Search Results (1,137)

Multimodal object detection leverages the complementary characteristics of visible (RGB) and infrared (IR) imagery, making it well-suited for challenging scenarios such as low illumination, occlusion, and complex backgrounds. However, most existing fusion-based methods rely on static or heuristic strategies, limiting their adaptability to dynamic environments. To address this limitation, we propose CLSANet, a cognitive learning-based self-adaptive network that enhances detection performance by dynamically selecting and integrating modality-specific features. CLSANet consists of three key modules: (1) a Dominant Modality Identification Module that selects the most informative modality based on global scene analysis; (2) a Modality Enhancement Module that disentangles and strengthens shared and modality-specific representations; and (3) a Self-Adaptive Fusion Module that adjusts fusion weights spatially according to local scene complexity. Compared to existing methods, CLSANet achieves state-of-the-art detection performance with significantly fewer parameters and lower computational cost. Ablation studies further demonstrate the individual effectiveness of each module under different environmental conditions, particularly in low-light and occluded scenes. CLSANet offers a compact, interpretable, and practical solution for multimodal object detection in resource-constrained settings. Full article

The growth and sustainability of today’s global economy heavily relies on smooth maritime operations. The increasing security concerns to marine environments pose complex security challenges, such as smuggling, illegal fishing, human trafficking, and environmental threats, for traditional surveillance methods due to their limitations. Artificial intelligence (AI), particularly deep learning, has offered strong capabilities for automating object detection, anomaly identification, and situational awareness in maritime environments. In this paper, we have reviewed the state-of-the-art deep learning models mainly proposed in recent literature (2020–2025), including convolutional neural networks, recurrent neural networks, Transformers, and multimodal fusion architectures. We have highlighted their success in processing diverse data sources such as satellite imagery, AIS, SAR, radar, and sensor inputs from UxVs. Additionally, multimodal data fusion techniques enhance robustness by integrating complementary data, yielding more detection accuracy. There still exist challenges in detecting small or occluded objects, handling cluttered scenes, and interpreting unusual vessel behaviours, especially under adverse sea conditions. Additionally, explainability and real-time deployment of AI models in operational settings are open research areas. Overall, the review of existing maritime literature suggests that deep learning is rapidly transforming maritime domain awareness and response, with significant potential to improve global maritime security and operational efficiency. We have also provided key datasets for deep learning models in the maritime security domain. Full article

Noncommunicable diseases (NCDs) like diabetes and cancer drive demand for therapeutic functional foods. This study developed freeze-dried fermented camel milk (FCM) with Ajwa date pulp (ADP), evaluating its physical and functional properties, probiotic survival, and potential benefits for diabetes and cancer. To achieve this target, six FCM formulations were prepared using ABT-5 starter culture (containing Lactobacillus acidophilus, Bifidobacterium bifidum, and Streptococcus thermophilus) with or without Lacticaseibacillus rhamnosus B-1937 and ADP (12% or 15%). The samples were freeze-dried, and their functional properties, such as water activity, dispersibility, water absorption capacity, water absorption index, water solubility index, insolubility index, and sedimentation, were assessed. Reconstitution properties such as density, flowability, air content, porosity, loose bulk density, packed bulk density, particle density, carrier index, Hausner ratio, porosity, and density were examined. In addition, color and probiotic survivability under simulated gastrointestinal conditions were analyzed. Also, antidiabetic potential was assessed via α-amylase and α-glucosidase inhibition assays, while cytotoxicity was evaluated using the MTT assay on Caco-2 cells. The results show that ADP supplementation significantly improved dispersibility (up to 72.73% in FCM15D+L). These improvements are attributed to changes in particle size distribution and increased carbohydrate and mineral content, which facilitate powder rehydration and reduce clumping. All FCM variants demonstrated low water activity (0.196–0.226), indicating good potential for shelf stability. The reconstitution properties revealed that FCM powders with ADP had higher bulk and packed densities but lower particle density and porosity than controls. Including ADP reduced interstitial air and increased occluded air within the powders, which may minimize oxidation risks and improve packaging efficiency. ADP incorporation resulted in a significant decrease in lightness (L*) and increases in redness (a*) and yellowness (b*), with greater pigment and phenolic content at higher ADP levels. These changes reflect the natural colorants and browning reactions associated with ADP, leading to a more intense and visually distinct product. Probiotic survivability was higher in ADP-fortified samples, with L. acidophilus and B. bifidum showing resilience in intestinal conditions. The FCM15D+L formulation exhibited potent antidiabetic effects, with IC₅₀ values of 111.43 μg mL⁻¹ for α-amylase and 77.21 μg mL⁻¹ for α-glucosidase activities, though lower than control FCM (8.37 and 10.74 μg mL⁻¹, respectively). Cytotoxicity against Caco-2 cells was most potent in non-ADP samples (IC₅₀: 82.22 μg mL⁻¹ for FCM), suggesting ADP and L. rhamnosus may reduce antiproliferative effects due to proteolytic activity. In conclusion, the study demonstrates that ADP-enriched FCM is a promising functional food with enhanced probiotic viability, antidiabetic potential, and desirable physical properties. This work highlights the potential of camel milk and date synergies in combating some NCDs in vitro, suggesting potential for functional food application. Full article

