Search Results (43)

Detecting citrus Huanglongbing (HLB) in orchard environments is particularly challenging due to multi-scale targets and occlusions due to clustering, which manifest as complex and variable backgrounds, targets ranging from distant single leaves to nearby full canopies, and frequent instances where symptomatic leaves are hidden behind others, all significantly hindering accurate detection. To overcome these challenges, this study introduces a novel citrus object detection model, Multi-Scale Huanglongbing DETR (MSHLB-DETR), developed on the basis of an improved Real-Time DEtection TRansformer (RT-DETR). The model significantly enhances detection accuracy and efficiency for HLB under complex orchard conditions. To address the issue of small target feature loss in leaf detection, a new efficient transformer module called Smart Disease Recognition for Citrus Huanglongbing with Multi-scale (SDRM) is introduced. SDRM includes a space-to-depth (SPD) module and inverted residual mobile block (IRMB), which facilitate deep interaction between local and global features and significantly improve the computational efficiency of the transformer. Additionally, the transformer encoder incorporates a Context-Guided Block (CGBlock) for contextual feature learning. To evaluate the proposed model under complex background conditions, a dataset of 4367 images was collected from diverse orchard scenes, preprocessed, and divided into training, validation, and testing subsets. The experimental results demonstrate that the proposed MSHLB-DETR achieved the best detection performance on the test set, with an ${\mathrm{mAP}}_{50}$ of 96.0%, surpassing other state-of-the-art models of similar scale. Compared to the original RT-DETR, the proposed model increased ${\mathrm{mAP}}_{50}$ by 15.8%, reduced Params by 7.5%, and decreased GFLOPs by 5.2%. This study reveals the critical importance of developing efficient multi-scale detection techniques for the accurate identification of citrus Huanglongbing in complex real-time monitoring scenarios. The proposed algorithm is expected to provide valuable references and new insights for the precise and timely detection of citrus Huanglongbing. Full article

Harvesting winter jujubes is a key step in production, yet traditional manual approaches are labor-intensive and inefficient. To overcome these challenges, we propose SCC-YOLO, a lightweight method for winter jujube detection, 3D localization, and cross-platform deployment, aiming to support intelligent harvesting. In this study, RGB-D cameras were integrated with an improved YOLOv11 network optimized by ShuffleNetV2, CBAM, and a redesigned C2f_WTConv module, which enables joint spatial–frequency feature modeling and enhances small-object detection in complex orchard conditions. The model was trained on a diversified dataset with extensive augmentation to ensure robustness. In addition, the original localization loss was replaced with DIoU to improve bounding box regression accuracy. A robotic harvesting system was developed, and an Eye-to-Hand calibration-based 3D localization pipeline was implemented to map fruit coordinates to the robot workspace for accurate picking. To validate engineering applicability, the SCC-YOLO model was deployed on both desktop (PyTorch and ONNX Runtime) and mobile (NCNN with Vulkan+FP16) platforms, and FPS, latency, and stability were comparatively analyzed. Experimental results showed that SCC-YOLO improved mAP by 5.6% over YOLOv11, significantly enhanced detection precision and robustness, and achieved real-time performance on mobile devices while maintaining peak throughput on high-performance desktops. Field and laboratory tests confirmed the system’s effectiveness for detection, localization, and harvesting efficiency, demonstrating its adaptability to diverse deployment environments and its potential for broader agricultural applications. Full article

‘Pera’ sweet orange is a key variety for the Brazilian citrus industry, but orchards rely on a limited number of clonal selections, which restricts adaptability and productivity across diverse environments. This study assessed the agronomic performance of 13 ‘Pera’ selections grafted on Rangpur lime, cultivated under rainfed conditions in subtropical Brazil. From 2002 to 2010, trees were assessed for vegetative growth, cumulative yield, alternate bearing, and fruit quality. Market-specific performance indices were calculated to determine suitability for fresh fruit or juice processing. Substantial genotypic variation was observed across traits, particularly during early orchard stage. Selections such as ‘Morretes’, ‘Seleção 11’, ‘Seleção 27’, ‘Seleção 37’, and ‘IPR 153’ demonstrated high cumulative yield, stable productivity, and favorable canopy traits, supporting their use in both conventional and high-density systems. ‘IPR 153’ combined compact growth with high yield efficiency and excellent fruit quality, while ‘Morretes’ had the highest juice content and broad market adaptability. In contrast, ‘IPR 159’ showed low vigor and yield under rainfed conditions. The results emphasize the value of regionally targeted clonal selection to improve orchard performance and market alignment. The identification of dual-purpose genotypes offers a pathway to diversify citrus production and improve profitability under subtropical growing conditions. Full article

