Fruit Clusters Research Articles

Effect of pre-flowering gibberellic acid applications on tartaric acid content in grape berries

Tartaric acid (TA) is a characteristic acid in grapes (Vitis vinifera L.), capable of increasing the acidity of wine, providing a fresh and lively taste, and contributing to the stability of wine while reducing the risk of microbial contamination. However, the transcriptional regulatory mechanisms underlying TA synthesis remain not clear. Here, we found that gibberellic acid (GA3) treatment can increase the content of TA with the upregulation of TA synthesis-related gene, which was confirmed by RNA-seq results. Yeast one-hybrid and electrophoretic mobility shift assay (EMSA) validated that transcription factor VvbZIP60 can interact with the promoter of VvL-IdnDH and activate its expression to promote TA synthesis. In summary, exogenous application of GA3 can elongate fruit clusters, improve fruit quality, and especially increase the TA content in fruit. This study provides a theoretical basis for the purposeful regulation of fruit TA content in grape production.

A review on banana flower: Nutritional composition, processed products and health benefits

India is the world’s largest producer of banana with 13.90 million tons followed by Uganda (10.14 million tons). Banana blossom also known as a banana heart, is a fleshy purple - skinned flower shaped like tear, which grows at the end of banana fruit cluster. Now days researchers aimed to addressing dietary related diseases through promotion of food products enriched with high protein, vitamins, minerals and dietary fiber. Banana blossom is rich source of nutrients and antioxidants which have several health benefits. The juice from the male bud provides an apparent remedy for stomach problems in people of all ages. Banana blossom is a popular dish in Sri Lanka. It is consumed as a curry as well as a boiled or deep fried salad with rice and wheat bread. It is generally valued as a fiber-rich source. Dietary fiber has demonstrated its benefits in health and disease prevention in medical nutrition therapy. Consumption of dietary fiber is known to lower blood cholesterol level, normalize blood glucose and insulin level, promote normal laxation, avoid constipation, prevent diverticulosis and diverticukitis, lower the risk of colon cancer and breast cancer and prevent obesity. The flower has been used to treat bronchitis, constipation and peptic ulcer. The extract has anti-oxidant property that prevents free radicals and control cell and tissue damage. Based on the main components of banana flower extract and its anti-oxidant properties, we hypothesized that the banana flower extract may have anticancer activities against cancer cell lines.

Effect of Spraying with Micro-Elements, Gibberellic Acid and Salicylic Acid on Some Yield Traits of Date Palm CV. Khastawi.

The study was conducted in one of the private palm orchards in the Euphrates district on date palm trees (CV. Khastawi) aged 30 years to find out the response of the date palm cultivar Khastawi to spraying with micro-elements at concentrations (0, 1 g L-1 ) and symbolized by (M0 and M1), and spraying with gibberellic acid at concentrations (0, 100, 200 mg L-1 ) and symbolized by (G0, G1, and G2) respectively, and spraying with salicylic acid in concentrations (0, 100, 200 mg L-1 ) and symbols symbolized by (S0, S1, S2) respectively. 54 trees were selected as homogeneous as possible, and the number of fronds for palms and fruit clusters was unified. All service operations of the orchard were carried out similarly to adding animal manure, pruning, pollination, watering, pest control and other service operations for all experimental units. The results showed that spraying with microelements at a concentration (M1) significantly affected all studied traits except for the non-reducing sugar content of the fruits. It amounted to (10.76 g, 15.63 kg cluster-1 , 125.03 kg palm-1 , 69.37%, 33.78%, 53.61%) this is for the traits (fruit weight, cluster weight, yield, total soluble solids, reducing sugars, total sugars), respectively. Also, spraying with gibberellin showed a significant effect on the traits (fruit weight, cluster weight, yield, total soluble solids), and the treatment (G2) gave the highest values for the traits (fruit weight, cluster weight, yield), with 10.53 g, 15.46 kg cluster-1 , 123.71 kg palm-1 , respectively. At the same time, treatment (G0) achieved the highest value of total soluble solids (67.50%). On the other hand, salicylic spraying did not significantly affect the studied traits, except total soluble solids and reducing sugars. The concentration (S2) showed the best values for the two traits, with 67.59% and 34.36%, respectively. The two-way interactions between the study factors showed a significant effect that varied according to the type of trait and the interaction factors. Whereas the three-way interaction between the study factors reached the level of significance in all the studied traits. The most significant effect of the interactions was achieved according to the type of trait and the interacting factors, while the control treatment showed the lowest values of most of the traits. Keywords: Date palm, Micro-elements, Gibberellic acid, Salicylic acid, yield.

