Tree Rows Research Articles

TEHNOLOGII ȘI SOLUȚII CONSTRUCTIVE PRIVIND MANAGEMENTUL INTERVALULUI DINTRE RÂNDURILE DE VIȚĂ DE VIE ȘI POMI FRUCTIFERI

The management of inter-row space of vineyards and fruit trees has emerged as an essential approach in sustainable agriculture, optimizing resource use and improving ecosystem services. This paper reviews a range of innovative technologies and solutions aimed at revolutionizing line management practices. Modern sensing and monitoring systems provide real-time data on soil moisture, nutrient levels, and plant health, facilitating precision row-to-row management. Furthermore, techniques for grassing the space between rows of vines and fruit trees are important for space management, ensuring good air circulation and facilitating agricultural activities such as maintenance and harvesting. In addition, the advent of inter-row seeding machines simplified the implementation of cover crops. These machines use advanced seed delivery mechanisms, precisely distributing the cover seed into the spaces between the rows. This not only encourages soil health and erosion prevention but also mitigates weed competition, increasing the overall resilience of the agroecosystem. The purpose of this review is to discuss the combination of state-of-the-art technologies such as 3D LIDAR technology, intelligent systems used for inter-row management of vines and fruit trees, and inter-row solar panel systems, all these examples have revolutionized inter-row management in vineyards and orchards. This holistic approach optimizes resource allocation, improves soil health, and encourages sustainable agricultural practices, paving the way for greener and more resilient inter-row spaces in modern agroecosystems.

Drivers of tree establishment in planted windbreaks and riparian buffers: A case study of farms in southern Quebec, Canada

Successfully established windbreaks and riparian buffers contribute to protection of soils, crops, watercourses and biodiversity, and help to combat climate change. To improve establishment success of trees planted to form these agroforestry systems, identifying the factors influencing their survival and growth is crucial. We related survival and size of trees planted in windbreaks and riparian buffer strips to 23 abiotic, biotic, structural and technical explanatory factors using multiple generalized linear models. We sampled 52 windbreaks and 26 riparian buffer strips planted in different cultivated fields in southern Quebec (Canada). We analyzed volunteer vegetational composition in the tree planting right-of-way relative to eight explanatory factors. Average survival of planted trees was 86.4% and varied mainly with planting site; tree survival was negatively and significantly correlated with soil pH. We modelled correlations between size of the ten most frequently occurring tree species and 20 explanatory factors, of which six were significant, i.e., method of volunteer vegetation control, soil texture, soil preparation before planting, volunteer vegetation abundance, tree row structure and agroforestry system type (windbreak vs riparian buffer). Relative abundance of different functional types of volunteer vegetation was influenced mainly by the age of agroforestry systems. To increase tree establishment success in winbreaks and riparian buffers, species must be properly selected for planting based upon edaphic conditions, while implementing soil preparation prior to planting and maintaining sufficient spacing between trees to optimize long-term growth. Our results suggest that tree establishment in windbreaks and riparian buffers within an intensive agricultural context should not be perceived as a barrier to their adoption.

Fertilisation strategies and their influence on nutrient flows in organic apple orchards

