Search Results (15)

In the context of blueberry orchard management and automated harvesting, this study introduces an improved YOLOv8 model, ADE-YOLO, designed for precise blueberry ripeness detection, enhancing automated picking efficiency. Built on the YOLOv8n architecture, ADE-YOLO features a dimensionality-reducing convolution at the backbone’s end, reducing computational complexity while optimizing input features. This improvement enhances the effectiveness of the AIFI module, particularly in multi-scale feature fusion, boosting detection accuracy and robustness. Additionally, the neck integrates a dynamic sampling technique, replacing traditional upsampling methods, allowing for more precise feature integration during feature transfer from P5 to P4 and P4 to P3. To further enhance computational efficiency, CIOU is replaced with EIOU, simplifying the aspect ratio penalty term while maintaining high accuracy in bounding box overlap and centroid distance calculations. Experimental results demonstrate ADE-YOLO’s strong performance in blueberry ripeness detection, achieving a precision of 96.49%, recall of 95.38%, and mAP scores of 97.56% (mAP50) and 79.25% (mAP50-95). The model is lightweight, with just 2.95 M parameters and a 6.2 MB weight file, outpacing YOLOv8n in these areas. ADE-YOLO’s design and performance underscore its significant application potential in blueberry orchard management, providing valuable support for precision agriculture. Full article

Precision and non-damaging harvesting is a key direction for the development of mechanized fruit harvesting technologies. Blueberries, with their soft texture and delicate skin, present significant challenges for achieving precise and non-damaging mechanical harvesting. This paper proposes an intelligent recognition and prediction method based on machine vision. The method uses image recognition technology to extract the physical characteristics of blueberries, such as diameter and thickness, and estimates fruit hardness in real-time through a predictive model. The gripping force of the mechanical claw is dynamically adjusted to ensure non-destructive harvesting. Firstly, a chimpanzee optimization algorithm (ChOA) was used to optimize a prediction model that established a mapping relationship between fruit diameter, thickness, weight, and fruit hardness. The radial basis network optimized by the chimpanzee optimization algorithm (ChOA-RBF) model was compared with a non-optimized model, and the results showed that the ChOA-RBF prediction model has significant advantages in predicting fruit hardness. Next, an orthogonal experiment further verified the model, showing that the prediction error between the model’s values and actual values was less than 5%. Additionally, considering practical applications, a simple and efficient two-parameter method was proposed, removing the weight parameter and predicting fruit hardness using only diameter and thickness. Although the two-parameter method increases the prediction error by 0.36% compared to the three-parameter method, it reduces the number of convergence steps by 71 and shortens the computation time by one-third, significantly improving iteration speed. Finally, further crushing experiments showed that using the two-parameter method for hardness prediction through parameter extraction via visual recognition resulted in a relative error of less than 8%, with an average relative error of 3.91%. The error falls within the acceptable range for the safety factor design. This method provides a novel solution for the non-damaging mechanized harvesting of soft fruits. Full article

Identifying fruit maturity accurately and achieving damage-free harvesting are challenges in designing blueberry-picking robots. This paper presents an intelligent flexible picking system. First, we trained a deep learning-based YOLOv8n network to locate the position of the fruit and determine fruit ripeness. We used a neural network to establish the relationship between fruit hardness and shape parameters, achieving an adaptive gripping force for different fruits. To address the issue of dense clusters in some blueberry varieties, we designed a fruit separation subsystem using a combination of flow field analysis and pressure-sensitive experiments. The results show that the mean average precision can reach 84.62%, the precision is 94.49%, the recall is 83.85%, the F1 score is 88.85%, and the test time is 0.12 s, which can meet the requirements for blueberry fruit recognition accuracy and speed. The spacing between closely packed fruits can increase by 4 mm, and the damage-free picking rate exceeds 92%, achieving stable, damage-free harvesting. Full article

