Fruit Harvest Research Articles

Structural Parameter Optimization of a Tomato Robotic Harvesting Arm: Considering Collision-Free Operation Requirements

The current harvesting arms used in harvesting robots are developed based on standard products. Due to design constraints, they are unable to effectively avoid obstacles while harvesting tomatoes in tight spaces. To enhance the robot’s capability in obstacle-avoidance picking of tomato bunches with various postures, this study proposes a geometric parameter optimization method for a 7 degree of freedom (DOF) robotic arm. This method ensures that the robot can reach a predetermined workspace with a more compact arm configuration. The optimal picking posture for the end-effector is determined by analyzing the spatial distribution of tomato bunches, the main stem position, and peduncle posture, enabling a quantitative description of the obstacle-avoidance workspace. The denavit–hartenberg (D-H) model of the harvesting arm and the expected collision-free workspace are set as constraints. The compactness of the arm and the accessibility of the harvesting space serve as the optimization objectives. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) multi-objective genetic algorithm is employed to optimize the arm length, and the results were validated through a virtual experiment using workspace traversal. The results indicate that the optimized structure of the tomato harvesting arm is compact, with a reachability of 92.88% in the workspace, based on the collision-free harvesting criteria. This study offers a reference for structural parameter optimization of robotic arms specialized in fruit and vegetable harvesting.

An Advancement in Postharvest Biology and Fresh-Keeping Technology of Kiwifruit (Actinidia spp.): A Review

Kiwifruit is a climacteric fruit that may decay rapidly and softens after harvest if not stored properly. How to expand the storage time of kiwifruit to maintain the quality, is a critical challenge for the kiwifruit industry development. Kiwifruit’s post-harvest life is tied closely to post-harvest management, such as scientific harvesting, green preservation, ethylene management, and low-temperature storage, as well as texture and quality. This study focuses on the advancement of related research from four perspectives and explores their impacts on kiwifruit storage in order to give a theoretical foundation for breeding varieties with superior storage capacity, and the development of storage and preservation technologies. Hayward and Hort16A varieties of kiwifruit had been cultivated largely in past but now, yellow-fleshed Sun Gold, Gold 3 and Gold 9, Hongyang, Maohua Cuixiang, Xuxiang, etc. are becoming significantly famous in international commerce. For the best postharvest quality, kiwifruit must be stored at low temperatures. Fruit quality, harvesting maturity, ethylene production, storage life, green preservation, and pathology are the priorities in breeding projects. To take advantage of adequate germplasm resources, reproductive biology understandings are needed.

New design and construction of a mechanical gripping device with a telescopic link of a fruit harvesting robot

Abstract Gripping devices for harvesting fruits have such types of work as cutting, tearing and unscrewing. For apples, it is preferable to use slicing or unscrewing, while the fruit leg should not remain, damaging the apple during storage. In this article, we are developing a grab for harvesting apples. The gripper is used both for holding the fruit and for jamming, followed by unscrewing. One of the advantages is that the proposed method of collecting apples allows you not to waste time moving the manipulator from the tree to the basket, but only to grab and tear them off. The fruit enters the gripper device; after which it enters the fruit collection container through a rigid or flexible pipe. The gripper device is built on the basis of a ball-screw transmission, which is supplemented by a gear drive along the helical surface. This allows for rotation and rectilinear movement of the held fruit. The gripping device has a ratchet mechanism that allows you to fix the fruit. A mathematical model of the gripper device has been developed, which allows determining the torque of the engine depending on the position of the fingers. The parameters of the mechanism were optimized using a genetic algorithm, and the results are presented in the form of a Pareto set. A 3D model of the gripper device has been built and a layout has been developed using 3D printing. Experimental laboratory and field tests of the gripping device were carried out.

