Search Results (163)

Accurate tomato ripeness detection is crucial for automated harvesting; however, complex greenhouse environments—characterized by dynamic light interference, foliage occlusion, and dense fruit overlapping—severely hinder detection performance and lead to frequent misdetections. This study aims to develop a high-precision, lightweight detection model that simultaneously addresses these three core challenges, thereby providing a technically deployable algorithmic foundation for resource-constrained agricultural edge devices. To this end, we propose CFD-DETR, a lightweight tomato ripeness detection model based on the RT-DETR architecture. The model incorporates a CAEfficientViT backbone for the lightweight extraction of multi-scale color and texture features. Furthermore, a Focused Efficient Additive Attention (FEAA) mechanism is integrated to capture fine-grained local ripening traits with minimal computational overhead. During feature reconstruction, a Deep Dynamic Upsampling (DwDySample) operator is utilized to preserve semantic integrity. Additionally, we designed the Wise-SIoU loss function, which dynamically penalizes low-quality samples to enhance boundary fitting and robustness against background noise. Experimental evaluations demonstrate that CFD-DETR achieves 90.2% mAP@0.5, outperforming the baseline model by 2.1 percentage points while significantly reducing the parameter count and computational complexity by 47.2% and 52.5%, respectively. Cross-dataset validation on the publicly available Laboro Tomato and RaUTD datasets confirms the model’s superior generalization capabilities. Overall, CFD-DETR provides a highly efficient and robust solution for real-time agricultural robotics. Full article

Accurate fruit ripeness assessment is essential for optimizing harvest timing and ensuring postharvest quality, particularly in climacteric fruits such as peaches, which exhibit rapid and heterogeneous ripening. This study proposes a deep learning-based approach for multistage peach ripeness classification across five maturity levels (green, green-blushed, blushed, yellow-blushed, and fully yellow). Four datasets were constructed using controlled image acquisition, segmentation, data augmentation, and perceptual hashing to mitigate data leakage. The performance of AlexNet, EfficientNet-B0, and three YOLO (You Only Look Once) architectures (YOLOv8, YOLOv11, and YOLOv12) was evaluated using standard metrics, including accuracy, precision, recall, F1 score, mAP, and inference speed. Results show that YOLO-based models significantly outperform classical networks, achieving accuracies between 95.25% and 98.3% and mAP@0.5 above 98.25%, while also reducing inference time to 8.1–12.7 ms compared with 722.23 ms for AlexNet and 171.87 ms for EfficientNet-B0. In a practical sorting experiment with 214 peaches, YOLOv12 achieved 92.06% accuracy, demonstrating robust real-world performance. Misclassifications were primarily observed between adjacent ripeness stages. These findings indicate that YOLO-based models provide an effective and scalable solution for real-time fruit sorting, while the use of perceptual hashing enhances dataset reliability and model generalization for deployment in agricultural quality control systems. Full article

Honeysuckle berries (Lonicera caerulea) represent a valuable source of bioactive compounds, primarily flavonoids, and iridoids. This study compared the chemical composition and in vitro antioxidant and antidiabetic properties of resin-purified extracts from ripe, unripe, and unripe lactofermented honeysuckle berries. Polyphenols and iridoids were identified using UPLC-ESI-qTOF-MS/MS and quantified using HPLC-PDA. A total of 6 anthocyanins, 7 phenolic acids, 9 flavan-3-ols, 8 iridoids, 8 flavonols, 3 flavones, and 1 flavanonol were identified in the extracts. The extract from ripe fruits was characterized by a high cyanidin glycoside content (273.59 mg/g) and high iridoid content (138.30 mg/g). The amount of individual iridoids varied among the extracts, with the highest level of loganic acid detected in the unripe fruit extract (39.42 mg/g) and the highest level of sweroside in the ripe fruit extract (55.59 mg/g). Phenolic acid content was approximately twofold higher in extracts from unripe and fermented fruits compared with ripe fruit extracts, suggesting a decrease during ripening, while fermentation did not significantly affect phenolic acid content. Among flavonols, quercetin and isorhamnetin derivatives were identified, with quercetin 3-O-rutinoside being the predominant compound in all extracts. The ripe fruit extract exhibited the strongest radical scavenging activity (in ABTS and DPPH assays), ferric ion-reducing power (FRAP), and α-amylase inhibition, while all extracts exhibited comparable α-glucosidase inhibition. These findings indicate that L. caerulea extracts, especially from ripe fruits, are a rich source of biologically active compounds with potential relevance for managing oxidative stress and hyperglycemia. Full article