This study aims to develop a multi-dimensional framework to systematically identify optimal adjustment zones for converting orchard land into cultivated land, thereby providing a reference for spatial optimization of cultivated land within the context of integrating diverse land occupation activities into the requisition–compensation balance system. The research incorporates land quality evaluation, land-use conversion cost assessment, ecological loss analysis, and scenario-based simulations. The study demonstrates that (1) compared to the common practice of directly converting orchard land to cultivated land by only considering the slope, our multi-scenario optimization model for cultivated land reduces both economic and ecological losses. (2) For cities prioritizing ecological or economic development, selecting strategies under corresponding priority scenarios can maximize the protection of local ecological environments or maintain economic levels, thereby providing reserve resources for cultivated land optimization and adjustment. (3) Under the MMEG (EG: Ecological priority scenario) and MMEM (EM: Economic priority scenario) scenarios (MM: conversion of medium-low-grade orchard land to medium-high-grade cultivated land), the area of cultivated land optimal adjustment zones is the largest. The method of comprehensively identifying cultivated land optimal adjustment zones through multi-dimensional scenario settings is more comprehensive than the conventional approach that only considers slope. This method enhances cultivated land quality more effectively and protects both the ecosystem and the economy. Full article

Crop fidelity is a desirable trait for managed pollinators and is influenced by factors like competing forage sources and colony knowledge of the surrounding environment. In European honey bees (Apis mellifera L.), colonies deployed when the crop is flowering display the highest fidelity. We tested for a similar outcome using a stingless bee species that is being increasingly used as a managed pollinator in Australian macadamia orchards. We observed Tetragonula carbonaria (Smith) colonies deployed in macadamia orchards at three time points: (1) before crop flowering (“permanent”), (2) early flowering (“early”), and (3) later in the flowering period (“later”). We captured returning pollen foragers weekly and estimated crop fidelity from the proportion of macadamia pollen they collected, using light microscopy. Pollen foraging activity was also assessed via weekly hive entrance filming. The early and later introduced colonies initially exhibited high fidelity, collecting more macadamia pollen than the permanent colonies. In most cases, the permanent colonies were already collecting diverse pollen species from the local environment and took longer to shift over to macadamia. Pollen diversity increased over time in all colonies, which was associated with an increase in the proportion of pollen foragers. Our results indicate that stingless bees can initially prioritize a mass-flowering crop, even when flowering levels are low, but that they subsequently reduce fidelity over time. Our findings will inform pollinator management strategies to help growers maximize returns from pollinator-dependent crops like macadamia. Full article

Target detection is the key technology of the apple-picking robot. To overcome the limitations of existing apple target detection methods, including low recognition accuracy of multi-species apples in complex orchard environments and a complex network architecture that occupies large memory, a lightweight apple recognition model based on the improved YOLO11 model was proposed, named YOLO-WAS model. The model aims to achieve efficient and accurate automatic multi-species apple identification while reducing computational resource consumption and facilitating real-time applications on low-power devices. First, the study constructed a high-quality multi-species apple dataset and improved the complexity and diversity of the dataset through various data enhancement techniques. The YOLO-WAS model replaced the ordinary convolution module of YOLO11 with the Adown module proposed in YOLOv9, the backbone C3K2 module combined with Wavelet Transform Convolution (WTConv), and the spatial and channel synergistic attention module Self-Calibrated Spatial Attention (SCSA) combined with the C2PSA attention mechanism to form the C2PSA_SCSA module was also introduced. Through these improvements, the model not only ensured lightweight but also significantly improved performance. Experimental results show that the proposed YOLO-WAS model achieves a precision (P) of 0.958, a recall (R) of 0.921, and mean average precision at IoU threshold of 0.5 (mAP@50) of 0.970 and mean average precision from IoU threshold of 0.5 to 0.95 with step 0.05 (mAP@50:95) of 0.835. Compared to the baseline model, the YOLO-WAS exhibits reduced computational complexity, with the number of parameters and floating-point operations decreased by 22.8% and 20.6%, respectively. These results demonstrate that the model performs competitively in apple detection tasks and holds potential to meet real-time detection requirements in resource-constrained environments, thereby contributing to the advancement of automated orchard management. Full article