Challenges in harvesting and utilization of Ziziphus tree fruits in Ethiopia

Ziziphus tree species commonly known as “jujube” are wide sources of nutritious and socio-economically important fruits in arid and semi-arid regions of Asia and Africa. However, understanding of local communities’ engagement in harvesting and utilization of these fruits remains limited consequently undermining sustainable harvesting and broader utilization. Household interviews (HHIs), focus group discussions (FGDs) and key informants’ interviews (KIIs) were used to investigate the level of harvesting and utilization of fruits from different tree species of jujube in Ethiopia. Multiple linear and binary logistic regressions were utilized to investigate factors influencing the annual fruit yield per tree and to discern factors impacting the local community's capacity to grow and sell jujube, respectively. Fruit yield per tree, market involvement and the principal challenges to growing were found to vary among two study sites. Bosset district's yield exceeded Bati's by 0.87 times. Women and children played significant roles in fruit collection, sale and management. Less rainfall reduced annual yield by 33 kg per tree while planting seedlings instead of relying solely on naturally regenerated trees boosted yield by 42 kg per year. With each advancing year in age, older respondents were 0.04 times less likely to sell harvested jujube fruits. The increasing impact of pests, water shortage and cultural influences decreased community interest in growing jujube by factors of 1.15, 1.41 and 2 times, respectively. Suboptimal involvement in jujube cultivation, fruit harvest and market activities was frequently ascribed to inadequate community support, organizational oversight and depressed market prices. These findings highlight the need to enhance awareness, management and market access for jujube fruits to broaden community benefits in Ethiopia.

Performance Analysis and Operation Parameter Optimization of Shaker-Type Harvesting for Camellia Fruits

This study aims to address the challenges of achieving a high harvesting rate and low flower bud damage rate during the harvesting of camellia fruits. To this end, a dynamic model of the camellia osmantha tree and a self-developed shaker-type harvesting machine were used as research subjects. The first 24 natural frequencies and mode shapes of the camellia tree were solved using the finite element method, and the effects of vibration frequency, excitation position, and vibration duration on the harvesting rate and flower bud damage rate were quantitatively analyzed through an orthogonal experiment. The numerical analysis results indicate that the camellia tree exhibits good response characteristics at vibration frequencies of 10–15.5 Hz and 38.5 Hz. The three-factors orthogonal experiment figured out that the optimal operational parameters for shaker-type harvesting were determined to be a vibration duration of 30 s, a motor output frequency of 12.5 Hz, and a gripping position height of 50 to 60 cm above the ground. Meanwhile, under these operational parameters, the harvesting efficiency reached 96.97%, while the flower bud damage rate was only 6%.

On-the-go table grape ripeness estimation via proximal snapshot hyperspectral imaging

The monitoring of grapes for ripeness estimation is a practice that enables fruit harvesting at the optimal time. Hyperspectral Imaging (HSI) represents a non-destructive and high-throughput alternative to traditional laboratory analyses. Current literature approaches perform hyperspectral measurements using line scan sensors or low-resolution static snapshot cameras, which hinder a fast per-bunch ripeness characterization. We propose a framework for on-the-go collection and processing of proximal snapshot hyperspectral images to estimate single bunch ripeness parameters. Focusing on table grapes (Vitis vinifera L. cv. Red Globe), we collected images under natural illumination with a hyperspectral camera (500–900 nm) mounted on a moving vehicle in an experimental block sited in Piacenza, Italy. We investigated images collected in August and September 2021 representing two ripening stages. The composition of the imaged grape bunches was determined through laboratory chemical analyses to predict Total Soluble Solids (TSS) and anthocyanin concentration. The images were pre-processed via multimodal image registration to correct the unalignment of bands due to the vehicle motion, and the single bunches were automatically identified on false RGB images through a Mask Region-Convolutional Neural Network (Mask R-CNN) instance segmentation network. The mean spectra of the bunches were used as input features of a Partial Least Squares Regression (PLSR) model to predict the chemical parameters at single bunch and whole vine scales. The regression model of TSS had an R2 (10-fold nested cross-validation) of 0.75 and 0.85 on a per-bunch and per-vine basis, respectively. The regression model of anthocyanin had an R2 of 0.68 and 0.49 on a per-bunch and per-vine basis, respectively. The results suggest the potential of using snapshot hyperspectral images for high-throughput analysis of a per-bunch grape ripeness estimation. The method described in this study could give valuable information to improve grape ripening monitoring and management of harvest operations and even allow for precise and automated robotic harvesting.

Barrier-free tomato fruit selection and location based on optimized semantic segmentation and obstacle perception algorithm.