Unmanned aerial vehicles (UAVs) are increasingly used for road infrastructure inspection and monitoring. However, challenges such as scale variation, complex background interference, and the scarcity of annotated UAV datasets limit the performance of traditional segmentation models. To address these challenges, this study proposes UAV-YOLOv12, a multi-scale segmentation model specifically designed for UAV-based road imagery analysis. The proposed model builds on the YOLOv12 architecture by adding two key modules. It uses a Selective Kernel Network (SKNet) to adjust receptive fields dynamically and a Partial Convolution (PConv) module to improve spatial focus and robustness in occluded regions. These enhancements help the model better detect small and irregular road features in complex aerial scenes. Experimental results on a custom UAV dataset collected from national highways in Wuxi, China, show that UAV-YOLOv12 achieves F1-scores of 0.902 for highways (road-H) and 0.825 for paths (road-P), outperforming the original YOLOv12 by 5% and 3.2%, respectively. Inference speed is maintained at 11.1 ms per image, supporting near real-time performance. Moreover, comparative evaluations with U-Net show that UAV-YOLOv12 improves by 7.1% and 9.5%. The model also exhibits strong generalization ability, achieving F1-scores above 0.87 on public datasets such as VHR-10 and the Drone Vehicle dataset. These results demonstrate that the proposed UAV-YOLOv12 can achieve high accuracy and robustness in diverse road environments and object scales. Full article

This study focuses on the clastic reservoir in the first member of Yaojia Formation within Qijia-Gulong Sag, Songliao Basin. The results indicate that the reservoir in the study area develops within a shallow-water delta sedimentary system. The dominant sedimentary microfacies comprise underwater distributary channels, mouth bars, and sheet sands. Among these, the underwater distributary channel microfacies exhibits primary porosity ranging from 15.97% to 17.71%, showing the optimal reservoir quality, whereas the sheet sand microfacies has a porosity of only 7.45% to 12.08%, indicating inferior physical properties. During diagenesis, compaction notably decreases primary porosity via particle rearrangement and elastic deformation, while calcite cementation and quartz overgrowth further occlude pore throats. Although dissolution can generate secondary porosity (locally up to 40%), the precipitation of clay minerals tends to block pore throats, leading to “ineffective porosity” (permeability generally < 5 mD) and overall low-porosity and low-permeability characteristics. Carbon–oxygen isotope analysis reveals a deficiency in organic acid supply in the study area, restricting the intensity of dissolution alteration. Reservoir quality evolution is dominantly governed by the combined controls of sedimentary microfacies and diagenesis. This study emphasizes that, within shallow-water delta sedimentary settings, the material composition of sedimentary microfacies and the dynamic equilibrium of diagenetic processes jointly govern reservoir property variations. This insight provides critical theoretical support for understanding diagenetic evolution mechanisms in clastic reservoirs and enabling precise prediction of high-quality reservoir distribution. Full article

Occlusion remains a major challenge in person re-identification, as it often leads to incomplete or misleading visual cues. To address this issue, we propose a dual-branch occlusion-aware network (DOAN), which explicitly and implicitly enhances the model’s capability to perceive and handle occlusions. The proposed DOAN framework comprises two synergistic branches. In the first branch, we introduce an Occlusion-Aware Semantic Attention (OASA) module to extract semantic part features, incorporating a parallel channel and spatial attention (PCSA) block to precisely distinguish between pedestrian body regions and occlusion noise. We also generate occlusion-aware parsing labels by combining external human parsing annotations with occluder masks, providing structural supervision to guide the model in focusing on visible regions. In the second branch, we develop an occlusion-aware recovery (OAR) module that reconstructs occluded pedestrians to their original, unoccluded form, enabling the model to recover missing semantic information and enhance occlusion robustness. Extensive experiments on occluded, partial, and holistic benchmark datasets demonstrate that DOAN consistently outperforms existing state-of-the-art methods. Full article

