Agricultural machinery automatic navigation technology.

In this paper, we review, compare, and analyze previous studies on agricultural machinery automatic navigation and path planning technologies. First, the paper introduces the fundamental components of agricultural machinery autonomous driving, including automatic navigation, path planning, control systems, and communication modules. Generally, the methods for automatic navigation technology can be divided into three categories: Global Navigation Satellite System (GNSS), Machine Vision, and Laser Radar. The structures, advantages, and disadvantages of different methods and the technical difficulties of current research are summarized and compared. At present, the more successful way is to use GNSS combined with machine vision to provide guarantee for agricultural machinery to avoid obstacles and generate the optimal path. Then the path planning methods are described, including four path planning algorithms based on graph search, sampling, optimization, and learning. This paper proposes 22 available algorithms according to different application scenarios and summarizes the challenges and difficulties that have not been completely solved in the current research. Finally, some suggestions on the difficulties arising in these studies are proposed for further research.

Large-scale and cost-efficient agrivoltaics system by spectral separation.

Agrivoltaics (AV) offers a promising solution to address both food and energy crises. However, crop growth under photovoltaic (PV) conditions faces substantial challenges due to insufficient light transmission. We propose a large-scale and cost-effective spectral separated concentrated agricultural photovoltaic (SCAPV) system. The system utilizes concentrator modules, cell components, and dual-axis tracking systems to enhance power conversion efficiency (PCE), achieving a maximum PCE of 11.6%. After three years of successful operation, a 10 kWp power plant achieved an average annual electricity generation exceeding 107 MWh/ha. The results showed higher yields of various crops, including ginger and sweet potatoes, and significant improvements in soil moisture retention compared to open air. The improvements in PCE and microclimate validate the scalability of the SCAPV, which provides better plant conditions and cost-effectiveness, with an estimated cost reduction of 18.8% compared to conventional PV power plant. This study provides valuable insights and directions for improvement in AV.

Coordinative Management of Soil Resources and Agricultural Farmland Environment for Food Security and Sustainable Development in China.

Major problems in China's pursuit of sustainable agricultural development include inadequate, low-quality soil and water resources, imbalanced regional allocation and unreasonable utilization of resources. In some regions, overexploitation of soil resources and excessive use of chemicals triggered a web of unforeseen consequences, including insufficient use of agricultural resources, agricultural non-point source pollution and land degradation. In the past decade, China has changed its path of agricultural development from an output-oriented one to a modern, sustainable one with agricultural ecological civilization as its goal. First, the government has formulated and improved its laws and regulations on soil resources and the environment. Second, the government has conducted serious actions to ensure food safety and coordinated management of agricultural resources. Third, the government has planned to establish national agricultural high-tech industry demonstration zones based on regional features to strengthen the connection among the government, agri-businesses, scientific community and the farming community. As the next step, the government should improve the system for ecological and environmental regulation and set up a feasible eco-incentive mechanism. At the same time, the scientific community should strengthen the innovation of bottleneck technologies and the development of whole solutions for sustainable management in ecologically fragile regions. This will enhance the alignment between policy mechanisms and technology modes and effectively promote the sustainable development of agriculture in China.

Large Semi-Membrane Covered Composting System Improves the Spatial Homogeneity and Efficiency of Fermentation.

Homogenous spatial distribution of fermentation characteristics, local anaerobic conditions, and large amounts of greenhouse gas (GHGs) emissions are common problems in large-scale aerobic composting systems. The aim of this study was to examine the effects of a semi-membrane covering on the spatial homogeneity and efficiency of fermentation in aerobic composting systems. In the covered group, the pile was covered with a semi-membrane, while in the non-covered group (control group), the pile was uncovered. The covered group entered the high-temperature period earlier and the spatial gradient difference in the group was smaller compared with the non-covered group. The moisture content loss ratio (5.91%) in the covered group was slower than that in the non-covered group (10.78%), and the covered group had a more homogeneous spatial distribution of water. The degradation rate of organic matter in the non-covered group (11.39%) was faster than that in the covered group (10.21%). The final germination index in the covered group (85.82%) was higher than that of the non-covered group (82.79%) and the spatial gradient difference in the covered group was smaller. Compared with the non-covered group, the oxygen consumption rate in the covered group was higher. The GHG emissions (by 30.36%) and power consumption in the covered group were reduced more significantly. The spatial microbial diversity of the non-covered group was greater compared with the covered group. This work shows that aerobic compost covered with a semi-membrane can improve the space homogeneity and efficiency of fermentation.