AbstractIn organic fruit production, permitted fertilisers contain multiple nutrients with stoichiometries differing from the nutrient offtakes of the fruit trees. Furthermore, some pesticides contain nutrients resulting in additional inputs. These conditions may cause unbalanced nutrient supplies and thereby influence the long-term sustainability of the system. An analysis of nutrient management practices in organic apple farms was conducted in three Southern and one Northern German apple-growing region. Data on nutrient inputs (via fertilisers and pesticides) and outputs (via fruit) per orchard were collected along with soil samples from up to five orchards per farm on 19 farms. On average, farmers fertilised 37 kg N and harvested 23 Mg apples per ha and year. Nutrient budgets showed imbalances for N (+ 25 kg ha−1 year−1), P (+ 3 kg), K (− 4 kg), Ca (+ 37 kg), Mg (+ 4 kg), S (+ 53 kg), Na (+ 4 kg) and Cl (+ 3 kg). Base fertilisers like compost or manure contributed to higher nutrient inputs due to a larger P and K-to-N-ratio. Commercial organic fertilisers such as keratins or vinasse contained much lower ratios. The main S input sources were pesticides (46 kg). N inputs by base (p = 0.06) and commercial (p = 0.37) fertilisers had no significant effect on the yield. Balanced nutrition can best be achieved by applying a combination of 20% of the total N demand via base fertilisers, complemented with commercial fertilisers with low element-to-N-ratios (e. g. keratin fertilisers, vinasse or biological N2 fixation). No correlation was found between soil nutrient status and nutrient budgets. Site conditions and internal field nutrient flows (transfer of the inter-row biomass via mulching into the tree row) had a stronger influence on the soil nutrient content than fertilisation strategy. In addition, fruit orchards showed a spatial differentiation of soil nutrient contents. Elevated P and K contents above the recommended range in the tree row were found in 67% of the orchards, while tendencies of depletion were found in the inter-row area. Mulching schemes which transfer biomass from the inter-row area to the tree row need to be adapted to this condition.

Effects of street tree configuration and placement on roadside thermal environment within a tropical urban canyon.

The Urban Heat Island (UHI) effect increases surface and air temperatures, affecting urban health and well-being. A well-known UHI mitigation measure is the increased roadside tree vegetation facilitating evapotranspiration and shade. In its implementation, the identification of thermally optimal street tree configurations and a quantitative assessment of how various street tree configurations impact the roadside thermal environment were deemed essential and were chosen as the main aims of the study. Twelve tropical urban canyons were categorized into three clusters representative of different street tree placement and configuration scenarios. A control cluster devoid of any roadside trees was also selected. The CFD-based 3-D microclimate model 'ENVI-met' was used to identify suitable roadside urban tree planting scenarios for better microclimate regulation. From a tree planting scenario analysis done as part of the study, the greening scenario of using a 'Continuous tree row (Densely foliated - high Leaf Area Density - LAD)' tree configuration was recognized with the highest ambient temperature reduction of 1.41°C. The study outcomes reveal that tree configuration of high LAD street trees placed in closer spacing contributes towards the better cooling effect of roadside environments and thus improves thermal comfort for warmer tropical climates of higher humidity levels. The study's findings offer valuable insights for urban planning professionals and policymakers involved in designing future cities and urban developments. They emphasize the importance of strategic tree-planting designs and configurations to enhance thermal comfort and livability in urban areas. This highlights the need to avoid ad-hoc procedures and instead prioritize well-planned roadside tree configurations within urban canyons.

The distance from tree legumes in silvopastoral systems modifies the litter in grass-composed pastures

AbstractThe use of silvopastoral systems with tree legumes is a viable alternative to recover and develop pastures, as they add N to the system influencing pasture growth. This study hypothesized that the herbage and litter of signalgrass (Urochloa decumbens Stapf) is affected by legume trees in the pasture. Treatments were composed of (1) signalgrass + Mimosa caesalpiniifolia Benth.; (2) signalgrass + Gliricidia sepium Jacq.; and (3) signalgrass monoculture. The 3-year experiment followed a randomized complete block design with three replications. Tree legumes were planted in double rows (15 × 1 × 0.5 m), in 1 ha paddocks. Litter samples were taken in five distance points (0, 1.8, 3.7, 5.6 and 7.5 m) perpendicular to tree legume rows. Signalgrass was taller at longer distances from the trees (P < 0.05). Signalgrass height differed between treatments, with taller signalgrass found in pastures mixed with G. sepium (15.6 cm) compared to M. caesalpiniifolia (9 cm) (P < 0.05). Herbage N content decreased with increasing distance from tree rows (P < 0.05). Litter N content followed a similar pattern, ranging from 23 g/kg under the trees to 12 g/kg at 7.5 m away from tree rows. Signalgrass did not grow under the tree crown (0–1.8 m), especially when intercropped with M. caesalpiniifolia. The findings of this study suggest that the type of legume trees used in the silvopastoral system has the potential to modify the pattern of grass growth and content of N in pasture litter.