Dragon fruit (Hylocereus undatus) is a high-value crop in the Philippines that has gained commercial importance due to its nutritional benefits and profitability. However, determining the optimal maturity stage remains challenging for farmers relying on manual classification. We developed an automated system that integrates You Only Look Once Version 7 (YOLOv7) for dragon fruit detection. A dataset of dragon fruit images across three maturity levels, unripe, ripe, and over-ripe, was collected and used to train the model. The system classifies maturity stages based on external features such as color and shape, and its performance will be evaluated using a confusion matrix. By providing accurate classification, the proposed system aims to assist farmers in harvesting dragon fruits at their optimal stage, improving yield quality and market competitiveness while reducing human error. Full article

Accurate blueberry ripeness detection is crucial for intelligent harvesting but is challenged by complex orchard environments involving small, dense fruit clusters. This study proposes BBYOLOv12, an improved YOLOv12 model, to address missed detections and ripeness misjudgments. The method integrates a lightweight RepGhost backbone for efficient multi-scale feature extraction, a modified SimAM attention mechanism to enhance feature capture in dense regions, and an improved WIoU loss function to optimize small object localization. Evaluated on a self-built dataset, BBYOLOv12 achieved a mAP@0.5 of 98.97%, mAP@0.5:0.95 of 83.55%, precision of 97.55%, and recall of 97.27%, outperforming baseline and mainstream lightweight models. The model maintains high accuracy with only 2.36 million parameters and 5.59 GFLOPs, reducing complexity relative to the baseline. A practical Graphical User Interface was also developed for real-time detection and statistical analysis. This research provides an effective technical solution for multi-scale, dense perception tasks in agricultural applications. Full article

In this work, we present a Physics-Informed Neural Network (PINN) framework for the classification of oil palm fresh fruit bunch (FFB) ripeness using RGB images. Unlike conventional Convolutional Neural Networks (CNNs) that learn solely from visual patterns, the proposed PINN integrates a physics-based index—derived from the red-to-green pixel intensity ratio—directly into the network architecture and loss function. This hybrid design embeds wavelength-dependent physical knowledge related to chlorophyll degradation during ripening, enabling the model to learn more robust and generalizable features even with limited and imbalanced training data. The PINN model achieves a peak accuracy of 0.73, outperforming the purely data-driven CNN baseline (0.68) by a margin of 5%. Overall, the PINN demonstrates superior performance in minority-class detection and maintains stable convergence under three different lighting conditions (different light spectra). These results highlight the effectiveness of integrating domain-specific physical insights into deep learning models, offering a promising pathway toward reliable, non-destructive, and automated ripeness assessment for agricultural applications. Full article

The codling moth (Cydia pomonella L.) is a major pest of pome fruits worldwide, guided by semiochemicals to locate hosts and oviposition sites. Quince (Cydonia oblonga Mill.), although less studied, is also affected by this pest. This study aimed to identify behaviorally active compounds for codling moth by characterizing the volatilome of quince cultivars. Volatile profiles were analyzed across four phenological stages (flowering, unripe, growth, and ripe fruit) using solid-phase microextraction and GC–MS. The cultivars evaluated were Champion, INTA 37, INTA 117, and INTA 147. Female oviposition behavior and neonate larval host choice were also assessed. Identified volatiles included esters, sesquiterpenes, monoterpenes, alcohols, aldehydes, and norisoprenoids. Among monoterpenes, limonene, consistently detected across all cultivars and stages, emerged as a key kairomone. Volatile composition varied across phenological stages, with the fruit growth stage exhibiting the highest diversity and abundance of compounds previously reported as behaviorally active. This pattern coincided with peak female oviposition and larval host selection. Females oviposited mainly on leaf surface, whereas during ripening, eggs were deposited on fruit lacking pubescence. Overall, INTA 147 was the most preferred cultivar. These findings highlight quince volatiles, particularly Limonene, as potential candidates for the development of semiochemical-based tools to improve codling moth management. Full article