With the advancement of computer vision technology, vision-based target perception has emerged as a predominant approach for harvesting robots to identify and locate fruits. However, little attention has been paid to the fact that fruits may be obscured by stems or other objects. In order to improve the vision detection ability of fruit harvesting robot, a fruit target selection and location approach considering obstacle perception was proposed. To enrich the dataset for tomato harvesting, synthetic data were generated by rendering a 3D simulated model of the tomato greenhouse environment, and automatically producing corresponding pixel-level semantic segmentation labels. An attention-based spatial-relationship feature extraction module (SFM) with lower computational complexity was designed to enhance the ability of semantic segmentation network DeepLab v3+ in accurately segmenting linear-structured obstructions such as stems and wires. An adaptive K-means clustering method was developed to distinguish individual instances of fruits. Furthermore, a barrier-free fruit selection algorithm that integrates information of obstacles and fruit instances was proposed to identify the closest and largest non-occluded fruit as the optimal picking target. The improved semantic segmentation network exhibited enhanced performance, achieving an accuracy of 96.75%. Notably, the Intersection-over-Union (IoU) of wire and stem classes was improved by 5.0% and 2.3%, respectively. Our target selection method demonstrated accurate identification of obstacle types (96.15%) and effectively excluding fruits obstructed by strongly resistant objects (86.67%). Compared to the fruit detection method without visual obstacle avoidance (Yolo v5), our approach exhibited an 18.9% increase in selection precision and a 1.3% reduction in location error. The improved semantic segmentation algorithm significantly increased the segmentation accuracy of linear-structured obstacles, and the obstacle perception algorithm effectively avoided occluded fruits. The proposed method demonstrated an appreciable ability in precisely selecting and locating barrier-free fruits within non-structural environments, especially avoiding fruits obscured by stems or wires. This approach provides a more reliable and practical solution for fruit selection and localization for harvesting robots, while also being applicable to other fruits and vegetables such as sweet peppers and kiwis.

SGW-YOLOv8n: An Improved YOLOv8n-Based Model for Apple Detection and Segmentation in Complex Orchard Environments

This study addresses the problem of detecting occluded apples in complex unstructured environments in orchards and proposes an apple detection and segmentation model based on improved YOLOv8n-SGW-YOLOv8n. The model improves apple detection and segmentation by combining the SPD-Conv convolution module, the GAM global attention mechanism, and the Wise-IoU loss function, which enhances the accuracy and robustness. The SPD-Conv module preserves fine-grained features in the image by converting spatial information into channel information, which is particularly suitable for small target detection. The GAM global attention mechanism enhances the recognition of occluded targets by strengthening the feature representation of channel and spatial dimensions. The Wise-IoU loss function further optimises the regression accuracy of the target frame. Finally, the pre-prepared dataset is used for model training and validation. The results show that the SGW-YOLOv8n model significantly improves relative to the original YOLOv8n in target detection and instance segmentation tasks, especially in occlusion scenes. The model improves the detection mAP to 75.9% and the segmentation mAP to 75.7% and maintains a processing speed of 44.37 FPS, which can meet the real-time requirements, providing effective technical support for the detection and segmentation of fruits in complex unstructured environments for fruit harvesting robots.

Effects of Biostimulants on the Eco-Physiological Traits and Fruit Quality of Black Chokeberry (Aronia melanocarpa L.).

Biostimulants contribute to the physiological growth of plants by enhancing the quality characteristics of fruit without harming the environment. In addition, biostimulants applied to plants strengthen nutritional efficiency, abiotic stress tolerance, and fruit biochemical traits. We investigated the effectiveness of specific organic biostimulants. Five treatments were tested: (1) control (H2O, no biostimulants); (2) Magnablue + Keyplex 350 (Mgl + Kpl350); (3) Cropobiolife + Keyplex 120 (Cpl + Kpl120); (4) Keyplex 120 (Kpl120); and (5) Magnablue + Cropobiolife + Keyplex 120 (Mgl + Cpl + Kpl120) on the mineral uptake and physiology in black chokeberry (Aronia) plants, as well as the quality of their berries. The different treatments were applied to three-year-old chokeberry plants, and the experimental process in the field lasted from May to September 2022 until the harvest of ripe fruits. Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES) revealed that the fifth treatment significantly increased concentrations of P, Ca, and K. Additionally, the fifth treatment enhanced photochemical efficiency (Fv/Fm), water-splitting efficiency (Fv/Fo) in PSII, and the performance index (PI) of both PSI and PSII in chokeberry leaves. Improvements in photosynthesis, such as CO2 assimilation (A), transpiration (E), and water-use efficiency (A/E), were also noted under biostimulant applications. Upon harvesting the ripe fruits, part of them was placed at room temperature at 25 °C, while the rest were stored at 4 °C, RH 90% for 7 days. The cultivation with biostimulants had beneficial effects on the maintenance of flesh consistency, ascorbic acid concentration, and weight of berries at 4 and 25 °C, especially in the 5th treatment. Moreover, the total antioxidant capacity, anthocyanin concentration, and total phenols of the berries were notably higher in the third and fifth treatments compared to the control. These data suggest that selecting appropriate biostimulants can enhance plant yield and fruit quality by potentially activating secondary metabolite pathways.