Root spatial distribution and belowground competition in an apple/ryegrass agroforestry system

CONTEXTForestry and fruit industry is a unique and advantageous industry in Xinjiang, China, and it is an important channel for farmers to increase income. With limited land resources and a shortage of forage in southern Xinjiang, farmers began to establish a fruit-grass interplanting model to improve the comprehensive economic benefits of orchards. OBJECTIVEThe objective of this study was to explore the effects of apple/ryegrass intercropping system on root spatial distribution and competition, and to evaluate the performance of field microclimate, soil physical properties and productivity under intercropping. METHODSIn the study, three different planting patterns were designed: sole-cropped apple (The spacing of the rows of apple trees was 4.0 m, and the plant spacing was 1.0 m), sole-cropped ryegrass (Strip sowing, row spacing was 0.25 m), and apple/ryegrass intercropping (The distance from apple row to ryegrass row was 1.0 m). Two-year field experiments were conducted to measure the root length density (RLD), specific root length (SRL), interspecific competitiveness index, soil moisture content, organic matter content, air temperature, relative humidity, wind speed, yield, land equivalent ratio (LER) and aggressivity. RESULTS AND CONCLUSIONCompared with sole cropping, intercropping reduced the RLD of apple and ryegrass and increased the SRL of ryegrass. The competition space between apple and ryegrass was concentrated in the soil area of 100 cm horizontally and 0–20 cm vertically, and apple was more competitive than ryegrass. Intercropping increased the content of soil moisture and organic matter and improved the microclimate of farmland, decreased the air temperature, increased the relative humidity of an orchard, and decreased wind speed. Although intercropping reduced ryegrass and apple yield, land equivalent ratio (LER) was 1.27–1.30, indicating that intercropping improved land use efficiency. Root competition led to an uneven distribution of root length density (RLD) and specific root length (SRL). The plasticity of root morphology and root spatial distribution was key to adapting to competition and maximizing the absorption of water and nutrients in apple/ryegrass agroforestry systems. SIGNIFICANCEApple/ryegrass intercropping system maximizes resource utilization and reduces interspecies resource competition. It improved land use efficiency, improved the comprehensive benefits of fruit and grass production.

Main soil microbial groups assessed by phospholipid fatty acid analysis of temperate alley agroforestry systems on crop- and grassland

The phospholipid fatty acid (PLFA) composition of soils was analysed at three poplar-based silvo-arable systems and at one willow-based silvo-grassland alley agroforestry system in Central Germany. The objective was to analyse tree row effects on the PLFA composition of main fungal and main bacterial groups. The fungal groups were BAM (Basidiomycota + Ascomycota + Mucoromycota) and AMF (Arbuscular Mycorrhizal Fungi). The bacterial groups were Gram-negative, Firmicutes, and Actinobacteria. The total PLFA content varied between 53 and 170 nmol g−1 soil. Total PLFA and microbial biomass carbon (MBC) showed a strong linear relationship, which resulted in a mean MBC/total PLFA ratio of 4.2 μg nmol−1. AMF contributed on average 4 mol% and the fungal BAM group 10 % to total PLFA. Gram-negative bacteria contributed on average 37 mol%, Firmicutes 23 mol%, and Actinobacteria 6 mol% to total PLFA. The presence of poplar or willow trees increased the mean total PLFA content in comparison with the alleyways by 30 %. Especially the mean contribution of fungal PLFA to total PLFA showed a significant +7.0 mol% increase in the tree row compared with the alleyways, exclusively caused by the BAM group (+7.6 mol%), whereas the contribution of the AMF PLFA linearly decreased from the middle of the alleyway to the tree row at all sites. Within the alleyways, the Gram-negative/Firmicutes PLFA ratio showed a significant decline from the 1 m up to the 24 m distance samples at sites Dornburg and Forst. Despite a decrease of AMF in tree rows, agroforestry tree rows led to a rapid increase in fungi, most likely due to the promotion of ecto-mycorrhizal fungi.