In the context of agricultural modernization and intelligentization, automated fruit recognition is of significance for improving harvest efficiency and reducing labor costs. The variety of fruits commonly planted in orchards and the fluctuations in market prices require farmers to adjust the types of crops they plant flexibly. However, the differences in size, shape, and color among different types of fruits make fruit recognition quite challenging. If each type of fruit requires a separate visual model, it becomes time-consuming and labor intensive to train and deploy these models, as well as increasing system complexity and maintenance costs. Therefore, developing a general visual model capable of recognizing multiple types of fruits has great application potential. Existing multi-fruit recognition methods mainly include traditional image processing techniques and deep learning models. Traditional methods perform poorly in dealing with complex backgrounds and diverse fruit morphologies, while current deep learning models may struggle to effectively capture and recognize targets of different scales. To address these challenges, this paper proposes a general fruit recognition model based on the Multi-Scale Attention Network (MSA-Net) and a Hough Transform localization compensation mechanism. By generating multi-scale feature maps through a multi-scale attention mechanism, the model enhances feature learning for fruits of different sizes. In addition, the Hough Transform ellipse detection compensation mechanism uses the shape features of fruits and combines them with MSA-Net recognition results to correct the initial positioning of spherical fruits and improve positioning accuracy. Experimental results show that the MSA-Net model achieves a precision of 97.56, a recall of 92.21, and an mAP@0.5 of 94.81 on a comprehensive dataset containing blueberries, lychees, strawberries, and tomatoes, demonstrating the ability to accurately recognize multiple types of fruits. Moreover, the introduction of the Hough Transform mechanism reduces the average localization error by 8.8 pixels and 3.5 pixels for fruit images at different distances, effectively improving the accuracy of fruit localization. Full article

Blueberry is among the fruits with high economic gains for orchard farmers. Identification of blueberry fruits with different maturities has economic significance to help orchard farmers plan pesticide application, estimate yield, and conduct harvest operations efficiently. Vision systems for automated orchard yield estimation have received growing attention toward fruit identification with different maturity stages. However, due to interfering factors such as varying outdoor illuminations, similar colors with the surrounding canopy, imaging distance, and occlusion in natural environments, it remains a serious challenge to develop reliable visual methods for identifying blueberry fruits with different maturities. This study constructed a YOLO-BLBE (Blueberry) model combined with an innovative I-MSRCR (Improved MSRCR (Multi-Scale Retinex with Color Restoration)) method to accurately identify blueberry fruits with different maturities. The color feature of blueberry fruit in the original image was enhanced by the I-MSRCR algorithm, which was improved based on the traditional MSRCR algorithm by adjusting the proportion of color restoration factors. The GhostNet model embedded by the CA (coordinate attention) mechanism module replaced the original backbone network of the YOLOv5s model to form the backbone of the YOLO-BLBE model. The BIFPN (Bidirectional Feature Pyramid Network) structure was applied in the neck network of the YOLO-BLBE model, and Alpha-EIOU was used as the loss function of the model to determine and filter candidate boxes. The main contributions of this study are as follows: (1) The I-MSRCR algorithm proposed in this paper can effectively amplify the color differences between blueberry fruits of different maturities. (2) Adding the synthesized blueberry images processed by the I-MSRCR algorithm to the training set for training can improve the model’s recognition accuracy for blueberries of different maturity levels. (3) The YOLO-BLBE model achieved an average identification accuracy of 99.58% for mature blueberry fruits, 96.77% for semi-mature blueberry fruits, and 98.07% for immature blueberry fruits. (4) The YOLO-BLBE model had a size of 12.75 MB and an average detection speed of 0.009 s. Full article