This study investigates the operational performance of fruit-picking robots under varying terrain slopes and soil moisture conditions, with a focus on comparing wheeled and tracked locomotion systems. A modular robot platform was designed and tested in both controlled environments and actual mountainous orchards in Shandong, China. The experiments assessed key performance metrics—average speed, slip rate, and path deviation—under combinations of four slope levels (0°, 8°, 18°, 28°) and three soil moisture levels (dry 10%, moderate 20%, wet 35%). Results reveal that wheeled robots perform optimally on dry and flat terrain but experience significant slippage and path deviation under steep and wet conditions. In contrast, tracked robots maintain better stability and terrain adaptability, demonstrating lower slip rates and more consistent trajectories across a wide range of conditions. A synergistic deterioration effect was observed when high slope and high soil moisture co-occur, significantly degrading the performance of wheeled systems, while tracked systems mitigated these effects. Complementary semi-structured interviews with 20 orchard stakeholders—including farmers, growers, and hired pickers—highlighted key user expectations: robust traction, terrain adaptability, reduced physical labor, and operational safety. The findings suggest that future agricultural robots should adopt adaptive hybrid mobility systems and integrate environmental perception capabilities to enhance performance in complex agricultural scenarios. These insights contribute practical and theoretical guidance for the design and deployment of intelligent fruit-picking robots in diverse field environments. Full article

Sugar apple (Annona squamosa) is prized for its excellent taste, rich nutrition, and diverse uses, making it valuable for both fresh consumption and medicinal purposes. Predominantly found in tropical regions of the Americas and Asia, its harvesting remains labor-intensive in orchard settings, resulting in low efficiency and high costs. This study investigates the use of computer vision for sugar apple instance segmentation and introduces an improved deep learning model, GCE-YOLOv9-seg, specifically designed for orchard conditions. The model incorporates Gamma Correction (GC) to enhance image brightness and contrast, improving target region identification and feature extraction in orchard settings. An Efficient Multiscale Attention (EMA) mechanism was added to strengthen feature representation across scales, addressing sugar apple variability and maturity differences. Additionally, a Convolutional Block Attention Module (CBAM) refined the focus on key regions and deep semantic features. The model’s performance was evaluated on a self-constructed dataset of sugar apple instance segmentation images captured under natural orchard conditions. The experimental results demonstrate that the proposed GCE-YOLOv9-seg model achieved an F1 score (F1) of 90.0%, a precision (P) of 89.6%, a recall (R) level of 93.4%, a mAP@0.5 of 73.2%, and a mAP@[0.5:0.95] of 73.2%. Compared to the original YOLOv9-seg model, the proposed GCE-YOLOv9-seg showed improvements of 1.5% in the F1 score and 3.0% in recall for object detection, while the segmentation task exhibited increases of 0.3% in mAP@0.5 and 1.0% in mAP@[0.5:0.95]. Furthermore, when compared to the latest model YOLOv12-seg, the proposed GCE-YOLOv9-seg still outperformed with an F1 score increase of 2.8%, a precision (P) improvement of 0.4%, and a substantial recall (R) boost of 5.0%. In the segmentation task, mAP@0.5 rose by 3.8%, while mAP@[0.5:0.95] demonstrated a significant enhancement of 7.9%. This method may be directly applied to sugar apple instance segmentation, providing a promising solution for automated sugar apple detection in natural orchard environments. Full article

Accurate object detection is a fundamental component of autonomous apple-picking systems. In response to the insufficient recognition performance and poor generalization capacity of existing detection algorithms under unstructured orchard scenarios, we constructed a customized apple image dataset captured under varying illumination conditions and introduced an improved detection architecture, YOLO11-ARAF, derived from YOLO11. First, to enhance the model’s ability to capture apple-specific features, we replaced the original C3k2 module with the CARConv convolutional layer. Second, to reinforce feature learning in visually challenging orchard environments, the enhanced attention module AFGCAM was embedded into the model architecture. Third, we applied knowledge distillation to transfer the enhanced model to a compact YOLO11n framework, maintaining high detection efficiency while reducing computational cost, and optimizing it for deployment on devices with limited computational resources. To assess our method’s performance, we conducted comparative experiments on the constructed apple image dataset. The improved YOLO11-ARAF model attained 89.4% accuracy, 86% recall, 92.3% mAP@50, and 64.4% mAP@50:95 in our experiments, which are 0.3%, 1.1%, 0.72%, and 2% higher than YOLO11, respectively. Furthermore, the distilled model significantly reduces parameters and doubles the inference speed (FPS), enabling rapid and precise apple detection in challenging orchard settings with limited computational resources. Full article