CrackYOLO: Rural Pavement Distress Detection Model with Complex Scenarios

The maintenance level of rural roads is relatively low, and the automated detection of pavement distress is easily affected by the shadows of rows of trees, weeds, soil, and distress object scale disparities; this makes it difficult to accurately evaluate the distress conditions of the pavement. To solve the above problems, this study specifically designed a target detection network called Crack Convolution (CrackYOLO) for pavement crack extraction on rural roads. CrackYOLO is based on an improved YOLOv5. The shadow created by rows of trees leads to the loss of crack features in the feature extraction and downsampling stages of the network; therefore, CrackConv and Adapt-weight Down Sample (ADSample) were introduced to strengthen the ability to locate and identify cracks. Due to disturbances such as soil and weeds, which cause the extraction of more redundant features, the Channel And Spatial mixed attention mechanism (CAS) was introduced to enhance crack weight. To address the issue of missed detections of fine cracks due to significant scale variations in crack objects in the same image, Multi Scale Convolution (MSConv) and Multi Scale Head (MSHead) were incorporated during the feature fusion and prediction inference stages of the network, thereby improving the multi-scale detection performance. In order to verify the effectiveness of the proposed method, the detection accuracy of CrackYOLO when used on the LNTU_RDD_NC dataset was determined to be 9.99%, 12.79%, and 4.61% higher than that of the current pavement crack detection models YOLO-LWNet, Faster R-CNN, and YOLOv7. At the same time, we compare the above model on public datasets of different scenarios, and the experimental results show that CrackYOLO has the same strong performance in urban roads and other scenarios.

ASSESSMENT OF THE CURRENT AGROBIOLOGICAL STATE OF THE PROTECTED FOREST STRIPS OF THE RIGHT BANK FOREST STEPPE

ASSESSMENT OF THE CURRENT AGROBIOLOGICAL STATE OF THE PROTECTED FOREST STRIPS OF THE RIGHT BANK FOREST STEPPE

UAV-Based High-Throughput Phenotyping to Segment Individual Apple Tree Row Based on Geometrical Features of Poles and Colored Point Cloud

Highlights Integrating RGB values and 3D coordinates of fruit trees provided phenotype-related data. The use of point clouds projection in tree rows segmentation has been confirmed. Using geometric features increased the accuracy of removing poles in an orchard. Segmenting fruit trees after removing poles on a single tree row was more accurate than traditional segmentation method. UAV equipped with LiDAR and a camera is promising for orchard high-throughput phenotyping. Abstract. High-throughput phenotyping (HTP) of fruit trees is important for providing crop geometrical information to evaluate their high yield genotypes. Unmanned aerial vehicle (UAV) is suitable for HTP by obtaining remote sensing data of large modern apple orchards, where each tree row needs to be segmented before segmenting a single tree. This study aims to develop a method for segmenting each row without noise (ERWON) of apple trees based on integrating RGB values and three-dimensional coordinates by UAV. A robust, real-time, RGB-colored, and LiDAR-inertial-visual tightly-coupled state estimation network was used to form a dense map of the orchard, which provided datasets of colored point clouds. Supporting poles were removed from the point clouds based on the consistent number of half upper parts and lower parts. Random sampling and an effective local feature aggregator were trained to segment ERWON after pole segmentation. Results showed that a precision of 0.971, a recall of 0.984, and an intersection-over-union of 0.817 for ERWON segmentation were achieved. This method proposed a potential solution for addressing the challenge of accurately and efficiently segmenting ERWON in large orchards. It is expected to be helpful for obtaining general parameters, such as geometric, morphological, and textural characteristics, as well as more specific parameters relevant to a particular phenotyping task. Keywords: Apple trees, Detection, Point cloud, RGB-colored, Segmentation.

