Search Results (633)

Cotton represents one of the world’s most significant agricultural commodities. However, severe weed proliferation in cotton fields seriously hampers the development of the cotton industry, making precise weed control essential for ensuring healthy cotton growth. Traditional object detection methods often suffer from computational complexity, rendering them difficult to deploy on resource-constrained edge devices. To address this challenge, this paper proposes AVGS-YOLO, a lightweight and enhanced model employing a Quadruple Synergistic Lightweight Perception Mechanism (QSLPM) for precise weed detection in complex cotton field environments. The QSLPM emphasizes synergistic interactions between modules. It integrates lightweight neck architecture (Slimneck) to optimize feature extraction pathways for cotton weeds; the ADown module (Adaptive Downsampling) replaces Conv modules to address model parameter redundancy; the small object attention modulation module (SEAM) enhances the recognition of small-scale cotton weed features; and angle-sensitive geometric regression (SIoU) improves bounding box localization accuracy. Experimental results demonstrate that the AVGS-YOLO model achieves 95.9% precision, 94.2% recall, 98.2% mAP50, and 93.3% mAP50-95. While maintaining high detection accuracy, the model achieves a lightweight design with reductions of 17.4% in parameters, 27% in GFLOPs, and 14.5% in model size. Demonstrating strong performance in identifying cotton weeds within complex cotton field environments, this model provides technical support for deployment on resource-constrained edge devices, thereby advancing intelligent agricultural development and safeguarding the healthy growth of cotton crops. Full article

Weed control in rice remains a critical challenge in direct-seeded rice cultivation. This study combined field and laboratory experiments to compare the efficacy of nine herbicide combinations against weeds in dryland rice fields and to evaluate their impact on rice economic traits. A model was constructed using principal component analysis for comprehensive evaluation, aiming to identify optimal herbicide combinations for direct-seeded rice under shallow drip irrigation in Hinggan League. The results indicate that pendimethalin provides better pre-emergence control compared to oxadiargyl and pretilachlor. The combination of florpyrauxifen-benzyl + benzobicyclon provided optimal weed control efficacy and rice economic performance when applied as a foliar treatment. Forty-five days after application, weed control efficacy against Echinochloa crus-galli (L.) P. Beauv. and Amaranthus retroflexus L. was 72% and 85%, respectively, with fresh weight reduction of 63%. Theoretical yield reached 4285.48 kg·ha⁻¹. At rice harvest, no herbicide residues were detected in rice straw or grains across all treatments, confirming the safety of the applied treatment for rice. Principal component analysis (PCA) was used to evaluate the comprehensive scores of each treatment, with pendimethalin + florpyrauxifen-benzyl + benzobicyclon achieving the highest score of 0.65. The study indicates that the combination of pendimethalin as a pre-emergence and florpyrauxifen-benzyl + benzobicyclon offers significant advantages in weed control efficacy and rice growth, achieving the highest comprehensive evaluation score. This combination holds important application value for weed control and grain yield assurance in direct-seeded rice fields. Full article

Precision agriculture is a key technology for addressing challenges such as increasing food demand, labour shortages, and the environmental impact of intensive agrochemical use. In this context, selective weed management remains a critical issue due to its direct effect on crop productivity and sustainability. This article presents a simulation-based framework for the design and evaluation of an agricultural robotic module for the detection, classification, and selective intervention of weeds. The proposed system integrates convolutional neural networks and the kinematic model of a 2DOF robot manipulator with 5 links for weed classification and treatment. The system is evaluated in a virtual environment, where camera calibration, perception accuracy, and the performance of the kinematic model are analysed. Quantitative results include detection accuracy, localization error, and intervention success rate under simulated field conditions. The results demonstrate selective weed management and the feasibility of simulation for developing weed control systems, while also identifying the main challenges for real-world deployment. Full article