A Focused Insight into Sumac: Biological, Chemical, Health Benefits and Its Applications in Food Industry

Sumac Spice is a tangy red-purple powder produced by drying and grinding the hairy clusters of sumac fruit. It is often used in several regions to add a lemony and astringent taste to many dishes. Sumac is considered a valuable plant that governs nutritious elements such as proteins, unsaturated fatty acids, dietary fibers, minerals, vitamins and many polyphenols. Its phenolic content contributes to activate its medical and therapeutic role. Traditionally, sumac was effective in treating several health issues for centuries. Recently, many studies proved that it has an antibacterial, antiviral, anti-inflammatory, antioxidant, anticancer, cardioprotective, hypolipidemic and hypoglycemic activities. Sumac succeeded to put its mark in the field of the food industry since it was utilized as a natural food additive such as preservative, antioxidant and colorant in various food products. It successfully boosts the quality of different food items such as bread, meat, dairy products, tomato paste, barley soap, peanut oil and shrimps. In total, sumac spice is not only a nutritious spice that adds a distinctive taste to many dishes, but also when incorporated in food industry it meets the consumer concern for the ''natural label'' food products, as well as its valuable role in disease prevention and health promotion.

O2RNet: Occluder-occludee relational network for robust apple detection in clustered orchard environments

Automated apple harvesting has attracted significant research interest in recent years because of its great potential to address the issues of labor shortage and rising labor costs. One key challenge to automated harvesting is accurate and robust apple detection, due to complex orchard environments that involve varying lighting conditions, fruit clustering and foliage/branch occlusions. Apples are often grown in clusters on trees, which may be mis-identified as a single apple and thus causes issues in fruit localization for subsequent robotic harvesting operations. In this paper, we present the development of a novel deep learning-based apple detection framework, called the Occluder-Occludee Relational Network (O2RNet), for robust detection of apples in clustered situations. A comprehensive dataset of RGB images were collected for two varieties of apples under different lighting conditions (overcast, direct lighting, and back lighting) with varying degrees of apple occlusions, and the images were annotated and made available to the public. A novel occlusion-aware network was developed for apple detection, in which a feature expansion structure is incorporated into the convolutional neural networks to extract additional features generated by the original network for occluded apples. Comprehensive evaluations of the developed O2RNet were performed using the collected images, which outperformed 12 other state-of-the-art models with a higher accuracy of 94% and a higher F1-score of 0.88 on apple detection. O2RNet provides an enhanced method for robust detection of clustered apples, which is critical to accurate fruit localization for robotic harvesting.

Application of Amelioran Compost of Empty Palm Plus Fruit Bunches to Soybean Plants in Ultisols through Multivariate Tests and Principal Component Analysis

The decline in national soy output results from a decline in planted area. Optimizing ultisol land is one of the efforts undertaken to increase national soybean production. This study seeks to examine the effect of composting empty palm oil bunches on the growth and yield of soybeans using multivariate tests and principal component analysis during the compost's incubation period. The application of compost and empty palm fruit clusters was able to chelate Al-DD and increase the soil's available P and K. There is a positive Pearson correlation between pH, Ca, K, and Mg, as well as a positive Pearson correlation between all observed growth and development parameters of soybean plants. Pearson's correlation demonstrates the relationship between the characteristics of plant height, number of leaves, number of branches, number of pods, age of blossoming, age of harvest, and productivity. Positive correlations are observed for each parameter observed.

Blueberry Ripeness Detection Model Based on Enhanced Detail Feature and Content-Aware Reassembly