Capim marandu sob diferimento em monocultivo e sistema silvipastoril: composição bromatológica e mineral

Abstract This study aimed to evaluate the chemical and mineral characteristics of Marandu grass under stockpiling in monoculture (MC) and a silvopastoral system (SPS) with 12- (SPS12) and 18-m (SPS18) spacing between tree rows. The experimental design consisted of randomized blocks, in which each system was allocated individually. Each treatment was formed in the center of each plot in a 3 × 4 factorial arrangement consisting of three systems (MC and SPS12 and SPS18 between the tree rows) and four stockpiling periods (60, 90, 120, and 150 days), totaling 12 treatments with three replications. No interaction effect was observed between the factors (p>0.05) for crude protein (CP), acid detergent fiber (ADF), neutral detergent fiber (NDF), phosphorus (P), potassium (K), calcium (Ca), or magnesium (Mg). The CP content decreased with increasing stockpiling days but met the suggested requirement for ruminants up to 75 days. The NDF and ADF concentrations increased, while P and K contents decreased with increasing stockpiling days. Magnesium and Ca concentrations did not differ with stockpiling days. However, a difference was observed only for Mg relative to the evaluated systems, which was higher in MC and SPS12, differing from SPS18. The spacing adopted in the SPS of 12 and 18 m does not negatively influence the nutritional value of the forage plant. The 75-day stockpiling period from March favored the concentration of macronutrients and CP content in Marandu grass in both MC and SPS.

Open-Format Prescription Maps for Variable Rate Spraying in Orchard Farming

Highlights Straightforward procedure to code prescription maps independent of manufacturers. Methodology suitable for orchard crops and vineyards including pressures up to 10 bar and flowrates up to 100 L/min. Algorithm validated for both trellis-based continuous rows and traditional orchard rows of discrete trees. Method scalable to other agricultural operations, such as fertilizing or data registration for auditing purposes. Abstract. The implementation of crop protection solutions contributing to significant reductions in the use and risk of chemical pesticides has motivated the interest of site-specific systems, such as variable rate technologies based on user-set prescriptions. However, the practical implementation of variable rates has been dissuasive for many growers who are not familiar with digital solutions, as proprietary firmware is often difficult to grasp. This paper presents a method for formatting prescription maps that is independent of manufacturers, can be easily and freely implemented by industry and can be adopted by growers not familiar with advanced software tools. The methodology was successfully demonstrated for perennial specialty crops, in particular for trellised vineyards in vertical shoot position and for traditional olive groves. Results showed that the variations within user prescription maps were translated to the fields, but flow errors appeared due to the challenge of measuring flow and pressure in the highly pulsating actuation of pulse-width-modulated (PWM) valves. Such errors diminished with the use of low-volume rates and the optimal selection of the nozzles when adjusted to the real pressure measured in the field. The use cases validated in the field showed the consistency of the method for highly populated prescription maps of 1,221 points/ha accessible to advanced farmers, as well as for modest maps of 80 points/ha within reach of the majority of growers. Keywords: Automated map building, Local tangent plane coordinates, Orchard crop operations, Precision farming, Prescription maps, User-centered approach, Variable rate spraying.

Potential Improvement of an Air-Conveyor Sprayer Performance Using a Spray Controller in Pear Orchard