Under maize–soybean rotation systems, weeds and crops at the seedling stage in dryland fields exhibit high similarity in morphological structure, scale distribution, and spatial arrangement. In addition, complex illumination conditions, occlusion, and background interference further complicate accurate weed discrimination. To address these challenges, this study proposes an improved YOLOv11n-based weed detection method for seedling-stage crops under dryland rotation conditions, aiming to enhance detection accuracy and robustness in UAV-acquired field images. Three key improvements were introduced to enhance model performance: (1) the incorporation of Dynamic Convolution (DynamicConv) to adaptively strengthen feature representation for weeds with varying morphologies and scales in low-altitude remote sensing imagery; (2) the design of a SlimNeck lightweight feature fusion architecture to improve multi-scale feature propagation efficiency while reducing computational cost; (3) the cascaded group attention mechanism (CGA) is integrated into the C2PSA module, thereby improving discrimination capability under complex background conditions. These results represent consistent improvements over baseline models, including YOLOv5, YOLOv6, YOLOv8, YOLOv11, and YOLOv12. Specifically, detection performance for broadleaf weeds and Poaceae weeds reached mAP@0.5 values of 87.2% and 73.9%, respectively. Overall, the proposed method demonstrates superior detection accuracy and stability for seedling-stage weed identification under rotation conditions, providing reliable technical support for variable-rate herbicide application and precision field management. Full article

Weed management, particularly in organic farming, poses a significant challenge due to high manual labor costs and the crop’s low competitive ability. Precision laser technology offers a promising non-chemical alternative. This study evaluates the field performance of a novel robotic system based on a Thulium fiber laser. The validation was conducted on commercial fields of the Westhof Bio GmbH in Friedrichsgabekoog, Germany. The Weeding Success rate of the laser weeding robot was 95% and the Detection Rate 85% for carrots for one weeding cycle. For beetroot, these values are 98% and 88%, respectively, after two weeding cycles. The field trials validate the Thulium fiber laser system as an agronomically effective and economically viable alternative for sustainable weed management. The technology demonstrates the potential to significantly reduce manual labor and reliance on herbicides in challenging crops. Full article

The expansion of organic farming in Europe increases the co-occurrence of medicinal and aromatic plant crops and pyrrolizidine alkaloid (PA)-producing weeds, raising serious contamination concerns. This study evaluated the risk of PA contamination in organically grown chamomile (Matricaria recutita L.) under field conditions in the North Vidzeme region of Latvia, with particular emphasis on vertical PA distribution in dominant weeds and on whether PA occurrence could be detected in chamomile plants growing adjacent to PA-producing weeds under field conditions. Three commercial fields were surveyed using systematic quadrat sampling to quantify weed density, biomass, and height. PA-producing weeds were segmented into 5 cm fractions, and pyrrolizidine alkaloids were quantified by LC-HRMS. Myosotis arvensis was the dominant species (up to 48,000 plants ha⁻¹), contributing the highest field-level PA load (up to 669.3 mg ha⁻¹), whereas Anchusa arvensis occurred at lower densities (≤2400 plants ha⁻¹) with a total PA load of 104.8 mg ha⁻¹. In both species, PA concentrations increased toward upper plant segments, while contamination hazard at harvest was determined by the amount of PA-bearing biomass in the harvest-relevant zone. No PAs were detected in chamomile samples collected within 10 cm of PA-producing weeds (<LOQ). Under the investigated conditions, contamination hazard was primarily associated with mechanical admixture during harvest rather than soil-mediated transfer. Full article