Machine Learning for Plant Stress Modeling: A Perspective towards Hormesis Management.

Plant stress is one of the most significant factors affecting plant fitness and, consequently, food production. However, plant stress may also be profitable since it behaves hormetically; at low doses, it stimulates positive traits in crops, such as the synthesis of specialized metabolites and additional stress tolerance. The controlled exposure of crops to low doses of stressors is therefore called hormesis management, and it is a promising method to increase crop productivity and quality. Nevertheless, hormesis management has severe limitations derived from the complexity of plant physiological responses to stress. Many technological advances assist plant stress science in overcoming such limitations, which results in extensive datasets originating from the multiple layers of the plant defensive response. For that reason, artificial intelligence tools, particularly Machine Learning (ML) and Deep Learning (DL), have become crucial for processing and interpreting data to accurately model plant stress responses such as genomic variation, gene and protein expression, and metabolite biosynthesis. In this review, we discuss the most recent ML and DL applications in plant stress science, focusing on their potential for improving the development of hormesis management protocols.

Systematic review of occupational hazards at postharvest grain operations.

INTRODUCTION: Agriculture stands out in relation to the high number of occupational incidents and diseases. In this sense, grains postharvest operations, such as receiving, precleaning, drying, storage and shipping the grains, are highlighted in the number of injuries and fatalities. AIM: To identify and extract qualitative and quantitative data related to the main occupational hazards present in grains postharvest operations at preprocessing and storage facilities. METHODS: A systematic review was carried out in the databases of Science Direct, Scopus and Web of Science for papers published between 1980 and 2019. The abstract should have described a study related to any occupational hazard (physical, chemical, biological, ergonomic and mechanical) and at least one of the occupational hazards should be related to any postharvest operations. RESULTS AND DISCUSSIONS: In total, 42% of 38 analysed papers were published between 2015 and 2019. Three journals were responsible for 45% of publications related to occupational hazards present in grains postharvest operations. The most part of analysed publications related to confined spaces, grain entrapment, machine entanglement and falls hazards are related to Purdue University's Agricultural Safety and Health Program which applied research in occupational safety at grains postharvest. CONCLUSIONS: The creation of standardised internationals can collaborate to reduce occupational risks in grain storage units. It is suggested the development of monitoring technologies to obtain real-time information on noise, dust, gases and heat in postharvest operations and equipment. The use of intelligent algorithms can create prevention mechanisms for possible occupational risks and avoid injuries to employees.

Oscillation effect dataset on the measurement accuracy of load-cell sensor applied to the weigh basket.

The dataset in the form of weight, which will be closely related to the moisture content of agricultural products that have been dried in a mechanical dryer, is important to know precisely. Changes in these properties occur very quickly, so that it is important to prepare a system that is integrated with the mechanical dryer, especially the fluidized dryer type. On the one hand, the fluidizing dryer causes a shock to the weigh basket, connected to the weighing system mechanism. Therefore, this article collects a dataset of the weight of agricultural products (maize and soybeans) that have experienced shocks on two weigh baskets that could potentially be used in fluidization-type mechanical dryers. A load-cell sensor connected to a weigh basket is used to measure the weight of the agricultural product. A new generation of IoT techniques will control the sensor. Its microcontroller will send data to the cloud server via an internet network. There were a total of 120 treatments in the raw dataset. For agriculture engineering researchers, this data will provide benefits in measuring the weight of agricultural material in the form of grain dried in a mechanical dryer, especially the type of fluidized dryer, it can be more accurately explained.

In Planta Nanosensors: Understanding Biocorona Formation for Functional Design.

Climate change and population growth are straining agricultural output. To counter these changes and meet the growing demand for food and energy, the monitoring and engineering of crops are becoming increasingly necessary. Nanoparticle-based sensors have emerged in recent years as new tools to advance agricultural practices. As these nanoparticle-based sensors enter and travel through the complex biofluids within plants, biomolecules including proteins, metabolites, lipids, and carbohydrates adsorb onto the nanoparticle surfaces, forming a coating known as the "bio-corona". Understanding these nanoparticle-biomolecule interactions that govern nanosensor function in plants will be essential to successfully develop and translate nanoparticle-based sensors into broader agricultural practice.