Highlights An orchard sprayer was equipped with a spray controller to monitor and manage the working conditions. Foliar deposits and losses of the optimized and conventional sprayer were tested on two different sized pear trees. No significant differences in leaf deposits were found between canopy positions with the optimized sprayer. Ground losses with the optimized sprayer in the target rows were 45% lower compared to the conventional sprayer. Abstract. Currently, mistblowers are the most common sprayer type used for pesticide application in orchards. However, maximizing canopy deposition with high application efficiency remained a challenge due to the intricate canopy structure. This study compares the performance of two air-conveyor sprayers on pear trees: a conventional sprayer and an optimized sprayer. The optimized sprayer was equipped with a spray controller that displays its operational conditions (forward speed, spraying pressure, etc.) during application through a user interface of the device. In addition, the controller was capable of recommending spray volume for an orchard with the operator’s inputs based on the Tree Row Volume (TRV) method. Two experimental blocks in two pear orchards, with different tree sizes referred to as 'small trees' and 'large trees', were designated to evaluate the foliage deposition and off-target losses of the two sprayers. The conventional sprayer applied a spray volume of 1160 L ha-1 on both orchards following the farmers' conventional procedure. In contrast, the spray volumes of the optimized sprayer were determined by the controller based on the TRV model, resulting in a reduction of 29% and 55% for the large and small pear trees, respectively. The foliar deposition of each block was sampled from five randomly selected trees in a central row, with leaves collected from nine different canopy positions for small trees and twelve positions for large trees. Petri dishes were placed on the ground to assess the ground losses. Poles with nylon threads were mounted at various positions to evaluate airborne drift. The results showed that the mean normalized foliar depositions of the optimized sprayer were 1.57 and 1.81 µg cm-2 / kg-1 tracer ha-1 for large and small trees, respectively, whereas with the conventional sprayer, the depositions were 0.85 and 2.11 µg cm-2 / kg-1 tracer ha-1 for large and small trees, respectively. The optimized sprayer achieved a more uniform deposition distribution throughout the canopy compared to the conventional sprayer, as no significant differences in foliage deposition were detected between positions with the optimized sprayer. The optimized sprayer was capable of providing higher normalized deposits than the conventional sprayer for the large trees with less application volume. In addition, the optimized sprayer reduced spray losses in the air by 10% and 64% compared to the conventional sprayer for small and large trees, respectively, whereas ground losses were diminished by 45% and 50%, respectively. The results of this study suggest that controlling sprayer parameters, along with the spray volume adjustment based on canopy characteristics, may increase foliar deposition and could reduce pesticide use, although its influences on off-target loss reduction were insignificant. Keywords: Air conveyor, Constant-rate application, Digital control, Off-target losses, Pear fruit, Pesticide spraying, Tree row volume.

Effect of Gmelina arborea (Khamhar) bund based Agroforestry system on growth performance of paddy crop

Present study describes the effect of Gmelina arborea bund based Agroforestry system on growth performance of paddy crop. An experiment was conducted on the farmer’s field in the Rudri village of Dhamtari block of Dhamtari district (C.G.) during the kharif season (July-November) of the year 2022-23. Experiment was conducted in randomized block design (RBD). The biometry of trees was studied. DBH is 20.7, 23.68, 22.62 cm and crown width 3.22, 5.2, 4.26 m. Samples were taken at the distances of 1 m, 3 m, 5 m, 7 m, and 9 m from the tree trunk and >15 m for the control. The result indicated that the Gmelina arborea bund agroforestry had a negative impact on paddy growth, which varied depending on the DBH and crown width of the tree row and distance from the tree bund. The growth of paddy, as measured by the number of hills and the number of tillers was significantly stunted by the wider crown and proximity to the tree. The number of hills and tillers were lowest between 1-3 m. from the base of tree and the highest number of hills was (14 quadrate-1) and number of tiller hill-1 were 9.58 and average shoot length was 99.33 cm, average ear length 25.29. Thus, it is concluded that Gmelina arborea trees with minimal crown width and increasing distance from the tree line had less harmful impact on the growth and production of paddy than trees with maximum crown width and close proximity to the tree or tree line.

Analysis of 5.8 GHz Network for Line of Sight (LOS) and Non-Line of Sight (NLOS) in Suburban Environment

This paper presents the findings of radio wave characterization based on the measurement data at 5.8 GHz. The measurement data were collected by a testbed channel, which links with the following scenarios: a single tree, a row of trees, a row of trees and a road, a row of trees, a road, and a building. These experiments were conducted at University Teknologi Malaysia (UTM) Skudai, Johor to represent the suburban environment. The links consist of pairs of transmitting and receiving antennas that deploy the path of a line of sight (LOS) and non-line of sight (NLOS) radio propagation wave networks. Based on the measurement data analysis, the general issue concerning the statistical probability distribution and the characteristics of LOS and NLOS are examined and discussed. Note that 5.8 GHz technology can be used in both LOS and NLOS scenarios, but its performance varies based on the presence of obstacles and signal propagation characteristics. Other prominent experimental analysis methods, such as hypothesis testing and goodness of fit tests, are implemented to consolidate the findings. The analysis found that the empirical probability density function of LOS and NLOS channels follows Gaussian, Rayleigh, and Rician distribution. Predicting specific future technological developments, such as the availability of 5.8 GHz technology, is challenging because it depends on various factors, including research and development efforts, regulatory decisions, market demand, and technological advancements.