Agricultural robots can mitigate labor shortages and advance precision farming. However, the dense vegetation canopies and uneven terrain in orchard environments reduce the reliability of traditional GPS-based localization, thereby reducing navigation accuracy and making autonomous navigation challenging. Moreover, inefficient path planning and an increased risk of collisions affect the robot’s ability to perform tasks such as fruit harvesting, spraying, and monitoring. To address these limitations, this study integrated stereo visual odometry with real-time appearance-based mapping (RTAB-Map)-based simultaneous localization and mapping (SLAM) to improve mapping and localization in both indoor and outdoor orchard settings. The proposed system leverages stereo image pairs for precise depth estimation while utilizing RTAB-Map’s graph-based SLAM framework with loop-closure detection to ensure global map consistency. In addition, an incorporated inertial measurement unit (IMU) enhances pose estimation, thereby improving localization accuracy. Substantial improvements in both mapping and localization performance over the traditional approach were demonstrated, with an average error of 0.018 m against the ground truth for outdoor mapping and a consistent average error of 0.03 m for indoor trails with a 20.7% reduction in visual odometry trajectory deviation compared to traditional methods. Localization performance remained robust across diverse conditions, with a low RMSE of 0.207 m. Our approach provides critical insights into developing more reliable autonomous navigation systems for agricultural robots. Full article

Interactions between honeybees and the environment are often difficult to achieve, particularly when the purpose is to optimize beekeeping production. The present study proposed to monitor the space-time variations of melliferous resources potentially exploited by colonies within a foraging area in Bosnia & Herzegovina, characterized by contrasting landscapes. The combination of methods involving Geographical Information Systems, floristic monitoring, and modelling enabled honey production potential to be calculated for the entire foraging area. In particular, the location of taxa, their abundance, diversity, and phenology enabled us to determine the spatial distribution and temporal variation of production potential. Robinia pseudoacacia and Rubus sp. made a major contribution. This potential was highly contrasted, with distant areas from the apiary more attractive than closer ones, depending on the moment. Specific periods, such as June were particularly conducive to establishing a high potential. Forest and grassland played a major role in the temporal succession, mainly because of the area covered, but moments with lower potential were supported by specific land uses (orchards). Land uses with a small surface area, such as orchards, wasteland, and riparian zones had a high potential per unit area, and improving the production potential within a foraging area could involve increasing these specific surfaces. Full article

The accurate and rapid detection of apple leaf diseases is a critical component of precision management in apple orchards. The existing deep-learning-based detection algorithms for apple leaf diseases typically demand high computational resources, which limits their practical applicability in orchard environments. Furthermore, the detection of apple leaf diseases in natural settings faces significant challenges due to the diversity of disease types, the varied morphology of affected areas, and the influence of factors such as lighting variations, leaf occlusions, and differences in disease severity. To address the above challenges, we constructed an apple leaf disease detection (ALD) dataset, which was collected from real-world scenarios, and we applied data augmentation techniques, resulting in a total of 9808 images. Based on the ALD dataset, we proposed a lightweight YOLO11n-based detection network, named CEFW-YOLO, designed to tackle the current issues in apple leaf disease identification. First, we designed a novel channel-wise squeeze convolution (CWSConv), which employs channel compression and standard convolution to reduce computational resource consumption, enhance the detection of small objects, and improve the model’s adaptability to the morphological diversity of apple leaf diseases and complex backgrounds. Second, we developed an enhanced cross-channel attention (ECCAttention) module and integrated it into the C2PSA_ECCAttention module. By extracting global information, combining horizontal and vertical convolutions, and strengthening cross-channel interactions, this module enables the model to more accurately capture disease features on apple leaves, thereby enhancing detection accuracy and robustness. Additionally, we introduced a new fine-grained multi-level linear attention (FMLAttention) module, which utilizes multi-level asymmetric convolutions and linear attention mechanisms to improve the model’s ability to capture fine-grained features and local details critical for disease detection. Finally, we incorporated the Wise-IoU (WIoU) loss function, which enhances the model’s ability to differentiate overlapping targets across multiple scales. A comprehensive evaluation of CEFW-YOLO was conducted, comparing its performance against state-of-the-art (SOTA) models. CEFW-YOLO achieved a 20.6% reduction in computational complexity. Compared to the original YOLO11n, it improved detection precision by 3.7%, with the mAP@0.5 and mAP@0.5:0.95 increasing by 7.6% and 5.2%, respectively. Notably, CEFW-YOLO outperformed advanced SOTA algorithms in apple leaf disease detection, underscoring its practical application potential in real-world orchard scenarios. Full article