Real-time visual inference on resource-constrained hardware remains a core challenge for edge computing and embedded artificial intelligence systems. Recent deep learning architectures, particularly Vision Transformers (ViTs) and Detection Transformers (DETRs), achieve high detection accuracy but impose substantial computational and memory demands that limit their deployment on low-power edge platforms such as NVIDIA Jetson and Raspberry Pi devices. This paper presents a systematic review of model compression and optimization strategies—specifically quantization, pruning, and knowledge distillation—applied to lightweight object detection architectures for edge deployment. Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, peer-reviewed studies were analyzed from Scopus, IEEE Xplore, and ScienceDirect to examine the evolution of efficient detectors from convolutional neural networks to transformer-based models. The synthesis highlights a growing focus on real-time transformer variants, including Real-Time DETR (RT-DETR) and low-bit quantized approaches such as Q-DETR, alongside optimized YOLO-based architectures. While quantization enables substantial theoretical acceleration (e.g., up to 16× operation reduction), aggressive low-bit precision introduces accuracy degradation, particularly in transformer attention mechanisms, highlighting a critical efficiency-accuracy tradeoff. The review further shows that Quantization-Aware Training (QAT) consistently outperforms Post-Training Quantization (PTQ) in preserving performance under low-precision constraints. Finally, this review identifies critical open research challenges, emphasizing the efficiency–accuracy tradeoff and the high computational demands imposed by Transformer architectures. Future directions are proposed, including hardware-aware optimization, robustness to imbalanced datasets, and multimodal sensing integration, to ensure reliable real-time inference in practical agricultural edge computing environments. Full article

To meet the growing demand for automated blueberry harvesting in smart agriculture, this study proposes an improved lightweight detection network, termed M-YOLOv11n, for fast and accurate blueberry maturity detection in complex natural environments. The proposed model enhances feature representation through an improved lightweight multi-scale design, enabling more effective extraction of fruit features under complex orchard conditions. In addition, attention-based feature refinement is incorporated to emphasize discriminative ripeness-related cues while suppressing background interference. These design choices improve robustness to scale variation and occlusion, addressing the limitations of conventional lightweight detectors in detecting small and partially occluded fruits. By incorporating MsBlock and the attention mechanism, M-YOLOv11n achieves improved detection accuracy without significantly increasing computational cost. Experimental results demonstrate that the proposed model attains 97.0% mAP50 on the validation set and maintains robust performance under challenging conditions such as occlusion and varying illumination, achieving 96.5% mAP50. With an inference speed of 176.6 FPS, the model satisfies both accuracy and real-time requirements for blueberry maturity detection. Compared with YOLOv11n, M-YOLOv11n increases the parameter count only marginally from 2.60 M to 2.61 M, while maintaining high inference efficiency. These results indicate that the proposed method is suitable for real-time deployment on embedded vision systems in smart agricultural harvesting robots and supports early yield estimation in complex field environments. Full article