Analysis of 5.8 GHz Network for Line of Sight (LOS) and Non-Line of Sight (NLOS) in Suburban Environment

This paper presents the findings of radio wave characterization based on the measurement data at 5.8 GHz. The measurement data were collected by a testbed channel, which links with the following scenarios: a single tree, a row of trees, a row of trees and a road, a row of trees, a road, and a building. These experiments were conducted at University Teknologi Malaysia (UTM) Skudai, Johor to represent the suburban environment. The links consist of pairs of transmitting and receiving antennas that deploy the path of a line of sight (LOS) and non-line of sight (NLOS) radio propagation wave networks. Based on the measurement data analysis, the general issue concerning the statistical probability distribution and the characteristics of LOS and NLOS are examined and discussed. Note that 5.8 GHz technology can be used in both LOS and NLOS scenarios, but its performance varies based on the presence of obstacles and signal propagation characteristics. Other prominent experimental analysis methods, such as hypothesis testing and goodness of fit tests, are implemented to consolidate the findings. The analysis found that the empirical probability density function of LOS and NLOS channels follows Gaussian, Rayleigh, and Rician distribution. Predicting specific future technological developments, such as the availability of 5.8 GHz technology, is challenging because it depends on various factors, including research and development efforts, regulatory decisions, market demand, and technological advancements.

Vision-based autonomous navigation stack for tractors operating in peach orchards

Recently, camera-based approaches have been proposed to replace expensive LiDAR or real-time kinematic (RTK) based solutions for the unmanned tractors operating in an orchard-like environment. However, constructing a completely autonomous navigation stack with a low-costly camera and onboard computer presents extra difficulties, such as a computationally efficient perception model, rapid path planning without costly SLAM, and the capacity to avoid obstacles. In this paper, a novel vision-based autonomous navigation stack is devised to address challenges of the wholly autonomous tractor using stereo camera and inertial measurement unit (IMU) that are inexpensive. The computational pipeline consists primarily of three modules: (1) the multi-task perception network, (2) the frame transformation algorithm, and (3) the motion planning module. The multi-task perception network detects tree trunks, obstacles, and traversable areas simultaneously from the RGB image with high efficiency (69 FPS) and accuracy (mAP@.5 of 96.7% and mIoU of 98.1%). For global path planning and trajectory prediction, the frame transformation algorithm integrates the downsized the navigational features and transforms them to the tractor frame from the image frame. The motion planning module then uses the fused data to plan the appropriate path (i.e., the center of the tree row, U-turn path, or J-turn path) and search for the optimal trajectory utilizing the optimized dynamic window approach (DWA) for path tracking. In the peach orchard, the proposed stack is implemented on our autonomous retrofitted tractor and its efficacy is demonstrated compared with the human-driving tractor.

CONSIDERATIONS REGARDING THE VASCULAR FLORA OF SOME FRUIT ORCHARDS IN DOLJ COUNTY, ROMANIA

Through the environmental requirement imposed by inter-rows, the eco-scheme contributes to the CAP objective of biodiversity conservation, as well as increasing the soil's carbon sequestration capacity and improving the quality of the soil structure, the main natural resource in agricultural activity. The present work aimed to analyze the vascular flora from some fruit orchards in Dolj County, Romania following a taxonomic study, starting from the need to establish a vegetal soil cover with spontaneous plants, both specific to the region and environmentally friendly. Following the observations made, it was found that the floristic composition of the grassy cover in the orchards in Dolj County is variable depending on the age of the orchard and the works that were carried out between and on the rows of trees. In orchards where human intervention is low, there is a good representation of taxa belonging to the Fabaceae family (eg Trifolium repens, T. pratense, Medicago arabica, M. sativa). On the other hand, isolated species are present in well-maintained orchards, especially from the category of weeds that can be difficult to fight (e.g. Sorghum halepense, Xanthium italicum, Conyza canadensis, etc.). Observations will be continued to consider the effect of wild plants on the environment and to establish an area-specific varietal soil cover for keeping the row spaces grass-covered.