During the automated picking of table grapes, the automatic recognition and segmentation of grape pedicels, along with the positioning of picking points, are vital components for all the following operations of the harvesting robot. In the actual scene of a grape plantation, however, it is extremely difficult to accurately and efficiently identify and segment grape pedicels and then reliably locate the picking points. This is attributable to the low distinguishability between grape pedicels and the surrounding environment such as branches, as well as the impacts of other conditions like weather, lighting, and occlusion, which are coupled with the requirements for model deployment on edge devices with limited computing resources. To address these issues, this study proposes a novel picking point localization method for table grapes based on an instance segmentation network called Progressive Global-Local Structure-Sensitive Segmentation (PGSS-YOLOv11s) and a simple combination strategy of morphological operators. More specifically, the network PGSS-YOLOv11s is composed of an original backbone of the YOLOv11s-seg, a spatial feature aggregation module (SFAM), an adaptive feature fusion module (AFFM), and a detail-enhanced convolutional shared detection head (DE-SCSH). And the PGSS-YOLOv11s have been trained with a new grape segmentation dataset called Grape-⊥, which includes 4455 grape pixel-level instances with the annotation of ⊥-shaped regions. After the PGSS-YOLOv11s segments the ⊥-shaped regions of grapes, some morphological operations such as erosion, dilation, and skeletonization are combined to effectively extract grape pedicels and locate picking points. Finally, several experiments have been conducted to confirm the validity, effectiveness, and superiority of the proposed method. Compared with the other state-of-the-art models, the main metrics $F1$ score and mask mAP@0.5 of the PGSS-YOLOv11s reached 94.6% and 95.2% on the Grape-⊥ dataset, as well as 85.4% and 90.0% on the Winegrape dataset. Multi-scenario tests indicated that the success rate of positioning the picking points reached up to 89.44%. In orchards, real-time tests on the edge device demonstrated the practical performance of our method. Nevertheless, for grapes with short pedicels or occluded pedicels, the designed morphological algorithm exhibited the loss of picking point calculations. In future work, we will enrich the grape dataset by collecting images under different lighting conditions, from various shooting angles, and including more grape varieties to improve the method’s generalization performance. Full article

With the advancement of computer vision and image processing technologies, scene recognition has gradually become a research hotspot. However, in practical applications, it is necessary to detect the categories and locations of objects in images while recognizing scenes. To address these issues, this paper proposes an indoor object detection and scene recognition algorithm based on the Apriori algorithm and the Mobile-EFSSD model, which can simultaneously obtain object category and location information while recognizing scenes. The specific research contents are as follows: (1) To address complex indoor scenes and occlusion, this paper proposes an improved Mobile-EFSSD object detection algorithm. An optimized MobileNetV3 with ECA attention is used as the backbone. Multi-scale feature maps are fused via FPN. The localization loss includes a hyperparameter, and focal loss replaces confidence loss. Experiments show that the method achieves stable performance, effectively detects occluded objects, and accurately extracts category and location information. (2) To improve classification stability in indoor scene recognition, this paper proposes a naive Bayes-based method. Object detection results are converted into text features, and the Apriori algorithm extracts object associations. Prior probabilities are calculated and fed into a naive Bayes classifier for scene recognition. Evaluated using the ADE20K dataset, the method outperforms existing approaches by achieving a better accuracy–speed trade-off and enhanced classification stability. The proposed algorithm is applied to indoor scene images, enabling the simultaneous acquisition of object categories and location information while recognizing scenes. Moreover, the algorithm has a simple structure, with an object detection average precision of 82.7% and a scene recognition average accuracy of 95.23%, making it suitable for practical detection requirements. Full article

This study addresses the challenges of manual measurement bias and low robustness in detecting small, occluded targets in complex marine environments during real-time onboard sorting of Portunus trituberculatus. We propose YOLO-DFAM, an enhanced YOLOv11n-based model that replaces the global average pooling in the Focal Modulation module with a spatial–channel dual-attention mechanism and incorporates the ASF-YOLO cross-scale fusion strategy to improve feature representation across varying target sizes. These enhancements significantly boost detection, achieving an mAP@50 of 98.0% and precision of 94.6%, outperforming RetinaNet-CSL and Rotated Faster R-CNN by up to 6.3% while maintaining real-time inference at 180.3 FPS with only 7.2 GFLOPs. Unlike prior static-scene approaches, our unified framework integrates attention-guided detection, scale-adaptive tracking, and lightweight weight estimation for dynamic marine conditions. A ByteTrack-based tracking module with dynamic scale calibration, EMA filtering, and optical flow compensation ensures stable multi-frame tracking. Additionally, a region-specific allometric weight estimation model (R² = 0.9856) reduces dimensional errors by 85.7% and maintains prediction errors below 4.7% using only 12 spline-interpolated calibration sets. YOLO-DFAM provides an accurate, efficient solution for intelligent onboard fishery monitoring. Full article