The blueberry, a deciduous shrub in the Ericaceae family, is celebrated for its delightful flavor, sweetness, and abundance of anthocyanins and antioxidants, qualities that have garnered significant attention for their potential health benefits. Blueberries grown in diverse environments and exhibit varied anthocyanin profiles, often influenced by factors such as altitude and climate. Varietal groups worldwide have been bred and categorized based on their growth habits and specific cold requirements, particularly with southern highbush cultivars thriving in temperate climates, demonstrating tolerance to higher altitudes or cooler climates—a result of hybridizations involving various Vaccinium species. In the Colombian Andes, southern highbush blueberries thrive in unique high-altitude conditions, leading to exceptional quality due to the region’s cool climate and specific soil characteristics. In this context, this study aimed to chemically characterize and differentiate three southern highbush blueberry cultivars (i.e., ‘Biloxi,’ ‘Legacy’ and ‘Sharpblue’) cultivated in a Colombian Andean plateau and compare them to three commercially available highbush blueberries. This comprehensive evaluation involved examining total phenols, flavonoids, anthocyanin content, and DPPH· free-radical scavenging capacity, as well as conducting anthocyanin-targeted profiling via HPLC-DAD-HRMS. Through supervised multivariate analyses such as sPLS-DA, this study delved into the pattern recognition of those anthocyanins that could potentially serve as markers for quality and cultivar-related chemical trait determination. These findings locate blueberry-derived anthocyanins in a metabolic context and afford some insights into southern highbush blueberry cultivar differentiation to be used for further purposes. Full article

In order to achieve accurate, fast, and robust recognition of blueberry fruit maturity stages for edge devices such as orchard inspection robots, this research proposes a lightweight detection method based on an improved YOLOv5 algorithm. In the improved YOLOv5 algorithm, the ShuffleNet module is used to achieve lightweight deep-convolutional neural networks. The Convolutional Block Attention Module (CBAM) is also used to enhance the feature fusion capability of lightweight deep-convolutional neural networks. The effectiveness of this method is evaluated using the blueberry fruit dataset. The experimental results demonstrate that this method can effectively detect blueberry fruits and recognize their maturity stages in orchard environments. The average recall (R) of the detection is 92.0%. The mean average precision (mAP) of the detection at a threshold of 0.5 is 91.5%. The average speed of the detection is 67.1 frames per second (fps). Compared to other detection algorithms, such as YOLOv5, SSD, and Faster R-CNN, this method has a smaller model size, smaller network parameters, lower memory usage, lower computation usage, and faster detection speed while maintaining high detection performance. It is more suitable for migration and deployment on edge devices. This research can serve as a reference for the development of fruit detection systems for intelligent orchard devices. Full article

To improve the control and detection methods of thiabendazole (TBZ), a fungicide and parasiticide often used in food products, we investigated the performance of the SERS technique applied to frozen blueberry fruits available on the market. TBZ-treated fruit extracts provided a multiplexed SERS feature, where the SERS bands of TBZ could be distinctly recorded among the characteristic anthocyanidins from blueberries. Quantitative SERS of TBZ in a concentration range from 20 µM to 0.2 µM has been achieved in solutions. However, quantitative multiplexed SERS is challenging due to the gradually increasing spectral background of polyphenols from extracts, which covers the TBZ signal with increasing concentration. The strategy proposed here was to employ food bentonite to filter a substantial amount of flavonoids to allow a higher SERS signal-to-background recording and TBZ recognition. Using bentonite, the LOD for SERS analysis of blueberry extracts provided a detection limit of 0.09 µM. From the relative intensity of the specific SERS bands as a function of concentration, we estimated the detection capability of TBZ to be 0.0001 mg/kg in blueberry extracts, which is two orders of magnitude lower than the maximum allowed by current regulations. Full article