Navigation path recognition between rows of fruit trees based on semantic segmentation

The navigation path recognition has been recognized as one of the most important subtasks of intelligent agricultural equipment in orchard operations. However, there are still some challenges in recognizing navigation paths between rows of fruit trees, including the accuracy, real-time performance, generalization of deep learning models. The Fast-Unet model was proposed by pruning and optimization based on Unet for recognizing navigation paths between rows of fruit trees, which inherited encoding–decoding structure and multi-layer feature sensing capability. The number of convolutional kernels used to extract features in the Fast-Unet was reduced to one-fourth of that in Unet to improve inference speed. To address the blurring of the boundary of the recognized object due to the reduction in the number of convolutional kernels, the atrous spatial pyramid pooling (ASPP) module was used in the encoding part to extract the multiscale information to improve the recognition accuracy. The navigation path edges determined by Fast-Unet and Canny operators, navigation lines and yaw angles were generated by the least square method.. In this study, the Fast-Unet model was first trained on the peach dataset, and then the trained model was transferred to the small dataset of oranges and kiwifruits for navigation path recognition to verify the generalization. The Mean Intersection over Union (MIOU) of the Fast-Unet for peaches, oranges and kiwifruits navigation path extraction accuracy were 0.977, 0.987 and 0.956, respectively. The mean difference between the predicted yaw angle of peaches, oranges and kiwifruits navigation paths and the labelled were 0.397°, 0.102° and 0.239°, respectively. In terms of real-time performance, the inference speed was 48.8 frames per second (FPS) to process the RGB image data on a single-core CPU. The inference speed of the Fast-Unet model was 1.59 times higher than that of Unet. Through transfer learning, the Fast-Unet model can realize real-time recognition of navigation paths for peaches, oranges and kiwifruits. These results can provide technical and theoretical support to the development of navigation equipment and visual slip prediction for intelligent agricultural machinery in the orchard.

Overall integrated navigation based on satellite and lidar in the standardized tall spindle apple orchards

Overall navigation in orchards is essential for autonomous production activities, however, most navigation studies, in orchards, focus on in-row scenes, and few of them pay attention to the headland transition or the overall navigation. This paper proposes an integrated navigation method based on satellite and lidar for overall orchards scenes, where the lidar was mainly used for in-row navigation and chassis position (CP) obtaining, whilst the satellite was utilized for headland transition as well as the assistant for in-row integrated navigation. Two overall integrated navigation modes were investigated: CMD-INT, which integrates the command signals from the lidar-based and satellite-based navigation systems, and BIAS-FUS, which combines the information of bias from the two navigation systems. The CP was used to detect the headland of the tree rows and achieve overall navigation integration. A position-ratio-based path planning method was also proposed, which enabled the chassis to maintain a proper constant offset from one side of the orchard. The refined pure pursuit algorithm was adopted for path tracking with good adaptivity on both the path curvature and tracking velocity. Both simulation and field tests with ten group parameters configuration in total were conducted to verify the performance of the system. The BIAS-FUS mode outperformed the CMD-INT mode, and the findings for the simulation experiments were consistent with that of the field tests. In the simulation experiments, the maximum value (Max), mean value (Mean), and root mean square error (RMSE) for the in-row process decreased by 0.0054 m, 0.0053 m, and 0.0062 m, respectively. Additionally, the corresponding heading deviation decreased by 0.3027°, 0.0050°, and 0.0256°, respectively. In the field tests, the Mean of the heading and lateral deviation for the in-row tracking process decreased by 0.3823°, and −0.0072 m respectively, and the corresponding deviations for the transition tracking process decreased by 2.8903°, and 0.0164 m respectively. Aiming at the standardized tall spindle apple orchards, this work contributes to an available overall integrated navigation method.