Strawberry planting requires different amounts of soil water-holding capacity and fertilizer at different growth stages. Determining the stages of strawberry growth has important guiding significance for irrigation, fertilization, and picking. Quick and accurate identification of strawberry plants at different stages can provide important information for automated strawberry planting management. We propose an improved multistage identification model for strawberry based on the YOLOv9 algorithm—the ASHM-YOLOv9 model. The original YOLOv9 showed limitations in detecting strawberries at different growth stages, particularly lower precision in identifying occluded fruits and immature stages. We enhanced the YOLOv9 model by introducing the Alterable Kernel Convolution (AKConv) to improve the recognition efficiency while ensuring precision. The squeeze-and-excitation (SE) network was added to increase the network’s capacity for characteristic derivation and its ability to fuse features. Haar wavelet downsampling (HWD) was applied to optimize the Adaptive Downsampling module (Adown) of the initial model, thereby increasing the precision of object detection. Finally, the CIoU function was replaced by the Minimum Point Distance based IoU (MPDIoU) loss function to effectively solve the problem of low precision in identifying bounding boxes. The experimental results demonstrate that, under identical conditions, the improved model achieves a precision of 97.7%, a recall of 97.2%, mAP50 of 99.1%, and mAP50-95 of 90.7%, which are 0.6%, 3.0%, 0.7%, and 7.4% greater than those of the original model, respectively. The parameters, model size, and floating-point calculations were reduced by 3.7%, 5.6% and 3.8%, respectively, which significantly boosted the performance of the original model and outperformed that of the other models. Experiments revealed that the model could provide technical support for the multistage identification of strawberry planting. Full article

Background: A critical review of the literature demonstrates that masticatory apparatus with an artificial oral environment is of interest in the fields including (i) dental science; (ii) food science; (iii) the pharmaceutical industries for drug release. However, apparatus that closely mimics human chewing and oral conditions has yet to be realised. This study investigates the vital role of dental morphology and form–function connections using two-bite test parameters for effective drug release from medicated chewing gum (MCG) and compares them to human chewing efficiency with the aid of a humanoid chewing robot and a bionics product lifecycle management (PLM) framework with built-in reverse biomimetics—both developed by the first author. Methods: A novel, bio-engineered two-bite testbed is created for two testing machines with compression and torsion capabilities to conduct two-bite tests for evaluating the mechanical properties of MCGs. Results: Experimental studies are conducted to investigate the relationship between biting force and crushing/shearing and understand chewing efficiency and effective mastication. This is with respect to mechanochemistry and power stroke for disrupting mechanical bonds releasing the active pharmaceutical ingredients (APIs) of MCGs. The manuscript discusses the effect and the critical role that jaw physiology, dental morphology, the Bennett angle of mandible (BA) and the Frankfort-mandibular plane angle (FMA) on two-bite test parameters when FMA = 0, 25 or 29.1 and BA = 0 or 8. Conclusions: The impact on other scientific fields is also explored. Full article

Chronic thromboembolic pulmonary hypertension (CTEPH) is a rare, progressive form of pre-capillary pulmonary hypertension characterized by persistent, organized thromboemboli in the pulmonary vasculature, leading to vascular remodeling, elevated pulmonary artery pressures, right heart failure, and significant morbidity and mortality if untreated. Despite advances, CTEPH remains underdiagnosed due to nonspecific symptoms and overlapping features with other forms of pulmonary hypertension. Basic Methodology: This review synthesizes data from large international registries, epidemiologic studies, translational research, and multicenter clinical trials. Key methodologies include analysis of registry data to assess incidence and risk factors, histopathological examination of lung specimens, and molecular studies investigating endothelial dysfunction and inflammatory pathways. Diagnostic modalities and treatment outcomes are evaluated through observational studies and randomized controlled trials. Recent Advances and Affected Population: Research has elucidated that CTEPH arises from incomplete resolution of pulmonary emboli, with subsequent fibrotic transformation mediated by dysregulated TGF-β/TGFBI signaling, endothelial dysfunction, and chronic inflammation. Affected populations are typically older adults, often with prior venous thromboembolism, splenectomy, or prothrombotic conditions, though up to 25% have no history of acute PE. The disease burden is substantial, with delayed diagnosis contributing to worse outcomes and higher societal costs. Microvascular arteriopathy and PAH-like lesions in non-occluded vessels further complicate the clinical picture. Conclusions: CTEPH is now recognized as a treatable disease, with multimodal therapies—surgical endarterectomy, balloon pulmonary angioplasty, and targeted pharmacotherapy—significantly improving survival and quality of life. Ongoing research into molecular mechanisms and biomarker-driven diagnostics promises earlier identification and more personalized management. Multidisciplinary care and continued translational investigation are essential to further reduce mortality and optimize outcomes for this complex patient population. Full article