Blueberries have high nutritional and economic value and are easy to cultivate, so they are common fruit crops in China. There is a high demand for blueberry in domestic and foreign markets, and various technologies have been used to extend the supply cycle of blueberry to about 7 months. However, blueberry grows in clusters, and a cluster of fruits generally contains fruits of different degrees of maturity, which leads to low efficiency in manually picking mature fruits, and at the same time wastes a lot of manpower and material resources. Therefore, in order to improve picking efficiency, it is necessary to adopt an automated harvesting mode. However, an accurate maturity detection model can provide a prerequisite for automated harvesting technology. Therefore, this paper proposes a blueberry ripeness detection model based on enhanced detail feature and content-aware reassembly. First of all, this paper designs an EDFM (Enhanced Detail Feature Module) that improves the ability of detail feature extraction so that the model focuses on important features such as blueberry color and texture, which improves the model’s ability to extract blueberry features. Second, by adding the RFB (Receptive Field Block) module to the model, the lack of the model in terms of receptive field can be improved, and the calculation amount of the model can be reduced at the same time. Then, by using the Space-to-depth operation to redesign the MP (MaxPool) module, a new MP-S (MaxPool–Space to depth) module is obtained, which can effectively learn more feature information. Finally, an efficient upsampling method, the CARAFE (Content-Aware Reassembly of Features) module, is used, which can aggregate contextual information within a larger receptive field to improve the detection performance of the model. In order to verify the effectiveness of the method proposed in this paper, experiments were carried out on the self-made dataset “Blueberry—Five Datasets” which consists of data on five different maturity levels of blueberry with a total of 10,000 images. Experimental results show that the mAP (mean average precision) of the proposed network reaches 80.7%, which is 3.2% higher than that of the original network, and has better performance than other existing target detection network models. The proposed model can meet the needs of automatic blueberry picking.

Unstructured road extraction and roadside fruit recognition in grape orchards based on a synchronous detection algorithm.

Accurate road extraction and recognition of roadside fruit in complex orchard environments are essential prerequisites for robotic fruit picking and walking behavioral decisions. In this study, a novel algorithm was proposed for unstructured road extraction and roadside fruit synchronous recognition, with wine grapes and nonstructural orchards as research objects. Initially, a preprocessing method tailored to field orchards was proposed to reduce the interference of adverse factors in the operating environment. The preprocessing method contained 4 parts: interception of regions of interest, bilateral filter, logarithmic space transformation and image enhancement based on the MSRCR algorithm. Subsequently, the analysis of the enhanced image enabled the optimization of the gray factor, and a road region extraction method based on dual-space fusion was proposed by color channel enhancement and gray factor optimization. Furthermore, the YOLO model suitable for grape cluster recognition in the wild environment was selected, and its parameters were optimized to enhance the recognition performance of the model for randomly distributed grapes. Finally, a fusion recognition framework was innovatively established, wherein the road extraction result was taken as input, and the optimized parameter YOLO model was utilized to identify roadside fruits, thus realizing synchronous road extraction and roadside fruit detection. Experimental results demonstrated that the proposed method based on the pretreatment could reduce the impact of interfering factors in complex orchard environments and enhance the quality of road extraction. Using the optimized YOLOv7 model, the precision, recall, mAP, and F1-score for roadside fruit cluster detection were 88.9%, 89.7%, 93.4%, and 89.3%, respectively, all of which were higher than those of the YOLOv5 model and were more suitable for roadside grape recognition. Compared to the identification results obtained by the grape detection algorithm alone, the proposed synchronous algorithm increased the number of fruit identifications by 23.84% and the detection speed by 14.33%. This research enhanced the perception ability of robots and provided a solid support for behavioral decision systems.

An Effective Hybrid Fungicide Containing Tea Tree Oil and Difenoconazole for Grape Powdery Mildew Management

Grape powdery mildew caused by Erysiphe necator (Schw.) Burr. is a destructive disease in vineyards. Synthetic fungicides are the main tool to combat this disease. The search for new alternatives to reduce pesticide usage and tactical approaches for resistance management encouraged us to develop the novel strategy that we report here. We evaluated the efficacy of a new premixed hybrid fungicide containing the demethylation inhibitor (DMI) difenoconazole and essential tea tree oil (TTO), derived from the Melaleuca alternifolia plant, against grape powdery mildew in seven field trials and two large-scale demonstration trials conducted in two different regions in the world, including Chile and Israel. Foliar sprays of difenoconazole-TTO were applied as a preventive treatment in field trials at 40–80 up to 80–160 gr/ha active ingredient, and they were highly effective in controlling powdery mildew on the fruit clusters of both wine and table grapes in experimental and large-scale demonstration trials and provided up to 99% efficacy in disease incidence and severity compared with the untreated control. Difenoconazole-TTO was as or more effective than other DMI fungicides, including difenoconazole, a pre-mixed fungicide boscalid-pyraclostrobin, or treatments that included various fungicides applied in rotation or mixtures of fungicides. The results suggest that a combination of difenoconazole-TTO with a reduced synthetic chemical load can be included in powdery mildew control programs for grapevine as a strategic approach in fungicide resistance management in vineyards.