Detection, counting, and maturity assessment of blueberries in canopy images using YOLOv8 and YOLOv9

Blueberry growers currently rely on manual or subjective approaches to harvest decision-making and yield estimation. Canopy image-based, pre-harvest blueberry detection provides a promising means for automated harvest maturity assessment, fruit counting, and yield estimation to optimize crop management and reduce labor costs. Data-driven deep-learning-based object detectors, especially the YOLO (You Only Look Once) series models, have emerged as a powerful tool for a diversity of computer vision tasks in agriculture. However, the detection of such small, densely populated objects as blueberries in unstructured scenes can pose great challenges, especially given the lack of dedicated datasets for model development. This study, therefore, presents the first publicly available dataset of blueberry canopy images with 17,955 ripe and unripe blueberries, which were captured in diverse orchard conditions, and performance evaluation of YOLOv8l (large) and YOLOv9-c (compact) with comparable complexity for blueberry detection and whereby fruit counting and ripe fruit percentage estimation. At the input image resolution of 2560 × 2560 pixels, both models performed similarly in terms of detection accuracy with around 91 % mAP@50, except that YOLOv9-c was far more time-consuming to train. Trained with the input of higher resolution images of 3520 × 3520 pixels, YOLOv8l achieved an overall mAP@50 of nearly 93 %, and an RMSEs (root-mean-square errors) of 10.4 in fruit counting and 3.62 % in estimating the percentage of ripe fruit of each image. Both the blueberry dataset11https://zenodo.org/records/14002517 and software programs22https://github.com/vicdxxx/BlueberryDetectionAndCounting of this study have been or will be made publicly available, which are expected to be useful for promoting greater community efforts for further algorithm development.

Identification of Technical Requirements for the Initial Design of an Autonomous Fruit-Harvesting Robot

Automation in agriculture is revolutionizing the management of field tasks. This paper focuses on identifying the essential needs and preliminary technical requirements for designing an autonomous robot specifically for fruit harvesting. The study examines the integration of advanced machine vision technologies and neural networks for the accurate detection of ripe fruits and obstacles, optimizing harvesting efficiency. Key features such as proximity and touch sensors are also evaluated to ensure the safe handling of fruits, minimizing damage during harvesting. The technical specifications, including traction, speed, and the robot’s ability to operate on uneven terrain, are analyzed to ensure adaptability across various crops and ground conditions. Perception systems, incorporating cameras and sensors, are crucial for crop inspection and route planning. The main findings of this review establish a set of technical requirements that serve as a foundation for developing efficient and economically viable fruit-harvesting robots. These systems offer significant potential to transform agriculture by addressing labor shortages and improving harvesting precision. However, challenges remain, particularly in adapting to diverse crops and environments, emphasizing the need for further research and development.

Juvenile-related tolerance to papaya sticky disease (PSD): proteomic, ultrastructural, and physiological events.