Comparison between conventional human energy measurement and physical human energy measurement methods in wetland rice production.

Measurement of human energy expenditure during crop production helps in the optimization of production operations and costs by identifying steps which that can benefit from the use of appropriate mechanization technologies. This study measures human energy expenditure associated with all 6 major rice (Oryza sativa L.) cultivation operations using two measurement methods-i.e. conventional human energy expenditure method and direct measurement with a Garmin forerunner 35 body media. The aim of this study was to provide a detailed comparison of these two methods and document the human energy costs in a manner that will identify steps to be taken to help optimize agricultural practices. Results (mean + 95%CL) revealed that the total human energy expenditure obtained through the conventional method was 25.5% higher (33.3 ± 1 versus 26.6 ± 1.3) in transplanting and 26.1% higher (30.3 ± 1.9 versus 24.0 ± 2.1) than the human energy expenditure recorded using the Garmin method in broadcast seeding method. Similarly, during the harvesting operation, the conventional measurement and Garmin measurement methods differed significantly, with the conventional method the human energy expenditure was 89.9% higher (3.2 ± 0.4 versus 1.68 ± 0.2) in the fields using the transplanting and 88.7% higher (3.3 ± 0.5 versus 1.8 ± 0.3) in the fields using the broadcast seeding than the human energy expenditure recorded using the Garmin method. When using Garmin method, the human energy expenditure in the case of using the midsize combine harvester was 13.49% lesser (592.4 ± 67.2 versus 522.0 ± 75.1) than the case of using conventional one. Results based on heart rate also indicated that operations such as tillage were less intensive (72 ± 3.3 bpm) compared with operations such as chemicals spraying (135 ± 4 bpm). Although we did not have a criterion measure available to determine which method was the most accurate, the Garmin measurement gives an estimate of actual physical human energy expended in performing a specific task with consider all conditions and thus more information to aid in identifying critical operations that could be optimized and mechanized.

Torrefaction of non - oil Jatropha curcas L. (Jatropha) biomass for solid fuel.

The use of non-oil Jatropha biomass in the energy mix as a solid fuel offers the most effective ways of utilising such resource. However, available information indicates that biomass has negative inherent properties which lower its fuel value. This negative effect can be improved by slow pyrolysis process called torrefaction where the biomass is heated in the range of 200 °C to 300 °C. In the present investigation the effects of torrefaction temperature on the solid fuel value of different Jatropha biomass materials were determined. Consequently, three types of Jatropha biomass namely; seed cake, stem and fruit cover were considered under five temperature levels (200 °C, 225 °C, 250 °C, 275 °C, 300 °C). Analysis of Variance (ANOVA) revealed that there were significant differences (P > 0.05) in bulk density, hygroscopicity, energy content and ultimate etc. The statistical analysis results indicated that there was biomass type and torrefaction temperature interaction effects on the ultimate analysis, bulk density, hygroscopicity, energy content and energy yield. The interaction effects of the factors under investigation were not observed in mass yield. Increase in torrefaction temperature generally reduced the equilibrium moisture content and volatile matters across the biomass types. However fixed carbon, carbon content, ash content and energy density were increased across the biomass types as the temperature was increased from 200 °C to 300 °C. The torrefied Jatropha seed cake biomass showed relatively enhanced fuel characteristics than the torrefied stem and the torrefied fruit husk when considering the properties under investigation.

Performance evaluation of maize hybrids in inner-plains of Nepal.

Hybridization plays a vital role in increasing the production and productivity of maize. Evaluating maize hybrids in a specific environment is a key task for the hybrid maize program. The objective of this study was to identify a promising maize hybrid for winter planting in inner terai regions. Ten maize hybrids were evaluated in a randomized complete block design (RCBD) with three replications during the winter season of 2018 and 2019 at the research field of Purwanchal Agriculture Campus, Jhapa, Nepal. The results suggested that among tested hybrids, P3396 (11.18 tons ha-1), Shresta (10.67 tons ha-1), and Rampur Hybrid 6 (10.37 tons ha-1) produced significantly higher yield in 2018 whereas P3396 (11.10 tons ha-1), Shresta (10.20 tons ha-1), and Ganga Kaveri (10.03 tons ha-1) were the ones with the highest grain yield in 2019. Comparing both years, P3396 and Shresta consistently outperform the other hybrids in terms of grain yield, which is an important traits for the farmers. Correlation studies suggested that ear weight and thousand-grain weight showed a positive significant correlation with grain yield. Therefore, we suggest P3396 and Shresta as promising hybrids for the maize growers in the inner terai regions of Nepal.

