diversity in oil palm plantation in Pagar Merbau Village, Tanjung Morawa, Indonesia

Weed vegetation growth affects the growth and production of oil palm plants. To control weeds in plantation land, especially by using herbicides or bioherbicides, weed vegetation analysis is needed. This research was conducted to determine the composition, structure, and level of diversity of weeds in oil palm plantations owned by the community of Pagar Merbau village, Tanjung Morawa District. The method used is a descriptive method with sampling technique done by porposive sampling. The results of the analysis showed that weeds found were 7 families, 10 species, and 3153 individuals. Weed species found were: Clidemia hirta, Borreria alata, Mimosa invisa, Setaria barbata, Ageratum conyzoides, Paspalum conjugatum, Ottochloa nodosa, Cyclosorus aridus, Calopogonium mucudoines, Ophioglossum reticulatum. Ottochloa nodosa is a type of weed that has the highest importance value index 66.52% (1323 individuals) and Setaria barbata is a type of weed that has the lowest important value index of 1.00% (4 individuals). Weed diversity index in this oil palm plantation is in the moderate category (H '= 1.3741). The weed control system to be carried out in this oil palm plantation must consider the dosage and types of herbicides and bioherbicides used so that it does not have the potential to reduce the level of diversity of weeds of grass or broadleaf weeds.

Assessing environmental impact of genetically modified seeds in Brazilian agriculture.

Genetically modified (GM) seeds have had relevant impacts on worldwide agriculture, even with a limited number of essential traits launched in the markets. The focus on platforms crops has favored the combination of traditional breeding, GM insertion, and diffusion in agriculture. One of the remarkable features of the GM traits has been the close link with pest and weed control systems. We investigate the environmental effects due to pesticides for two different GM seeds: insect resistant (IR) cotton and herbicide tolerant (HT) soybeans in a particular period of Brazilian agriculture, 2009–2013. We use a dataset on commercial farms' use of pesticides and biotechnology in Brazil to document environmental effects of GM traits. We explore within farm variation for farmers planting conventional and GM seeds to identify the effect of adoption on the environmental impact of pesticides measured as the quantity of active ingredients of chemicals and the Environmental Impact Quotient (EIQ) index. The findings show that the IR trait reduces application of insecticides by 22% and the associated environmental impact by 20% the environmental impact of insecticides. However, for HT traits, we find that application of herbicides increases by 55.8% and the associated environmental impact by 44.4%, showing a significant increase in the EIQ. The HT results are driven by an increase of less toxic herbicides elevenfold larger than the decrease in less toxic ones, which we interpret as evidence of weak substitutability between herbicides of different toxicity levels. Addressing what happened in the last decade, the paper also presents a view of the transformations in GM usage in Brazil, focusing on the considerable success in adopting stacked genes. Future perspectives point to a more diversified menu of technologies, crops, and adopting countries, going beyond platform crops and more prominent agriculture exporters.

WEED DETECTION AND CLASSIFICATION

In the agricultural sector, weed detection and categorization are of critical technical and financial relevance. It is possible to automate various processes, such as shape, colour, and texture, in weed control systems. Building a machine vision weed control system that can locate weeds in real-time is the aim of this article. The system is designed to categorise photos into wide and narrow classes for on-the-fly spraying of selective herbicides. The developed Edge Link Detector-based algorithm has been put to the test on weeds in various areas, and the results have revealed how good the algorithm is at identifying weeds. Additionally, the outcomes demonstrate a very trustworthy performance on weeds under various field circumstances. Over 240 sample photos (wide, narrow, and no or little weeds) including 100 samples from broad weeds, 100 samples from narrow weeds, and the remaining 40 samples from no or little weeds were classified with over 93 percent accuracy, according to the results analysis.

Effect of 2,4-D formulation on volatility under field conditions

AbstractAuxinic herbicides have been commonly used in production systems for broadleaf weed control for many years. One potential negative aspect to their use is their propensity to volatilize and move away from the treated area after application. This research examined three herbicide formulations and their relative amounts of vaporization following application under field conditions in Knoxville, TN, in 2017, 2018, and 2019. Herbicide treatments evaluated included 2,4-D choline, 2,4-D amine, and the diglycolamine (DGA) salt of dicamba. Ten field studies were conducted with major parameters including air sampler height (0.3 and 1.3 m) and applied surface condition (dry wheat stubble or green-plant vegetation). The relative volatility indicated by the study was that dicamba > 2,4-D choline = 2,4-D amine. Detected herbicide concentrations were numerically higher at the 0.3-m sampling height and in the green-plant surface condition. These results confirm that dicamba is more volatile than 2,4-D and that there was no difference in vapor emissions between the amine and choline salts of 2,4-D under field conditions.

AN AUTONOMOUS BRAKING CONTROL SYSTEM FOR A 2017 YAMAHA GRIZZLY 700

Weed control is an important issue for environmental protection all around the world. Traditional hand weed control is laborious whereas chemical control is costly and a threat to the atmosphere. A chemical patch weed control system is an optimized system but lacks cheap technical equipment. This research outlines a design process and test of a braking system that can be applied during the designing of an autonomous braking system for a 2017 Yamaha Grizzly 700. The system is intended to be used as an autonomous weed chemical spraying. A bolt-on approach that did not require any manipulation of the stock, an internal braking system was followed to reduce the complexity and installation time of multiple systems. Three different types of autonomous braking system solutions were initially investigated, with the linear actuator solution being decided on through the assistance of a weighted decision matrix. The system was designed around a 30 kg hand force; however, a spare actuator of approximately 20 kg of force was repurposed and used instead. Finite element analysis concluded that all major components within the proposed system were suitable for a lifetime of at least 1,000,000 cycles with a mild steel yield stress failure criterion of 370 MPa. A stationary test for the system was conducted to determine the success of the system, which pushed the brake lever approximately 25% of its disengaged handlebar to lever length. The resulting system met the requirements of the expectation and could be used to apply the ATV’s brakes autonomously while retracting the gear interlocking mechanism enough to change gears.