Background: Pancreatic Ductal Adenocarcinoma (PDAC) is one of the most common malignancies associated with thrombotic events. While there is research present on various techniques of portal vein reconstruction, there is limited published data on the techniques and/or considerations of reconstruction in the setting of complete portal vein occlusion. We therefore sought to analyze and present our experience of this clinical scenario. Methods: This was a retrospective analysis of a prospectively collected database. All patients who underwent portal vein resection and/or reconstruction during a pancreatic resection were included. Post-operatively, all patients underwent a contrast-enhanced CT scan on post-operative day 1 to assess for any portal vein thrombus. Results: Pancreatic resection with portal vein reconstruction was performed in 183 patients. Complete PV occlusion was seen in 12 patients at the time of surgery. In those patients with an occluded PV, reconstruction options included primary repair with end-end anastomosis (n = 2) or use of an interposition graft (n = 9). Interposition graft conduits included the left renal vein (n = 6), tubularized bovine pericardium (n = 3), and femoral vein (n = 1). Post-operative portal vein thrombus was seen in 4/12 patients. The majority of patients (n = 7) were discharged on therapeutic anticoagulation, 4 were discharged on an antiplatelet, and 1 patient received neither. Conclusions: Based on our series, we would recommend attempting PV reconstruction in these patients with an interposition graft (with autologous left renal vein or bovine pericardium). We believe that with this technique, the post-operative thrombosis risk is similar to PV reconstructions in non-occluded patients. Full article

Recent advancements in polymer science have catalyzed a transformative shift in biomedical engineering, particularly through the development of biodegradable and smart polymers. This review explores the evolution, functionality, and application of these materials in areas such as tissue scaffolding, cardiovascular occluders, and controlled drug delivery systems. Emphasis is placed on shape-memory polymers (SMPs), conductive polymers, and polymer-based composites that combine tunable degradation, mechanical strength, and bioactivity. The synergy between natural and synthetic polymers—augmented by nanotechnology and additive manufacturing—enables the creation of intelligent scaffolds and implantable devices tailored for specific clinical needs. Key fabrication methods, including electrospinning, freeze-drying, and emulsion-based techniques, are discussed in relation to pore structure and functionalization strategies. Finally, the review highlights emerging trends, including ionic doping, 3D printing, and multifunctional nanocarriers, outlining their roles in the future of regenerative medicine and personalized therapeutics. Full article

The United States leads in corn production and consumption in the world with an estimated USD 50 billion per year. There is a pressing need for the development of novel and efficient techniques aimed at enhancing the identification and eradication of weeds in a manner that is both environmentally sustainable and economically advantageous. Weed classification for autonomous agricultural robots is a challenging task for a single-camera-based system due to noise, vibration, and occlusion. To address this issue, we present a multi-camera-based system with decision-level sensor fusion to improve the limitations of a single-camera-based system in this paper. This study involves the utilization of a convolutional neural network (CNN) that was pre-trained on the ImageNet dataset. The CNN subsequently underwent re-training using a limited weed dataset to facilitate the classification of three distinct weed species: Xanthium strumarium (Common Cocklebur), Amaranthus retroflexus (Redroot Pigweed), and Ambrosia trifida (Giant Ragweed). These weed species are frequently encountered within corn fields. The test results showed that the re-trained VGG16 with a transfer-learning-based classifier exhibited acceptable accuracy (99% training, 97% validation, 94% testing accuracy) and inference time for weed classification from the video feed was suitable for real-time implementation. But the accuracy of CNN-based classification from video feed from a single camera was found to deteriorate due to noise, vibration, and partial occlusion of weeds. Test results from a single-camera video feed show that weed classification accuracy is not always accurate for the spray system of an agricultural robot (AgBot). To improve the accuracy of the weed classification system and to overcome the shortcomings of single-sensor-based classification from CNN, an improved Dempster–Shafer (DS)-based decision-level multi-sensor fusion algorithm was developed and implemented. The proposed algorithm offers improvement on the CNN-based weed classification when the weed is partially occluded. This algorithm can also detect if a sensor is faulty within an array of sensors and improves the overall classification accuracy by penalizing the evidence from a faulty sensor. Overall, the proposed fusion algorithm showed robust results in challenging scenarios, overcoming the limitations of a single-sensor-based system. Full article