Reduction of the acidity and peroxide numbers of tengkawang butter (Shorea stenoptera) using thermal and acid activated bentonites.

Tengkawang fat (Shorea stenoptera), from an indigenous plant of the Kalimantan forest, has excellent potential as an alternative source of vegetable fat because it has a high level of fatty acids composition. Activated natural bentonite can be used as a bleaching agent to improve the quality of tengkawang fat. This research aims to reduce the acidity, peroxide number values and identify the physicochemical properties (fatty acid composition, nutrients, and thermal) of tengkawang butter. Initially, tengkawang samples from Nanga Yen and Sintang were pre-treated using the degumming process with 1% phosphoric acid and the neutralization process with a 1 M NaOH 10% w/w solution. The results show that the acidity (mg NaOH/g) of the tengkawang fat samples was reduced from 11.00 to 3.36 when using bentonite activated at 200 °C. The bentonite activated with 0.5 M HCl reduced the acidity to 3.61. The peroxide number (meq O2/kg) of the tengkawang fat samples was reduced from 9.45 to 4.84 and 3.47 by bleaching with thermal-activated and acid-activated bentonites, respectively. Peroxide value correlates with ß-carotene content. The smaller of the ß-carotene content, the smaller the peroxide value. The acidity, peroxide number, and iodine number values from tengkawang fat after treatment adhere to the SNI 2903: 2016 standard. The main content of fatty acids in tengkawang fat is palmitic acid, stearic acid, and oleic acid. These results show that both products are suitable for the food industry in terms of the acid and peroxide numbers. The application of this research results will assist local people in increasing the economic value of the product from tengkawang plant, which is an indigenous plant from Kalimantan.

Decision-level fusion of Sentinel-1 SAR and Landsat 8 OLI texture features for crop discrimination and classification: case of Masvingo, Zimbabwe.

Radar imagery have few polarization bands which can limit the ability to do traditional digital classification. Harmonization of Sentinel-1 and Landsat 8 data despite having complementary texture information can be a challenge. The objectives of this paper are to explore texture features derived from Landsat 8 OLI and dual-polarized Sentinel-1 SAR speckle filtered and unfiltered backscatter, to aggregate classification results using Decision-Level Fusion (DLF), and to evaluate the performance of decision-level fused maps. Gray Level Co-occurrence Matrix (GLCM) is employed to derive sets of seven texture features for Landsat 8 bands and VV + VH backscatter using 5 × 5, 7 × 7, 9 × 9, and 11 × 11 window sizes. Each texture feature is stacked with a respective source image and classified using Support Vector Machine (SVM). Classified maps from the best three performers from both speckle filtered and unfiltered are aggregated with classified maps from Landsat 8 using plurality voting algorithm and compared using Z-test. Results indicate an overall classification accuracy of 96.02% from DLF images of Landsat and non-speckle filtered maps, whereas Landsat and speckle filtered achieved 94.69%. The best texture information are derived from the blue band followed by the red band, whereas speckle unfiltered textures performed better than speckle filtered textures. We conclude that integration of Landsat 8 and Sentinel-1, either speckle filtered or unfiltered, improves crop classification and speckles do not have statistically significant effects (p = 0.1208).

Non-destructive characterization of physical and chemical clogging in cylindrical drip emitters.

Characteristics and deposition pattern of clogging material on cylindrical drip emitters was studied using non-destructive methods of evaluation. Two sets of four cylindrical emitter samples were collected from farm lands. One set of sample emitters was analyzed using Computed Tomography (CT). Other set was dissected and the clogging material extracted was analyzed using Energy Dispersive X-Ray Fluorescence (EDXRF) and X-Ray Diffraction (XRD). CT scans revealed the geometric properties of emitters and the spread of clogging material on the emitter surface. EDXRF analysis found statistically significant inverse relationship between the proportion of physical clogging and chemical clogging materials. XRD analysis indicated presence of physical and chemical clogging materials in their crystalline forms. Emitters having transverse flow path and the boundary optimized with curvature found with the least deposition of physical clogging materials. Corresponding proportion of chemical clogging (as Ca) was found to be much higher. All the samples were found with more clogging material closer to the outlets. Efforts to optimize emitter geometry shall also take into account the outlet area optimization and chemical clogging for obtaining best results.