The proteomic analysis of PMeV-complex-infected C. papaya unveiled proteins undergoing modulation during the plant's development. The infection notably impacted processes related to photosynthesis and cell wall dynamics. The development of Papaya Sticky Disease (PSD), caused by the papaya meleira virus complex (PMeV-complex), occurs only after the juvenile/adult transition of Carica papaya plants, indicating the presence of tolerance mechanisms during the juvenile development phase. In this study, we quantified 1609 leaf proteins of C. papaya using a label-free strategy. A total of 345 differentially accumulated proteins were identified-38 at 3months (juvenile), 130 at 4months (juvenile/adult transition), 160 at 7months (fruit development), and 17 at 9months (fruit harvesting)-indicating modulation of biological processes at each developmental phase, primarily related to photosynthesis and cell wall remodeling. Infected 3- and 4-mpg C. papaya exhibited an accumulation of photosynthetic proteins, and chlorophyll fluorescence results suggested enhanced energy flux efficiency in photosystems II and I in these plants. Additionally, 3 and 4-mpg plants showed a reduction in cell wall-degrading enzymes, followed by an accumulation of proteins involved in the synthesis of wall precursors during the 7 and 9-mpg phases. These findings, along with ultrastructural data on laticifers, indicate that C. papaya struggles to maintain the integrity of laticifer walls, ultimately failing to do so after the 4-mpg phase, leading to latex exudation. This supports initiatives for the genetic improvement of C. papaya to enhance resistance against the PMeV-complex.

Hengniu: Fast Bearing and High Yielding Coconut Varieties

Benefits of coconut varieties that stakeholders want are early bearing, high yielding, short stems, and slow growth for height. Most local tall coconut palms in Indonesia have stem height above 20 m, making it increasingly difficult to climb to harvest fruit or tapping sap thereby making the harvesting cost high. To breed varieties of desired characters, an evaluation trial was initiated in 2014 with BYD x MTT-S4, RAD x MTT-S4, and KHINA-1 as a control. The crossing was done in 2012 and seedlings planted in January 2014 at Mapanget Experimental Garden, Indonesian Palma Crops Research Institute, North Sulawesi. The study used a Randomized Block Design (RBD) of three types of coconut hybrids, four replications with a plot size of 16 trees. Morphological observations were carried out on stem, crown and leaf characters, inflorescences and flowers, nut production, fruit components, copra, oil content, and fatty acid composition. The results of ANOVA analysis and statistical tests obtained those vegetative characters, such as stem circumference and number of leaf, generative characters namely the number of bunches, first flowering, and fruit production of these three crosses at the age of 4 years after planting, did not show a significant difference. The first initial flowering was in the coconut hybrid of RBD x MTT-S4, which is 26 months, followed by BYD x MTT-S4 in 32 months and KHINA-1 in 36 months after planting. The results of the analysis of fruit and copra production at the age of 5 years showed a significant increase between hybrid coconuts. The highest to lowest fruit production was obtained in BYD x MTT-S4 hybrid coconut, RBD x MTT-S4, KHINA-1, which were 64 nuts, 44 nuts and 26 nuts /palm respectively, or estimated copra production was 2.26 tons, 1.45 tons and 0.88 tons copra/ha. At 6 years old the harvest of fruits from the three hybrid coconuts is obtained sequentially 118 nuts, 99 nuts and 94 nuts/palm. While estimation of copra yield per hectare is found the highest in BYD x MTT-S4 hybrid coconut is 3.86 ton/ha/year and this yield differently significant compare with RBD x MTT-S4 is found 3.04 ton/ha/year, and control hybrid of KHINA-1, which is about 2.74 ton/ha/year. Based on the production potential, hence the estimated optimum production when aged over 10 years can reach more than 5 tons/ha/year. The hybrid coconut variety BYD x MTT-S4 is released in October 2019 under the name HENGNIU.

Under-Canopy Drone 3D Surveys for Wild Fruit Hotspot Mapping

Advances in mobile robotics and AI have significantly expanded their application across various domains and challenging conditions. In the past, this has been limited to safe, controlled, and highly structured settings, where simplifying assumptions and conditions allowed for the effective resolution of perception-based tasks. Today, however, robotics and AI are moving into the wild, where human–robot collaboration and robust operation are essential. One of the most demanding scenarios involves deploying autonomous drones in GNSS-denied environments, such as dense forests. Despite the challenges, the potential to exploit natural resources in these settings underscores the importance of developing technologies that can operate in such conditions. In this study, we present a methodology that addresses the unique challenges of natural forest environments by integrating positioning methods, leveraging cameras, LiDARs, GNSS, and vision AI with drone technology for under-canopy wild berry mapping. To ensure practical utility for fruit harvesters, we generate intuitive heat maps of berry locations and provide users with a mobile app that supports interactive map visualization, real-time positioning, and path planning assistance. Our approach, tested in a Scandinavian forest, refines the identification of high-yield wild fruit locations using V-SLAM, demonstrating the feasibility and effectiveness of autonomous drones in these demanding applications.