Early detection and accurately rating the level of plant diseases plays an important role in protecting crop quality and yield. The traditional method of mummy berry disease (causal agent: Monilinia vaccinii-corymbosi) identification is mainly based on field surveys by crop protection experts and experienced blueberry growers. Deep learning models could be a more effective approach, but their performance is highly dependent on the volume and quality of labeled data used for training so that the variance in visual symptoms can be incorporated into a model. However, the available dataset for mummy berry disease detection does not contain enough images collected and labeled from a real-field environment essential for making highly accurate models. Complex visual characteristics of lesions due to overlapping and occlusion of plant parts also pose a big challenge to the accurate estimation of disease severity. This may become a bigger issue when spatial variation is introduced by using sampling images derived from different angles and distances. In this paper, we first present the “cut-and-paste” method for synthetically augmenting the available dataset by generating additional annotated training images. Then, a deep learning-based object recognition model Yolov5s-CA was used, which integrates the Coordinated Attention (CA) module on the Yolov5s backbone to effectively discriminate useful features by capturing channel and location information. Finally, the loss function GIoU_loss was replaced by CIoU_loss to improve the bounding box regression and localization performance of the network model. The original Yolov5s and the improved Yolov5s-CA network models were trained on real, synthetic, and combined mixed datasets. The experimental results not only showed that the performance of Yolov5s-CA network model trained on a mixed dataset outperforms the baseline model trained with only real field images, but also demonstrated that the improved model can solve the practical problem of diseased plant part detection in various spatial scales with possible overlapping and occlusion by an overall precision of 96.30%. Therefore, our model is a useful tool for the estimation of mummy berry disease severity in a real field environment. Full article

Blueberries are widely planted because of their rich nutritional value. Due to the problems of dense adhesion and serious occlusion of blueberries during the growth process, the development of automatic blueberry picking has been seriously hindered. Therefore, using deep learning technology to achieve rapid and accurate positioning of blueberries in the case of dense adhesion and serious occlusion is one of the key technologies to achieve the automatic picking of blueberries. To improve the positioning accuracy, this paper designs a blueberry recognition model based on the improved YOLOv5. Firstly, the blueberry dataset is constructed. On this basis, we design a new attention module, NCBAM, to improve the ability of the backbone network to extract blueberry features. Secondly, the small target detection layer is added to improve the multi-scale recognition ability of blueberries. Finally, the C3Ghost module is introduced into the backbone network, which reduces the number of model parameters while ensuring the accuracy, thereby reducing the complexity of the model to a certain extent. In order to verify the effectiveness of the model, this paper conducts experiments on the self-made blueberry dataset, and the mAP is 83.2%, which is 2.4% higher than the original network. It proves that the proposed method is beneficial to improve the blueberry recognition accuracy of the model. Full article

Blueberries, which are rich in nutrition, are susceptible to fungal infection during postharvest or storage. However, early detection of diseases in blueberry is challenging because of their opaque appearance and the inconspicuousness of spots in the early stage of disease. The goal of this study was to investigate the potential of hyperspectral imaging over the spectral range of 400–1000 nm to discriminate early disease in blueberries. Scanning electron microscope observation verified that fungal damage to the cellular structure takes place during the early stages. A total of 400 hyperspectral images, 200 samples each of healthy and early disease groups, were collected to obtain mean spectra of each blueberry samples. Spectral correlation analysis was performed to select an effective spectral range. Partial least square discrimination analysis (PLSDA) models were developed using two types of spectral range (i.e., full wavelength range of 400–1000 nm and effective spectral range of 685–1000 nm). The results showed that the effective spectral range made it possible to provide better classification results due to the elimination of the influence of irrelevant variables. Moreover, the effective spectral range combined with an autoscale preprocessing method was able to obtain optimal classification accuracies, with recognition rates of 100% and 99% for healthy and early disease blueberries. This study demonstrated that it is feasible to use hyperspectral imaging to measure early disease blueberries. Full article