Towards an optimal hybrid solar method for lime-drying behavior.

Lime is one of the most commonly consumed medicinal plants in Indonesia, which must be dried to preserve its quality, but mostly by using traditional, ineffective drying method. Therefore, this study aims to investigate lime drying process a hybrid solar drying method. The hybrid solar dryer consisted of a solar dryer and Liquefied Petroleum Gas as the supplementary heater. The drying process was conducted until there was no significant weight decrease, with the drying temperature of 40, 50, 60, 70, and 80 °C. Thin-layer modeling and quality analysis were also conducted. The experimental results indicated that 5 h was required to sufficiently dry the lime at 80 °C, while drying at 40 °C took 24 h to finish. The drying rate curve of lime suggested that lime drying mostly happened during the falling-rate period. Moreover, the average efficiency of the hybrid solar dryer ranged from 5.36% to 38.61%, which increased with temperature. From the 10 thin-layer drying models used, the Wang and Singh model was the most suitable to describe the drying behavior of lime. The effective diffusivity values of the limes and the activation energy value during hybrid solar drying were within their respective acceptable range for agricultural products. However, as the drying temperature was increased from 40 to 80 °C, the total phenolic content and vitamin C content decreased, from 87.3 to 27.8 mg GAE/100 g dry limes and 0.118 to 0.015 ppm, respectively. It can be concluded that hybrid solar dryer is able to sufficiently dry the lime, with acceptable drying time and dryer efficiency, although using high drying temperature will decrease the quality of dried lime. Further modifications and improvements to the hybrid solar dryer are required to maximize the quality of dried lime while still maintaining fast and effective drying process.

A computer system supporting agricultural machinery and farm tractor purchase decisions.

Operational research, i.e. searching for optimal solutions in a situation of uncertainty and risk, can also be used to support decisions to purchase expensive agricultural machinery. Although Polish farmers receive subsidies from the EU, it does not mean they do not need to make well-thought-out purchases, because wrong purchase decisions will have long-term consequences while using machinery. The article presents the results of the IFOP - the system which has been available on the Internet for several years. It collects data on farming machinery and vehicles based on users' voluntary but subjective opinions. The authors of this article developed an original multi-criteria method of evaluating the quality of these specific products, which enabled them to make relevant rankings of brands. It is an algorithmic-heuristic method, which uses pairwise comparison tools to determine the significance ratios of the criteria. This article presents the results of the 1st and 2nd IFOP edition (Race Ranking), which included several dozen brands of tractors registered in Poland. More than fifty qualitative (Q) and non-qualitative (C) traits of farm tractors were taken into account. According to Polish farmers, Valtra - a Finnish brand of farm tractors, part of the AGCO concern, was the most versatile (Q = 4.39 and Q&C = 4.23). These tractors received the best opinions for their functionality, durability, ergonomics and safety.

Characterization of the acyl-ACP thioesterases from Koelreuteria paniculata reveals a new type of FatB thioesterase.

Koelreuteria paniculata is a deciduous tree, popular in temperate regions for its ornamental value, which accumulates unusual cyanolipids in its seeds. The seed oil of this plant is rich in the unusual cis-11-eicosenoic fatty acid (20:1, or gondoic acid), a monounsaturated oil of interest to the oleochemical industry. In higher plants, de novo fatty acid biosynthesis takes place in the plastids, a process that is terminated by hydrolysis of the thioester bond between the acyl moiety and the ACP by acyl-ACP thioesterases. The specificity of acyl-ACP thioesterases is fundamental in controlling the fatty acid composition of seed oil. To determine the mechanisms involved in fatty acid biosynthesis in K. paniculata seeds, we isolated, cloned and sequenced two cDNAs encoding acyl-ACP thioesterases in this plant, KpFatA and KpFatB. Both of them were expressed heterologously in Escherichia coli and characterized with different acyl-ACP substrates. The K. paniculata FatB2 displayed unusual substrate specificity, so that unlike most FatB2 type enzymes, it displayed preference for oleoyl-ACP instead of palmitoyl-ACP. This specificity was consistent with the changes in E. coli and N. benthamiana fatty acid composition following heterologous expression of this enzyme. KpFatB also showed certain genetic divergence relative to other FatB-type thioesterases and when modelled, its structure revealed differences at the active site. Together, these results suggest that this thioesterase could be a new class of FatB not described previously.