Impact of Operational Parameters on Droplet Distribution Using an Unmanned Aerial Vehicle in a Papaya Orchard

Papaya production and export is increasingly expanding in the world market due to the nutritional importance of the fruit. Phytosanitary issues, labor shortages, and unevenness in land-based costal and motorized applications compromise crops, the environment, and humankind. The purpose of this study was to evaluate the efficiency of droplet distribution using an unmanned aerial vehicle, with different application rates (12.0, 15.0, and 18.0 L ha−1) and spray nozzles (XR110015 and MGA015) in the upper (UL), middle (ML), and lower (LL) layers, and on papaya fruit clusters (BF). Water-sensitive paper labels and artificial targets were used to assess the efficiency. Coverage, density, droplet distribution, and droplet diameter were influenced by the application rates in the following order: 18.0 > 15.0 > 12.0 L ha−1, showing concentrated droplet distribution in the respective layers: UL > ML > LL > BF. The 18.0 L ha−1 rate increased the variables examined, and the droplet coverage on the UL using the XR110015 nozzle was 6.56 times greater than that found on the LL and BF. The MGA015 nozzle presented better results in the LL and BF in all variables analyzed. The UAVs were efficient in applying to the papaya crop and further studies should be carried out in order to confirm the efficacy of plant protection products applied using this technology.

Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms

Robots must first detect the number of banana bunches when making judgements on sterile bud removal and estimating weight for harvest in the field environment. Banana bunches are complex in shape, arranged in a nonlinear helical curve along the stalk, and have different growth states in different periods, with bunches widely spaced in the early period and densely arranged in the harvest period. Deep learning nor classical image-processing algorithms alone can detect and count bunches in both periods. Therefore, these algorithms were combined to calculate the number of bunches in the two periods. For counting bunches in the debudding period, the convolutional neural network Deeplab V3 + model and classic image-processing algorithm were combined to finely segment bunches and calculate bunch numbers, providing intelligent decision-making for judgment on the timing for debudding. To count bunches during harvest, based on deep learning to identify the overall banana fruit cluster, the edge detection algorithm was employed to extract the centroid points of fruit fingers, and the clustering algorithm was used to determine the optimal number of bunches on the visual detection surface. An estimation model for the total number of bunches, including hidden ones, was created based on their helical curve arrangement. The results indicated a target segmentation MIoU of 0.878 during the debudding period, a mean pixel precision of 0.936, and a final bunch detection accuracy rate of 86%. Bunch detection was highly challenging during the harvest period, with a detection accuracy rate of 76% and a final overall bunch counting accuracy rate of 93.2%. Software was designed to estimate banana fruit weight during the harvest period. This research method provided a theoretical basis and experimental data support for automatic sterile bud removal and weight estimation for bananas.

Recognition and Counting of Apples in a Dynamic State Using a 3D Camera and Deep Learning Algorithms for Robotic Harvesting Systems.

Recognition and 3D positional estimation of apples during harvesting from a robotic platform in a moving vehicle are still challenging. Fruit clusters, branches, foliage, low resolution, and different illuminations are unavoidable and cause errors in different environmental conditions. Therefore, this research aimed to develop a recognition system based on training datasets from an augmented, complex apple orchard. The recognition system was evaluated using deep learning algorithms established from a convolutional neural network (CNN). The dynamic accuracy of the modern artificial neural networks involving 3D coordinates for deploying robotic arms at different forward-moving speeds from an experimental vehicle was investigated to compare the recognition and tracking localization accuracy. In this study, a Realsense D455 RGB-D camera was selected to acquire 3D coordinates of each detected and counted apple attached to artificial trees placed in the field to propose a specially designed structure for ease of robotic harvesting. A 3D camera, YOLO (You Only Look Once), YOLOv4, YOLOv5, YOLOv7, and EfficienDet state-of-the-art models were utilized for object detection. The Deep SORT algorithm was employed for tracking and counting detected apples using perpendicular, 15°, and 30° orientations. The 3D coordinates were obtained for each tracked apple when the on-board camera in the vehicle passed the reference line and was set in the middle of the image frame. To optimize harvesting at three different speeds (0.052 ms-1, 0.069 ms-1, and 0.098 ms-1), the accuracy of 3D coordinates was compared for three forward-moving speeds and three camera angles (15°, 30°, and 90°). The mean average precision (mAP@0.5) values of YOLOv4, YOLOv5, YOLOv7, and EfficientDet were 0.84, 0.86, 0.905, and 0.775, respectively. The lowest root mean square error (RMSE) was 1.54 cm for the apples detected by EfficientDet at a 15° orientation and a speed of 0.098 ms-1. In terms of counting apples, YOLOv5 and YOLOv7 showed a higher number of detections in outdoor dynamic conditions, achieving a counting accuracy of 86.6%. We concluded that the EfficientDet deep learning algorithm at a 15° orientation in 3D coordinates can be employed for further robotic arm development while harvesting apples in a specially designed orchard.