Olive anthracnose is a major disease worldwide; although once chiefly attributed to Colletotrichum acutatum, it is now clear that the predominant pathogen varies among regions. In this study, we identified Colletotrichum scovillei for the first time as a latent pathogen in olive fruits from groves in the Peloponnese, Greece, expanding the known diversity of Colletotrichum species associated with olive anthracnose. To better understand the ecological context of this finding, we examined the role of endophytic microorganisms in olive tissues and their interactions with phytopathogens. Endophytic fungi isolated from asymptomatic ripe olive fruits and leaves were characterized for phylogeny and potential pathogenicity, while competitive interactions between Colletotrichum species and other endophytes were assessed to identify potential biological control agents. In parallel, meteorological variability among sampling sites was analyzed to explore possible links with pathogen distribution. Our results indicate that naturally occurring endophytes sharing the Colletotrichum niche can suppress the necrotrophic phase of Colletotrichum spp., supporting the potential of such endophytes as sustainable tools for disease management. We detected C. scovillei in asymptomatic olives in one sampling year and confirmed its virulence via inoculation assays. This temporally limited yet virulent occurrence, alongside the activity of resident endophytes, supports an integrated, ecology-informed approach to anthracnose management. Full article

Loquat fruit is valued for its pleasant taste and favorable ripening period. However, its delicate texture and high perishability make it highly vulnerable to damage during packaging, so the fruit is usually packed by hand. Developing a fruit-sizing machine could increase commercial market opportunities. Automated mass detection reduces manual sorting errors and labor requirements. Overall, it enhances grading accuracy, speed, and uniformity in loquat processing. It also helps distinguish between ripe, underripe, and overripe fruits through subtle mass differences. Mass modeling has proven to be an effective baseline approach for the development and optimization of grading machines, and its efficiency has been demonstrated across different fruit types. Here, we present a comparative analysis of various models for mass modeling of six international and Italian loquat varieties (“Algerie,” “Peluche,” “Golden Nugget,” “Virticchiara,” “Nespolone di Trabia,” and “Claudia”) cultivated in southern Italy. On fifty fruits per variety, singular mass and spatial diameters [longitudinal (DL), maximum transverse (DT1), and minimum transverse (DT2) were measured. Linear and non-linear regression analyses, including quadratic, polynomial, and cubic models, were applied to both the complete dataset and individual varieties. A set of predictors was used, including DL (length), DT1 (width), and DT2 (thickness), ellipsoid and oblate spheroid volume. Model performance was evaluated based on higher R² values, and lower RMSE and MBE values. The best general model was obtained using an ellipsoidal volume (R² = 0.97, RMSE = 2.76). Both linear and cubic models demonstrated high suitability across all varieties, with ellipsoidal volume emerging as the most effective predictor. Conversely, (DL) based models were the least suitable, yielding the lowest (R² = 0.41) values in “Virticchiara.” The developed general and specific-variety models and equations provide a solid foundation for establishing high-performance systems for mass and size estimation, which can be effectively integrated into a fruit sizer machine. Full article

Strawberries are important cash crops. Traditional manual picking is costly and inefficient, while automated harvesting robots are hindered by field challenges like stem-leaf occlusion, fruit overlap, and appearance/maturity variations from lighting and viewing angles. To address the need for accurate cross-maturity fruit identification and keypoint detection, this study constructed a strawberry image dataset covering multiple varieties, ripening stages, and complex ridge-cultivation field conditions: MSRBerry. Based on the YOLO11-pose framework, we proposed DHN-YOLO with three key improvements: replacing the original C2PSA with the CDC module to enhance subtle feature capture and irregular shape adaptability; substituting C3K2 with C3H to strengthen multi-scale feature extraction and robustness to lighting-induced maturity/color variations; and upgrading the neck into a New-Neck via CA and dual-path fusion to reduce feature loss and improve critical region perception. These modifications enhanced feature quality while cutting parameters and accelerating inference. Experimental results showed DHN-YOLO achieved 87.3% precision, 88% recall, and 78.6% mAP@50:95 for strawberry detection (0.9%, 1.6%, 5% higher than YOLO11-pose), and 83%, 87.5%, 83.6% for keypoint detection (1.9%, 2.1%, 4.6% improvements). It also reached 71.6 FPS with 15 ms single-image inference. The overall performance of DHN-YOLO also surpasses other mainstream models such as YOLO13, YOLO10, DETR and so on. This demonstrates DHN-YOLO meets practical needs for robust strawberry and picking point detection in complex agricultural environments. Full article