Genetic diversity study of bacterial wilt-tolerant bell pepper (Capsicum annuum) genotypes using cluster and principal component analysis

The present study was carried out during summer and rainy (kharif) seasons of 2019 and 2020 at the research farm of Himachal Pradesh Krishi Vishvavidyalaya, Palampur, Himachal Pradesh to study the genetic diversity among 43 bacterial wilt tolerant genotypes of bell pepper (Capsicum annuum L. var. grossum Sendt), focusing on 12 quantitative and 3 qualitative traits along with disease resistance. The experiment was laid out in a randomized complete block design (RCBD) with 3 replications. Following hierarchical cluster analysis, the 43 unique genotypes were categorized into 5 separate clusters. Cluster I consisted of maximum number of genotypes (39), followed by clusters II, III, IV and V, each having only one genotype. The greatest inter-cluster distance was observed between cluster II and V (3090.70), while the smallest distance was noted between cluster II and III (1299.21). Cluster I displayed the greatest intra-cluster distance (803.75), while clusters II, III, IV and V showed the lowest distances (0.00). The primary contributors to genetic divergence were found to be capsanthin content (23.4%), followed by ascorbic acid (21.4%), fruit length (12.5%), plant survival (11.1%) and marketable fruit yield/plant (10.9%). Principal component analysis indicated that the initial six principal components, each possessing an eigen value surpassing one, jointly accounted for 70.62% of the total observed variability. PCA biplot revealed that, the traits namely, marketable fruits/plant, average fruit weight, harvest duration and plant height were the major yield contributing traits. The results underscored the importance of genetic characterization and the selection of diverse genotypes for hybridization, facilitating the development of improved bell pepper cultivars with enhanced productivity and quality.

Cherry Tomato Detection for Harvesting Using Multimodal Perception and an Improved YOLOv7-Tiny Neural Network

Robotic fruit harvesting has great potential to revolutionize agriculture, but detecting cherry tomatoes in farming environments still faces challenges in accuracy and efficiency. To overcome the shortcomings of existing cherry tomato detection methods for harvesting, this study introduces a deep-learning-based cherry tomato detection scheme for robotic harvesting in greenhouses using multimodal RGB-D perception and an improved YOLOv7-tiny Cherry Tomato Detection (YOLOv7-tiny-CTD) network, which has been modified from the original YOLOv7-tiny by eliminating the “Objectness” output layer, introducing a new “Classness” method for the prediction box, and incorporating a new hybrid non-maximum suppression. Acquired RGB-D images undergo preprocessing such as color space transformation, point cloud normal vector angle computation, and multimodal regions of interest segmentation before being fed into the YOLOv7-tiny-CTD. The proposed method was tested using an AGV-based robot in a greenhouse cherry tomato farming facility. The results indicate that the multimodal perception and deep learning method improves detection precision and accuracy over existing methods while running in real time, and the robot achieved over 80% successful picking rates in two-trial mode in the greenhouse farm, showing promising potential for practical harvesting applications.

Utilization of banana crop ligno-cellulosic waste for sustainable development of biomaterials and nanocomposites.

Banana (Musa spp.) is a tropical fruit cultivated in over 130 countries, producing significant lignocellulosic biomass. However, much of the agro-industrial waste from banana plants is neglected, contributing to environmental pollution. Around 60 % of the plant's biomass is generated after fruit harvesting, representing an untapped resource. This review examines the potential of banana plant waste for developing biocomposite and biodegradable materials. It covers the extraction and modification of banana fibers for composites, with a focus on the fabrication of nano biocomposites using banana fibers as reinforcement and polysaccharides or proteins as matrices. The review also evaluates the biodegradability and environmental impact of these materials through Life Cycle Assessment studies. Future research directions include refining processing methods, improving fiber-matrix compatibility, and enhancing the durability of banana fiber composites for packaging applications.

SILICIO COMO BIOESTIMULANTE EN EL CULTIVO DE PEPINO (Cucumis sativus L.)