Autonomous navigation in agricultural environments requires precise obstacle classification to ensure collision-free movement. This study proposes a convolutional neural network (CNN)-based model designed to enhance obstacle classification for agricultural robots, particularly in orchards. Building upon a previously developed YOLOv8n-based real-time detection system, the model incorporates Ghost Modules and Squeeze-and-Excitation (SE) blocks to enhance feature extraction while maintaining computational efficiency. Obstacles are categorized as “Real”—those that physically impact navigation, such as tree trunks and persons—and “Fake”—those that do not, such as tall weeds and tree branches—allowing for precise navigation decisions. The model was trained on separate orchard and campus datasets and fine-tuned using Hyperband optimization and evaluated on an external test set to assess generalization to unseen obstacles. The model’s robustness was tested under varied lighting conditions, including low-light scenarios, to ensure real-world applicability. Computational efficiency was analyzed based on inference speed, memory consumption, and hardware requirements. Comparative analysis against state-of-the-art classification models (VGG16, ResNet50, MobileNetV3, DenseNet121, EfficientNetB0, and InceptionV3) confirmed the proposed model’s superior precision (p), recall (r), and F1-score, particularly in complex orchard scenarios. The model maintained strong generalization across diverse environmental conditions, including varying illumination and previously unseen obstacles. Furthermore, computational analysis revealed that the orchard-combined model achieved the highest inference speed at 2.31 FPS while maintaining a strong balance between accuracy and efficiency. When deployed in real-time, the model achieved 95.0% classification accuracy in orchards and 92.0% in campus environments. The real-time system demonstrated a false positive rate of 8.0% in the campus environment and 2.0% in the orchard, with a consistent false negative rate of 8.0% across both environments. These results validate the model’s effectiveness for real-time obstacle differentiation in agricultural settings. Its strong generalization, robustness to unseen obstacles, and computational efficiency make it well-suited for deployment in precision agriculture. Future work will focus on enhancing inference speed, improving performance under occlusion, and expanding dataset diversity to further strengthen real-world applicability. Full article

Microplastic (MP) pollution has raised global concerns, and biodegradable plastics have been recommended to replace conventional ones. The “plastisphere” has been considered a hotspot for the interactions among organisms and environments, but the differences in the properties of soil microbial communities in the plastisphere of conventional and biodegradable MPs remain unclear. This in situ experiment was conducted to compare the diversity and structure of the bacterial community in the plastisphere of conventional MPs (polyethylene [PE]) and biodegradable MPs (polylactic acid [PLA]) in vegetable fields, orchards, paddy fields, and woodlands. It was discovered that the bacterial α-diversity within the plastisphere was significantly lower than that in the soil across all land use. Significant differences between plastic types were only found in the vegetable field. Regarding the community composition, the relative abundances of Actinobacteriota (43.2%) and Proteobacteria (70.9%) in the plastisphere were found to exceed those in the soil, while the relative abundances of Acidobacteriota (45.5%) and Chloroflexi (27.8%) in the soil were significantly higher. The complexity of the microbial network within the plastisphere was lower than that of the soil. Compared with the soil, the proportion of dispersal limitation in the PLA plastisphere significantly decreased, with the greatest reduction observed in the vegetable field treatment, where it dropped from 57.72% to 3.81%. These findings indicate that different land use types have a greater impact on bacterial community diversity and structure than plastics themselves, and that biodegradable MPs may pose a greater challenge to the ecological function and health of soil ecosystems than conventional MPs. Full article

The application of citrus-picking robotic hands in orchard environments is constrained by the diversity in fruit size and shape, as well as the need to control fruit damage during harvesting. To address this issue, this study proposes a passively compliant citrus-picking robotic hand and experimentally evaluates its performance. The robotic hand employs a spring-assisted grasping mechanism, optimizing the gripping force range and adjusting spring parameters to achieve passive, compliant encapsulation of citrus fruits of varying sizes while preventing damage. Furthermore, to accommodate citrus fruits with varying ellipticity, the robotic hand incorporates a floating linkage mechanism, enabling each finger to move independently under the control of a single stepper motor, thereby enhancing adaptability to morphological variations. Experimental results indicate that the robotic hand can reliably grasp citrus fruits of various sizes and ellipticities, and complete the harvesting process by rotating four times without applying tensile force, with a damage rate of only 2.6%. The proposed passively compliant robotic hand features a simple structure and strong adaptability, offering a reference for enhancing the applicability of citrus-picking robots in complex orchard environments. Future research will focus on further optimizing the robotic hand’s structure, improving harvesting efficiency, and exploring its adaptability in various operational environments. Full article