Effect of Pruning Treatments and the Addition of Humic Acid on Growth and Yield of Zaytoni Cultivar Grape Trees

This study was conducted in one of the private orchards located in the Altun Kobri sub-district of Dibs district, about (20) km away from Kirkuk governorate, during the growing season (2020-2021). This is to study the effect of six levels of summer pruning, the first level (T1) without pruning, the second level (T2) removing the tops of the main branches after the decade, and the third level (T3) removing the tops of the main branches after the decade and the fourth level (T4) removing leaves and leaving (8) Leaves for each fruit cluster, the fifth level (T5) remove the leaves and leave (10) leaves for each fruit cluster, the sixth level (T6) remove the leaves and leave (12) leaves for each fruit cluster. And the addition of three levels of humic acid (zero, 20, 40) g. vine-1 and its symbol (H1, H2, H3) sequentially, in the growth and yield characteristics of grape vines of the olive variety, and it was added a week after the contract (25/5/2021). The experiment was carried out according to a randomized complete block design with three sectors.

Using Green Atlas Cartographer to investigate orchard-specific relationships between tree geometry, fruit number, fruit clustering, fruit size and fruit colour in commercial apples and pears

Using Green Atlas <i>Cartographer</i> to investigate orchard-specific relationships between tree geometry, fruit number, fruit clustering, fruit size and fruit colour in commercial apples and pears

Influence of Preharvest Bagging on Maturity Indices and Postharvest Quality of Cherry Tomato (Solanum lycopersicum var. cerasiforme)

The production of cherry tomato (Solanum lycopersicum var. cerasiforme) is negatively affected by harsh environmental conditions such as extremely high and low temperatures, wind and hail damage, and pest and disease infestation. These factors delay maturity and cause uneven ripening, fruit abrasion, and blemishes, which consequently result in poor fruit quality and reduced shelf life. Preharvest bagging is an environmentally friendly alternative technique for enhancement of fruit quality and hence alleviates the stated problems. The study evaluated the physico-chemical quality of ‘Tinker’ and ‘Roma VF’ cherry tomato as influenced by preharvest bagging (transparent and blue plastics) during 8 days of shelf life at ambient conditions. Five clusters of fruit per plant per cultivar with a diameter of 1.5 to 2.0 cm were bagged after 16 days of fruit set and harvested at the green maturity stage, 12 days after preharvest bagging for the assessment of postharvest quality. Preharvest bagging effectively accelerated fruit maturity and ripening as indicated by enhanced fruit size, uniform color development, high pH, dry matter (DM) content, soluble solid content (SSC), and low titratable acidity (TA) during shelf life. Bagged fruit had higher loss of firmness and weight mainly due to ripening and showed very slight incidence of diseases during shelf life of 8 days. Unbagged cherry tomato had delayed maturity and ripening; small-sized fruit; uneven color development; low pH, SSC, and DM; and high TA. Although unbagged cherry tomato had lower firmness and weight loss due to delayed ripening, fruit showed moderate to severe incidence of tomato bacterial canker disease (Clavibacter michiganensis subsp. michiganensis) during shelf life. These results indicated that preharvest bagging accelerated fruit maturity and ripening, improved physico-chemical quality, and reduced disease infestation on cherry tomato during shelf life.

Participatory tomato (Lycopersicon esculentum Mill) variety selection and evaluation for production in Eastern Amhara regional state

A field experiment was conducted at Kobo and Mersa under irrigation with the objectives of evaluating the adaptability and yield potential of different tomato varieties and asses’ farmers’ perception. The experiment was laid out in Randomized Complete Block Design (RCBD) with three replications and used six released tomato varieties. The result showed that there was variation on yield and yield components of tomato varieties. The highest number of fruit clusters per plant (15.7) and marketable yield (45.8 tha-1) was recorded from variety Oval red whereas highest fruit per plant (70.5) and fruit length (5.9 cm) was recorded from variety Mersa. From the six tested tomato varieties Oval red was first ranked by its yield advantage from other tomato varieties and its shape has good market value by farmers’ selection. Variety Mersa was selected by farmer’s due to its disease resistance (powdery mildew) and good market value. Therefore, Oval Red and Mersa tomato varieties were recommended for Mersa and Kobo areas under irrigation.