Weeding Effectiveness and Changes in Soil Physical Properties Using Inter-Row Hoeing and a Robot

Weed control is one of the most important technological operations to ensure crop yield and quality in ecological sugar beet production. However, conventional mechanical weed control is labor- and time-intensive and has adverse effects on the soil and the environment. The aim of this study was to experimentally investigate the influence of conventional mechanical and robotic weed control systems on soil properties and to assess the effectiveness of these different weed control methods in ecological sugar beet production. This study examines two different weed control systems: robotic weed control (RWC) and conventional weed control (CWC). Field experimental studies were carried out with a solar-powered field robot and conventional inter-row cultivation (CWC1—first cultivation, CWC2—second cultivation) to determine the effectiveness of mechanical weed control in ecological sugar beet crops. The influence of different weed control systems on the physical properties of the soil in the contact zone between the soil and the tires of weed control machines was investigated. The results showed that the average weed control effectiveness inter-row was higher in the RWC (81%) compared to that in the CWC2 (46%). The overall weed control effectiveness of the robotic weed control in the sugar beet inter-row and intra-row was around 49%. The measurements showed that the weed control process reduced the soil moisture and temperature in all treatments tested. Experimental studies have confirmed that the weed control operation, although carried out with relatively lightweight robots, also has an impact on soil bulk density. RWC weed control resulted in an average increase of 0.16 g cm–3 in soil bulk density in the topsoil layer (0–10 cm) after weeding. Both CWC1 and RWC increased soil penetration resistance (PR). For CWC1, the average increase in topsoil PR after weed control was 20%, while for RWC, the increase was marginal, only around 1%. Automated precision weed control by self-propelled solar-powered field robots is an important solution to reduce the need for tedious and time-consuming manual weeding.

Effect of Labor Saving and Production Enhancement Technologies on Cotton Production in Omiya Anyima Sub County-Kitgum District

The study made an assessment of the effect of labor saving and production enhancement technologies on cotton production in Omiya Anyima sub County-Kitgum District. The specific objectives were to: identify the types of labour saving and productivity enhancement technologies being employed by farmers in cotton production, compare cotton production by farmers using labour saving and productivity enhancement technologies and those not using the technologies, identify areas of research that could enhance cotton productivity and lessen drudgery and excessive labour use, and the challenges associated with the use of labor saving and productivity enhancement technologies in cotton production and recommend some innovative solutions. The study was cross-sectional in nature employing qualitative and quantitative approaches for data collection and analysis. A questionnaire was used to capture information from 376 respondents. The study identified different labour saving and productivity enhancement technologies used in the area such as; animal draft power, tractors, sprayers, herbicides, fertilizers and pesticides. An average production difference between adopters and non-adopters of labour saving and productivity enhancement technologies were 519.8 kilograms per acre in a season. The identified areas of research to enhance cotton productivity and lessen drudgery included; automated irrigation systems, automated weed control systems, auto-guided agricultural systems, automatic motorized sprayers while and robotic planters. Adoption and use of labour saving and productivity enhancement technologies was influenced by factors like economic status, land tenure system, lack of credit to services, and high costs of procurement and operations. The study concluded that Labor Saving and Production Enhancement Technologies have a positive effect on Cotton Production but the users were still affected by challenges like poverty, low knowledge on use, lack of accessibility, costs of hire, capital and land tenure system. The study therefore recommended more education for farmers on the technologies, revisiting land tenure policies to allow farmers have access to bigger land to apply the technologies, supporting farmers through credit services and more capacity building and external support.

Key technologies of machine vision for weeding robots: A review and benchmark

• This paper reviews the research status of typical machine-vision-based weeding robots. • This paper has evaluated the performance of eight baseline methods that are based on deep learning on a public dataset. • This paper presents the application of object detection algorithms based on deep learning to weed identification. Due to its obvious advantages in saving labor and pesticides, weeding robots are one of the key technologies for modern and sustainable agriculture and have attracted increasing attention from researchers and developers. Some papers on machine-vision-based weeding robots have been published in recent years, yet there is no clear attempt to systematically study these papers to discuss the components of a robotic weed control system, such as visual navigation, weed detection and directional weeding. In this paper, typical machine-vision-based weeding robots proposed or constructed in the last 30 years, together with a few open datasets for weed detection, are reviewed. Key technologies such as image preprocessing, image segmentation, navigation line extraction, and weed recognition based on machine learning (ML) or deep learning (DL) for weeding robots are discussed. To illustrate the application of DL algorithms to weed detection, this paper provides weed object detection results and a comparative analysis of eight baseline methods based on DL using a public dataset. The study found that there are still many issues that need to be addressed in each part of the robotic weeding control system. Because of environmental variation and system complexity, machine-vision-based weeding robots are still in their early stages. The results of the systematic review provide an understanding of innovative trends in the use of machine vision in weeding systems and references for future research on weeding robots.

A Comprehensive Survey for Weed Classification and Detection in Agriculture Lands

In modern agriculture, there are many technologies that improve the performance of farming and production of the main plant. Few such important technologies are the machine learning and deep learning for the automatic weed classification and detection. It is very useful to control or remove the weeds in the agriculture lands by automated weed control systems. This paper gives the overall survey of the existing research of the weed classification and detection using various techniques present in the digital image processing, machine learning and deep learning field. It also covers the merits, demerits and challenges of the existing methods and the future scope of the research.