<p><strong>Background. </strong>The use of silicon as a fertilizer can reduce the need to use chemical fertilizers and thereby prevent the adverse effects of the latter. <strong>Objective. </strong>To evaluate silicon as a biostimulant in the cultivation of cucumber (Cucumis sativus L.) under greenhouse conditions<strong>. Methodology. </strong>Four concentrations of silicon dioxide (0, 0.15, 0.21 and 0.27 g of SiO<sub>2 </sub>per plant) were applied to the plant at six, 20 and 28 d after transplanting (six days after the emergency). At 40 days after sowing, the length of guides (m), stem diameter (mm) and number of leaves were determined. Likewise, the number of flowers, number of fruits, length fruits, diameter and weight of the fruit and yield (kg ha<sup>-1</sup>). The variables were analyzed using a general linear model and polynomials by regression. <strong>Results. </strong>The treatment of 0.22 g of SiO<sub>2 </sub>per plant increased stem diameter and length of the guides. The concentration of 0.27 g of SiO<sub>2 </sub>per plant had a positive influenced the growth of the cucumber crop, allowing fruit harvests of greater length, weight and diameter and a greater number of fruits per plant. <strong>Implications. </strong>It is possible to increase the yield of cucumber crops by applying silicon. <strong>Conclusions. </strong>The use of<strong> </strong>SiO<sub>2 </sub>at concentrations of 0.27 g per cucumber plant under greenhouse conditions increases it yield per hectare.</p>

Chinese Bayberry Detection in an Orchard Environment Based on an Improved YOLOv7-Tiny Model

The precise detection of Chinese bayberry locations using object detection technology is a crucial step to achieve unmanned harvesting of these berries. Because of the small size and easy occlusion of bayberry fruit, the existing detection algorithms have low recognition accuracy for such objects. In order to realize the fast and accurate recognition of bayberry in fruit trees, and then guide the robotic arm to carry out accurate fruit harvesting, this paper proposes a detection algorithm based on an improved YOLOv7-tiny model. The model introduces partial convolution (PConv), a SimAM attention mechanism and SIoU into YOLOv7-tiny, which enables the model to improve the feature extraction capability of the target without adding extra parameters. Experimental results on a self-built Chinese bayberry dataset demonstrate that the improved algorithm achieved a recall rate of 97.6% and a model size of only 9.0 MB. Meanwhile, the precision of the improved model is 88.1%, which is 26%, 2.7%, 4.7%, 6.5%, and 4.7% higher than that of Faster R-CNN, YOLOv3-tiny, YOLOv5-m, YOLOv6-n, and YOLOv7-tiny, respectively. In addition, the proposed model was tested under natural conditions with the five models mentioned above, and the results showed that the proposed model can more effectively reduce the rates of misdetections and omissions in bayberry recognition. Finally, the improved algorithm was deployed on a mobile harvesting robot for field harvesting experiments, and the practicability of the algorithm was further verified.

Blue and Red Light Downconversion Film Application Enhances Plant Photosynthetic Performance and Fruit Productivity of Rubus fruticosus L. var. Loch Ness

Light downconversion films can modulate incident light wavebands on crops, converting less utilised wavebands in an efficient way. In this experiment, red (conversion of green into red light wavebands), pink (conversion of UV and green into blue and red light but to a smaller degree than red film), and blue (conversion of UV into blue light) light downconversion films were used to cover blackberry plants throughout all phenological stages (from leaf emergence to fruit harvesting). The plants’ physiological and biometric performance, and fruit yield and quality were evaluated. Plants under blue and red films showed a higher net photosynthetic rate with +23.1% and +14.9%, respectively, and a higher stomatal conductance with +56.0% and +23.6%, respectively, with respect to controls, maintaining stability across stages, except for a decrease under the red film during fruiting. Both films significantly boosted the fruit yield, with the red film increasing the fruit number (+49.8%) and the blue film enhancing the berry shape (+10.7) and fresh weight (+36.6). Notably, no significant differences in nutraceutical quality, including total flavonoid and anthocyanin content, were observed. These findings suggest that light downconversion films, particularly red and blue films, can effectively enhance the photosynthetic performance and fruit production in blackberry plants without compromising the fruit quality. Future research on this topic should focus on balancing plant growth, fruit productivity, and enhancing fruit nutraceutical properties.