Lychee detection and maturity classification are crucial for yield estimation and harvesting. In densely packed lychee clusters with limited training samples, accurately determining ripeness is challenging. This paper proposes a new transformer model incorporating a Kolmogorov–Arnold Network (KAN), termed GhostResNet (GRN)–KAN–Transformer, for lychee detection and ripeness classification in dense on-tree fruit clusters. First, within the backbone, we introduce a stackable multi-layer GhostResNet module to reduce redundancy in feature extraction and improve efficiency. Next, during feature fusion, we add a large-scale layer to enhance sensitivity to small objects and to increase polling of the small-scale feature map during querying. We further propose a multi-layer cross-fusion attention (MCFA) module to achieve deeper hierarchical feature integration. Finally, in the decoding stage, we employ an improved KAN for the classification and localization heads to strengthen nonlinear mapping, enabling a better fitting to the complex distributions of categories and positions. Experiments on a public dataset demonstrate the effectiveness of GRN-KANformer. Compared with the baseline, GFLOPs and parameters of the model are reduced by 8.84% and 11.24%, respectively, while mean Average Precision (mAP) metrics mAP50 and mAP50–95 reach 94.7% and 58.4%, respectively. Thus, it lowers computational complexity while maintaining high accuracy. Comparative results against popular deep learning models, including YOLOv8n, YOLOv12n, CenterNet, and EfficientNet, further validate the superior performance of GRN-KANformer. Full article

Strawberry picking relies primarily on manual labor, making it the most labor-intensive stage in strawberry cultivation. Harvesting robots have become essential for strawberry production, and fruit ripeness detection models are critical for picking operations. This study collected strawberry ripeness photographs under various natural environments and enhanced feature expression through diverse image enhancement techniques. Considering practical deployment on harvesting robots, the low-parameter, high-accuracy YOLOv8s was selected as the base model. Leveraging the ease of integration of the Global Attention Mechanism (GAM) within the YOLO model, we incorporated GAM before the SPFF module to enhance the extraction capabilities of both global and local features. Experimental results demonstrate that the improved YOLOv8s achieves excellent performance, with a mAP of 91.5% for three maturity classes and a frame rate of 53 FPS. Compared with other mainstream models, the improved YOLOv8s presented in this paper demonstrates superior detection performance, achieving mAP improvements of 12.1%, 8.0%, 6.1%, 4.6%, and 3.1% over YOLOv3, YOLOv5s, YOLOv7s, YOLOv8s, and CBAM-YOLOv8s, respectively. It also exhibits robust detection capabilities under varying lighting conditions and occlusions, meeting the demands for high precision and rapid performance during harvesting operations. Full article

The accurate assessment of Chinese bayberry (Myrica rubra) maturity is critical for intelligent harvesting. This study proposes a novel cascaded framework combining instance segmentation and multi-feature regression for accurate maturity detection. First, a lightweight SOLOv2-Light network is employed to segment each fruit individually, which significantly reduces computational costs with only a marginal drop in accuracy. Then, a multi-feature extraction network is developed to fuse deep semantic, color (LAB space), and multi-scale texture features, enhanced by a channel attention mechanism for adaptive weighting. The maturity ground truth is defined using the a*/b* ratio measured by a colorimeter, which correlates strongly with anthocyanin accumulation and visual ripeness. Experimental results demonstrated that the proposed method achieves a mask mAP of 0.788 on the instance segmentation task, outperforming Mask R-CNN and YOLACT. For maturity prediction, a mean absolute error of 3.946% is attained, which is a significant improvement over the baseline. When the data are discretized into three maturity categories, the overall accuracy reaches 95.51%, surpassing YOLOX-s and Faster R-CNN by a considerable margin while reducing processing time by approximately 46%. The modular design facilitates easy adaptation to new varieties. This research provides a robust and efficient solution for in-field bayberry maturity detection, offering substantial value for the development of automated harvesting systems. Full article