Traditional mechanized chestnut harvesting is too costly for small producers, non-selective, and prone to damaging nuts. Accurate, reliable detection of chestnuts on the orchard floor is crucial for developing low-cost, vision-guided automated harvesting technology. However, developing a reliable chestnut detection system faces challenges in complex environments with shading, varying natural light conditions, and interference from weeds, fallen leaves, stones, and other foreign on-ground objects, which have remained unaddressed. This study collected 319 images of chestnuts on the orchard floor, containing 6524 annotated chestnuts. A comprehensive set of 29 state-of-the-art real-time object detectors, including 14 in the YOLO (v11–v13) and 15 in the RT-DETR (v1–v4) families at various model scales, was systematically evaluated through replicated modeling experiments for chestnut detection. Experimental results show that the YOLOv12m model achieved the best mAP@0.5 of 95.1% among all the evaluated models, while RT-DETRv2-R101 was the most accurate variant among the RT-DETR models, with mAP@0.5 of 91.1%. In terms of mAP@[0.5:0.95], the YOLOv11x model achieved the best accuracy of 80.1%. All models demonstrated significant potential for real-time chestnut detection, and YOLO models outperformed RT-DETR models in terms of both detection accuracy and inference, making them better suited for on-board deployment. This work lays a foundation for developing AI-based, vision-guided intelligent chestnut harvest systems. Full article

The invasive weed Malachra capitata is unsuitable for human or animal consumption but has recently attracted attention for potential alternative uses. In this study, the allelopathic potential of M. capitata for weed control was investigated, as were its allelopathic effects on selected crops. The influence of plant developmental stage on its phytotoxic activity was also assessed. In addition, the physiological effects of the extract on seed germination were investigated. Aqueous leaf extracts were obtained across a range of growth stages and evaluated using seed germination and seedling growth bioassays, followed by bioassay-guided fractionation and GC-MS analysis. Leaves extracts collected at 35 days after planting exhibited the strongest inhibitory activity. Dicot plant species (Phaseolus lathyroides, Cucumis sativus, Brassica oleracea, and B. chinensis) were more susceptible to M. capitata extracts than grassy species (Echinochloa crus-galli, Zea mays, and Oryza sativa), indicating selective phytotoxicity. In pot experiments, application of leaf residues as surface mulch at rates of 100, 200, and 400 g/m² significantly reduced P. lathyroides emergence by 11.25%, 35.00%, and 71.25%, respectively. Bioassay-guided fractionation indicated the ethyl acetate-soluble acidic fraction to contain the active allelochemicals. This inhibition was associated with reduced water uptake and suppression of α-amylase activity during seed germination. The most abundant GC-MS detectable components of the acidic fraction were octadecane (12.45%), eicosane (9.74%), and hexadecane (9.60%). Overall, these findings highlight the allelopathic potential of M. capitata, providing a foundation for further applied research and supporting its valorization for sustainable weed management. Full article

Accurate assessment of cotton emergence rates is essential for precision agriculture management, and unmanned aerial vehicle (UAV) imagery provides a scalable means for field-level monitoring. However, cotton seedling detection from UAV images faces persistent challenges: individual seedlings appear as small targets with diverse morphologies across varying flight altitudes; strong plastic film reflections, weeds, and soil cracks introduce substantial background interference; and “missing seedling” targets, which manifest as negative space features, exhibit high similarity to background noise. Existing CNN–Transformer hybrid detection architectures are limited by fixed convolutional receptive fields that cannot adapt to multi-scale target variations, attention mechanisms that lack explicit directional geometric modeling, and interpolation-based upsampling that attenuates high-frequency edge details of small targets. To address these issues, this paper proposes DDF-DETR (Dynamic-Direction-Frequency Detection Transformer), a multi-scale spatial context detection method based on RT-DETR. The method incorporates three components: a Dynamic Gated Mixer Block (DGMB) for adaptive multi-scale feature extraction with background noise suppression, a Direction-Aware Adaptive Transformer Encoder (DAATE) for directional geometric feature modeling at linear computational complexity, and a Frequency-Aware Sub-pixel Upsampling Network (FASN) for high-frequency detail recovery in the feature pyramid. On the self-constructed Xinjiang cotton field dataset, DDF-DETR achieves 83.72% mAP@0.5 and 63.46% mAP@0.5:0.95, representing improvements of 2.38% and 5.28% over the baseline RT-DETR-R18, while reducing the parameter count by 30.6% and computational cost to 42.8 GFLOPs. Generalization experiments on the VisDrone2019 and TinyPerson datasets further validate the robustness of the proposed method for small target detection across different scenarios. Full article