Post-Bloom CPPU Application Is Effective at Improving Fruit Set and Suppressing Coloration but Ineffective at Increasing Fruit Size in Litchi

This study aimed to provide a reference for the practical use of forchlorfenuron (CPPU) in the improvement of fruit set and quality (especially size) in litchi (Litchi chinensis Sonn.). CPPU at 5 mg/L was sprayed to fruit clusters of ‘Feizixiao’ at 2, 4, 6 and 8 weeks after female bloom (WAFB) in 2017 and at 2, 4, 6, 8, 9 or 10 WAFB in 2018, with spraying water as the control. The treatments were all effective at suppressing fruit abscission, resulting in higher fruit retention at harvest. Except for treatment at 2 WAFB, which caused stunted fruit and significantly reduced fruit weight, all the treatments had no significant influence on fruit weight and flesh (aril) weight, although CPPU tended to increase pericarp weight and strongly suppressed fruit coloration, and such effects were most significant in treatments at 4, 6 and 8 WAFB. Content of total soluble solids (TSS) in commercially ripe fruit (11WAFB) was not significantly influenced by CPPU applied at any of the stages. Ripe fruit continued to gain redness but lost TSS as it became overripe. CPPU suppressed redness gaining, the effect being stronger in later application. The treatments did not influence TSS loss, but treatments at 4, 6 and 8 WAFB significantly reduced the increase in fruit membrane leakage. In treatment at 6 WAFB, CPPU residue in the pericarp decreased sharply with time but relatively constant in the aril, where it maintained lower than 10 μg/kg, the maximal residue limitation in Australia and the United States. The results suggest that 5 mg/L CPPU is effective at improving fruit set and suppressing fruit pigmentation but has no significant effect on fruit size and TSS accumulation or maintenance in litchi.

First report of Colletotrichum fioriniae causing anthracnose on the fruit of omija (schisandra) in South Korea.

Omija or Schisandra (Schisandra chinensis Baillon) is one of Korea's most unique fruits and have been used in herbal medicine. It is also used for making cold drinks during summer and hot tea during winter. Among the different diseases, anthracnose poses great threat for omija production as it reduces the yield and market quality of fruits. In September 2021, severe anthracnose symptoms were observed in some commercial farmer fields (36°36'14.9"N 127°59'31.3"E) in Mungyeong and disease incidence was approximately 30 to 35%. The symptoms on fruits were manifested as small sunken lesions. The presumed fungi were isolated from necrotic tissues on potato dextrose agar (PDA) and purified using the single spore isolation technique (Cai et al. 2009; Hassan et al.2019). A total of 20 morphological similar isolates were obtained from 18 sampled fruits. The cultures were incubated at 25°C in the dark for 5 to 7 days. The colonies were pink with white aerial mycelium on the upper side and pink with black zones on the reverse. All the colonies produced fusiform conidia measuring 12.7 to 17.5 × 4.7 to 7.4 μm (n=50). The appressoria were brown, globose to ellipsoid and measuring 6.3 to 12 × 5.9 to 9.7 μm (n=30). Morphological characteristics of present isolates were in concordance with that of Colletotrichum acutatum sensu lato (Damm et al., 2012). For molecular identification, genomic DNA of five representative isolates was extracted for sequencing of target markers and the phylogenetic tree was constructed. For amplification and sequencing of internal transcribed spacers (ITS), glyceraldehyde-3-phosphate dehydrogenase (GAPDH), actin (ACT) chitin synthase-1 (CHS-1), histone 3 (HIS3) and beta-tubulin (TUB2), the primer pairs ITS1/ITS4, GDF1/GDR1, ACT-512F/ACT-783R, CHS1-79F/CHS-1-354R, CYLH3F /CYLH3R and BT2a /BT2b were used respectively (Damm et al., 2012). The resulting sequences were deposited in GenBank with accession numbers LC680890 to LC680914 and LC687627 to LC687631. The maximum likelihood tree based on concatenated sequences of the five genes shows that present isolates were grouped in the C. fioriniae. Pathogenicity on red schisandra fruits was confirmed using the two isolates OR1 and O59. Fruit clusters (20-30 fruits/ cluster) were surface sterilized by dipping them in 1% NaOCl for 3 minutes, rinsing in sterile distilled water, and placing them in a sterile plastic box containing moist paper tissues. All the fruits in each cluster were inoculated with 10 μl of 106 conidia/ml suspensions of each isolate by following either the wounded or un- wounded method (Hassan et al.2019). Fruit clusters treated with sterile distilled water served as a control. Three fruit clusters were inoculated per isolate for each method. With the wounding method, all the inoculated fruits showed typical anthracnose symptoms after 4 days of incubation at 25 ± 1°C in the dark, while the control and un- wounded fruits remained symptomless. This test was repeated twice. The species C. fioriniae were reisolated from the infected fruit. The morphology and ITS sequences of the reisolated fungi were consistent with the original one, fulfilling Koch's postulates. The species C. fioriniae have been described as a causal agent of anthracnose of numerous hosts worldwide including South Korea (Damm et al., 2012; Hassan et al.2019; Oo et al. 2016; Lee et al. 2020). To our knowledge, this is the first report of C. fioriniae as causal agent of omija anthracnose in South Korea. As this disease results in deterioration of fruits quality, management practices should be tailored to address C. fioriniae management. Acknowledgments This research was supported by Kyungpook National University Research Fund, 2021. References Cai, L., et al. 2009. Fungal Divers. 39:183. Damm, U., et al. 2012. Stud. Mycol. 73:37. Hassan, O., et al. 2019. Sci. Rep. 9:12089. Lee, D., et al. 2020. Mycobiology. 48: 210. Oo, M.M., et al. 2016. Mycobiology. 44: 325.