The objective of this study was to determine and compare the sugar profile, distribution in fruits and leaves and sink-source relationship in three strawberry (‘Favette’, ‘Alba’ and ‘Clery’) and three blueberry cultivars (‘Bluecrop’, ‘Duke’ and ‘Nui’) grown in organic (OP) and integrated production systems (IP). Sugar analysis was done using high-performance anion-exchange chromatography (HPAEC) with pulsed amperometric detection (PAD). The results showed that monosaccharide glucose and fructose and disaccharide sucrose were the most important sugars in strawberry, while monosaccharide glucose, fructose, and galactose were the most important in blueberry. Source-sink relationship was different in strawberry compared to blueberry, having a much higher quantity of sugars in its fruits in relation to leaves. According to principal component analysis (PCA), galactose, arabinose, and melibiose were the most important sugars in separating the fruits of strawberries from blueberries, while panose, ribose, stachyose, galactose, maltose, rhamnose, and raffinose were the most important sugar component in leaves recognition. Galactitol, melibiose, and gentiobiose were the key sugars that split out strawberry fruits and leaves, while galactose, maltotriose, raffinose, fructose, and glucose divided blueberry fruits and leaves in two groups. PCA was difficult to distinguish between OP and IP, because the stress-specific responses of the studied plants were highly variable due to the different sensitivity levels and defense strategies of each cultivar, which directly affected the sugar distribution. Due to its high content of sugars, especially fructose, the strawberry cultivar ‘Clery’ and the blueberry cultivars ‘Bluecrop’ and ‘Nui’ could be singled out in this study as being the most suitable cultivars for OP. Full article

Increasing consumer awareness of potentially harmful pesticides used in conventional agriculture has prompted organic farming to become notably more prevalent in recent decades. Central European countries are some of the most important producers of blueberries, raspberries and strawberries in the world and organic cultivation methods for these fruits have a significant market share. Fungal pathogens are considered to be the most significant threat to organic crops of berries, causing serious economic losses and reducing yields. In order to ameliorate the harmful effects of pathogenic fungi on cultivations, the application of rapid and effective identification methods is essential. At present, various molecular methods are applied for fungal species recognition, such as PCR, qPCR, LAMP and NGS. Full article

We studied three calls of common marmosets, Callithrix jacchus, elicited in the context of food. Call A, but not B or C, had been described previously as a food call. We presented insects (live mealworms or crickets) and fruit (banana or blueberries) and used playbacks of calls. We found that Call C was produced only in response to seeing insects, and not fruit; it consistently signaled the availability of insects (includes mealworms), and more so when this food could be seen but not consumed. Playback of Call C caused the marmosets to stop feeding on a less preferred food (banana) and, instead, go to inspect a location where mealworms had been found previously, providing evidence that it has referential meaning. No such immediate response was elicited on hearing Call A or background noise. Call A differed from C in that it was produced more frequently when the marmosets were consuming the food than when they could only see it, and call A showed no specificity between insects and fruit. Call B was emitted less frequently than the A or C calls and, by the marmosets that were tested alone, most often to crickets. An audience effect occurred, in that all three calls were emitted more often when the marmosets were tested alone than when in pairs. Recognition of the functional significance of marmoset calls can lead to improved husbandry of marmosets in captivity. Full article

Previous research has shown beneficial effects of polyphenol-rich diets in ameliorating cognitive decline in aging adults. Here, using a randomized, double blinded, placebo-controlled chronic intervention, we investigated the effect of two proprietary blueberry formulations on cognitive performance in older adults; a whole wild blueberry powder at 500 mg (WBP500) and 1000 mg (WBP1000) and a purified extract at 100 mg (WBE111). One hundred and twenty-two older adults (65–80 years) were randomly allocated to a 6-month, daily regimen of either placebo or one of the three interventions. Participants were tested at baseline, 3, and 6 months on a battery of cognitive tasks targeting episodic memory, working memory and executive function, alongside mood and cardiovascular health parameters. Linear mixed model analysis found intervention to be a significant predictor of delayed word recognition on the Reys Auditory Verbal Learning Task (RAVLT), with simple contrast analysis revealing significantly better performance following WBE111 at 3 months. Similarly, performance on the Corsi Block task was predicted by treatment, with simple contrast analysis revealing a trend for better performance at 3 months following WBE111. Treatment also significantly predicted systolic blood pressure (SBP) with simple contrast analysis revealing lower SBP following intervention with WBE111 in comparison to placebo. These results indicate 3 months intervention with WBE111 can facilitate better episodic memory performance in an elderly population and reduce cardiovascular risk factors over 6 months. Full article