Weed control is crucial for safeguarding the yield and quality of fresh maize. To achieve comprehensive, low-damage removal of weeds in fresh maize fields, an intelligent mechanical weeding system was developed. Based on the spatial distribution of maize seedling roots and agronomic requirements, a three-dimensional protection zone was established and a dedicated intra-row weeding knife was designed. An EDEM–RecurDyn co-simulation was then performed; single-factor and orthogonal experiments were used to evaluate the effects of operating speed, hydraulic cylinder extension–retraction speed, and knife bending angle on the coverage rate and intrusion rate, and to determine the optimal parameter combination. Seedling detection and field weeding trials were subsequently conducted. The detection accuracies under good and low illumination were 95.82% and 93.32%, respectively. Under the optimal settings (operating speed 1.5 km/h, hydraulic cylinder extension–retraction speed 0.22 m/s, and knife bending angle 20°), the system achieved a mean weeding rate of 90.79% and a mean seedling damage rate of 2.27%. The results demonstrate stable performance and confirm that the proposed system meets the requirements for comprehensive, low-damage weeding in fresh maize fields, providing a reference for the design of intelligent mechanical weeding equipment. Full article

The automated management of invasive weeds is critical for sustainable agriculture, yet the performance of deep learning models in real-world fields is often compromised by two factors: challenging environmental conditions and the high cost of data annotation. This study tackles both issues through a diagnostic-driven, semi-supervised framework. Using a unique dataset of approximately 975 labelled and 10,000 unlabelled images of Guinea Grass in sugarcane, we first establish strong supervised baselines for classification (ResNet) and detection (YOLO, RF-DETR), achieving F1 scores up to 0.90 and mAP50 scores exceeding 0.82. Crucially, this foundational analysis, aided by interpretability tools, uncovered a pervasive “shadow bias,” where models learned to misidentify shadows as vegetation. This diagnostic insight motivated our primary contribution: a semi-supervised pipeline that leverages unlabelled data to enhance model robustness. By training models on a more diverse set of visual information through pseudo-labelling, this framework not only helps mitigate the shadow bias but also provides a tangible boost in recall, a critical metric for minimising weed escapes in automated spraying systems. To validate our methodology, we demonstrate its effectiveness in a low-data regime on a public crop–weed benchmark. Our work provides a clear and field-tested framework for developing, diagnosing, and improving robust computer vision systems for the complex realities of precision agriculture. Full article

Greek oregano (Origanum vulgare ssp. hirtum) is an important aromatic and medicinal crop grown in Greece, often on marginal lands. Effective weed management is essential for sustainable production, but the use of herbicides raises concerns about potential pesticide residues. Therefore, this study was conducted to evaluate the residue levels of metribuzin + pendimethalin applied and incorporated pre-planting, as well metribuzin + cycloxydim and glyphosate applied post-emergence in oregano crop grown over a three-year period in the Agrinio location in Greece. Herbicide residue analysis in the edible part of the oregano plants was performed using two validated protocols, i.e., QuEChERS and QuPPe coupled with LC-MS/MS. The analytical methods demonstrated high sensitivity, with limits of quantification (LOQ) at 0.01 mg/kg and recovery rates ranging from 71% to 102%. These results indicated that the application of the above herbicides in oregano crop grown under Greek field conditions resulted in no detectable residues above the established LOQs, strongly supporting the potential safe use of these herbicides in oregano crop and their possible use for regulatory assessments and consumer safety assurance. Full article