An effective litchi detection method based on edge devices in a complex scene

Due to the random distribution and irregular growth of fruit clusters on fruit trees, litchi mainly depends on manual picking and harvesting. Given this situation, the visual-guidance automatic picking system is utilised in existing studies to reduce the picking time effectively and improve economic benefits. However, the existing methods are primarily based on high-performance computing equipment in the laboratory. This equipment's volume and energy consumption makes it challenging to deploy, severely limiting the application of automatic picking. This study adopts portable, low-power edge devices and proposes an effective litchi detection method to solve the shortcomings mentioned above. First, litchi images in the orchard were collected, and data augmentation was adopted to improve the generalisation of the images. Then, an effective litchi detection model was constructed to detect the litchi. Finally, the trained model was compressed to remove redundant parameters according to the channel pruning and layer pruning algorithms to deploy the model on edge devices. The knowledge distillation was leveraged to fine-tune the model. The experimental results demonstrated that the proposed method could construct a model of only 7.6 MB with a compression rate of 96.8%. The model can achieve an average precision of 95.3% and an average recall of 97.3% at 117.6 frames per second (FPS), 1.8 times that of the original model. The proposed method can be easily deployed on portable and low-computing automatic picking equipment to achieve rapid and accurate detection of litchi, which is of great significance for biological systems. • A litchi detection method based on edge device for automatic picking is proposed. • Trained model was compressed at a 96.8% rate for better deployment on edge device. • The compressed model can achieve 95.3% precision and 97.3% recall at 117.6 FPS. • The proposed method is portable, low power consumption, and suitable for orchard.

Computer Vision and Machine Learning Based Grape Fruit Cluster Detection and Yield Estimation Robot

Estimation and detection of fruits plays a crucial role in harvesting. Traditionally, fruit growers rely on manual methods but nowadays they are facing problems of rapidly increasing labor costs and labour shortage. Earlier various techniques were developed using hyper spectral cameras, 3D images, clour based segmentation where it was difficult to find and distinguish grape bunches. In this research computer vision based novel approach is implemented using Open Source Computer Vision Library (OpenCV) and Random Forest machine learning algorithm for counting, detecting and segmentation of blue grape bunches. Here, fruit object segmentation is based on a binary threshold and Otsu method. For training and testing, classification based on pixel intensities were taken by a single image related to grape and non-grape fruit. The validation of developed technique represented by random forest algorithm achieved a good result with an accuracy score of 97.5% and F1-Score of 90.7% as compared to Support Vector Machine (SVM). The presented research pipeline for grape fruit bunch detection with noise removal, training, segmentation and classification techniques exhibit improved accuracy.