Nexus between light and culture media on morphogenesis in Bacopa monnieri and saponin yield thereof.

Bacopa monnieri, a well-documented nootropic plant of high commercial global demand had been explored for its effect in alleviating other diseases and symptoms. This is primarily attributed to different phytocompounds present in the plant. One of the major constituents among them are saponins. However, variation in agro-climatic conditions and choice of germplasm often affect the growth rate and yield of phytocompounds that significantly impact the efficacy of the plant and its extract. Tissue culture has been attempted to improve the yield of phytocompounds but is often restricted by higher cost and scalability. Current study explores the role of commercial hydroponic media 'Leafy 200' vis-à-vis Murashige and Skoog (MS) media, under different color and intensity of lights, on plant morphogenesis, biomass and saponin yield. Blue light induced more shoot differentiation than normal white light. Statistical studies performed using fractional factorial design showed no significant variations in the yield of saponins among the extracts. The study suggests that hydroponic culture to be a sustainable solution and possible substitute to tissue culture that may be exploited for scalable cultivation of the plant.

Performance evaluation of digestate spreading machines in vineyards and citrus orchards: preliminary trials.

This research was carried out to evaluate a local biogas plant's solid fraction digestate spreading in a citrus orchard and vineyard. Three spreaders were tested: a broadcast manure spreader in the citrus orchard, and two cylindrical-shaped spreaders in the vineyard; the first one working in broadcast configuration, the second one in localised configuration. Experimental tests assessed effective work time, mean work speed, digestate flow rate and longitudinal and transverse spreading uniformity. In the citrus orchard, the digestate was mainly spread in the centre of the inter-row (around 66%), with low variability between inter-rows (coefficient of variation (CV) equal to 2.7%) and much higher variability within inter-rows (CV = 31.4%). The effective work time was about 28% of total field time and real work capacity was about 0.96 ha h-1. In the vineyard, broadcast spreading released more on the right compared to the left (ratio 1.74) due to distributor disc rotation, whereas localised spreading was more uniform. Overall, variability between inter-rows had CV = 15.1% and within inter-rows CV = 33.3%. Real work capacity was about 0.16 ha h-1 for broadcast spreading and 0.26 ha h-1 for localised spreading. A preliminary economic evaluation, based on sub-contractor tariffs, produced the mean tariff for transaction and spreading costs of digestate in farms near the biogas plant.

An automatic visible-range video weed detection, segmentation and classification prototype in potato field.

Weeds might be defined as destructive plants that grow and compete with agricultural crops in order to achieve water and nutrients. Uniform spray of herbicides is nowadays a common cause in crops poisoning, environment pollution and high cost of herbicide consumption. Site-specific spraying is a possible solution for the problems that occur with uniform spray in fields. For this reason, a machine vision prototype is proposed in this study based on video processing and meta-heuristic classifiers for online identification and classification of Marfona potato plant (Solanum tuberosum) and 4299 samples from five weed plant varieties: Malva neglecta (mallow), Portulaca oleracea (purslane), Chenopodium album L (lamb's quarters), Secale cereale L (rye) and Xanthium strumarium (coklebur). In order to properly train the machine vision system, various videos taken from two Marfona potato fields within a surface of six hectares are used. After extraction of texture features based on the gray level co-occurrence matrix (GLCM), color features, spectral descriptors of texture, moment invariants and shape features, six effective discriminant features were selected: the standard deviation of saturation (S) component in HSV color space, difference of first and seventh moment invariants, mean value of hue component (H) in HSI color space, area to length ratio, average blue-difference chrominance (Cb) component in YCbCr color space and standard deviation of in-phase (I) component in YIQ color space. Classification results show a high accuracy of 98% correct classification rate (CCR) over the test set, being able to properly identify potato plant from previously mentioned five different weed varieties. Finally, the machine vision prototype was tested in field under real conditions and was able to properly detect, segment and classify weed from potato plant at a speed of up to 0.15 m/s.