Precision weeding is crucial for maximizing crop yields and minimizing herbicide use. However, deploying standard deep learning models in agriculture faces challenges due to the high morphological diversity of weeds and the computational constraints of edge devices. Hence, this study proposes MCS-YOLO, a lightweight detection model based on the YOLOv8 architecture. First, a channel-level Mamba module is integrated into the backbone to model long-range feature dependencies and enhance global texture representation. The LMAB module employs parallel depthwise separable convolutions with varying receptive fields and coordinate attention to improve multi-scale weed discrimination. To mitigate feature blurring and misalignment during upsampling, the LCAU module adopts dynamic offset sampling beyond fixed interpolation methods. Finally, the SCS-Head integrates dual-branch depthwise separable convolution with channel shuffling to reduce parameter redundancy while preserving efficient feature expression. Experimental results on the Weed-Crop dataset demonstrate that MCS-YOLO achieves 76.4% mAP@50 and 38.3% mAP@50–95, outperforming YOLOv8s by 3.1% and 1.5%, respectively. Furthermore, the parameter count is reduced by 20.7%, from 11.13 M to 8.83 M, and GFLOPs are reduced by 39.6%, from 28.5 to 17.2. These results confirm that MCS-YOLO effectively balances a lightweight design with high detection accuracy, offering a viable solution for real-time weed detection and automated weeding on embedded agricultural platforms. Full article

White lupin (Lupinus albus L.) is increasingly promoted as a sustainable protein crop; however, the consistency of agronomic input responses under rainfed continental conditions remains insufficiently documented. This study evaluated the interannual consistency of a foliar amino acid-based biostimulant (Aminotop N) and herbicide-based weed control on morphological traits, grain yield, seed physical quality (thousand-seed weight and hectoliter mass), and seed nitrogen and crude protein concentration of white lupin (cv. Măriuca). A 2 × 2 factorial field experiment arranged in a randomized complete block design was conducted across two consecutive growing seasons (2024–2025). Two-way ANOVA revealed significant effects of year and significant year × treatment interactions for grain yield and seed physical traits (p ≤ 0.05), indicating season-dependent treatment responses. Statistically significant treatment differences were detected in 2024, whereas no differences were observed among treatments in 2025. Seed total nitrogen concentration and crude protein content remained statistically stable across treatments and years. Principal component analysis explained 98.2% of total variance, with the first component primarily separating years rather than treatments. These results demonstrate that treatment effects were not consistently expressed across seasons and highlight the necessity of multi-year validation when assessing agronomic input effectiveness in white lupin under rainfed conditions. Full article

In recent years, agriculture has begun to transform thanks to the arrival of robots and autonomous vehicles capable of performing complex operations such as weeding and spraying in an intelligent and targeted manner. In fact, new-generation agricultural robots use artificial intelligence (AI), cameras, and sensors to recognise weeds, analyse crop conditions, and apply plant protection products only where necessary, thus reducing waste and environmental impact. Some systems combine drones and ground vehicles to achieve even more accurate results. This systematic review synthesises recent advances in agricultural robotics for weed and pest management through a PRISMA-based approach. Literature was collected from major scientific databases (Scopus, Web of Science, IEEE Xplore, Google Scholar) and complementary sources, leading to the inclusion of 83 eligible studies. The selected evidence was structured into four application domains: (i) weed detection and mapping, (ii) robotic and non-chemical weed control (mechanical and laser-based approaches), (iii) selective/variable-rate spraying for pest and disease management, and (iv) integrated weeding–spraying solutions, including cooperative Unmanned Aerial Vehicle–Unmanned Ground Vehicle (UAV–UGV) systems. Overall, the reviewed studies confirm rapid progress in real-time perception (deep learning-based detection), navigation/localization (e.g., GNSS/RTK, LiDAR, sensor fusion) and targeted actuation (spot spraying and precision interventions), while also revealing persistent limitations: heterogeneous evaluation protocols, limited system-level comparisons in terms of work rate, scalability, costs and robustness under variable field conditions, and an often unclear distinction between prototype platforms and solutions close to commercialization. However, the large-scale spread of these technologies is still hampered by high costs, technical complexity, and cultural resistance. The review highlights how the integration of automation, sustainability, and accessibility is key to the agriculture of the future. Full article