Search Results (656)

Automated Road defect detection using Unmanned Aerial Vehicles (UAVs) has emerged as an efficient and safe solution for large-scale infrastructure inspection. However, object detection in aerial imagery poses unique challenges, including the prevalence of extremely small targets, complex backgrounds, and significant scale variations. Mainstream deep learning-based detection models often struggle with these issues, exhibiting limitations in detecting small cracks, high computational demands, and insufficient generalization ability for UAV perspectives. To address these challenges, this paper proposes a novel comprehensive network, RoadNet, specifically designed for high-precision road defect detection in UAV-captured imagery. RoadNet innovatively integrates Transformer modules with a convolutional neural network backbone and detection head. This design not only significantly enhances the global feature modeling capability crucial for understanding complex aerial contexts but also maintains the computational efficiency necessary for potential real-time applications. The model was trained and evaluated on a self-collected UAV road defect dataset (UAV-RDD). In comparative experiments, RoadNet achieved an outstanding mAP@0.5 score of 0.9128 while maintaining a fast-processing speed of 210.01 ms per image, outperforming other state-of-the-art models. The experimental results demonstrate that RoadNet possesses superior detection performance for road defects in complex aerial scenarios captured by drones. Full article

With the development of the semiconductor manufacturing process towards miniaturization and high integration, the detection of microscopic defects on wafer surfaces faces the challenge of balancing precision and efficiency. Therefore, this study proposes a lightweight inspection model based on the YOLOv8 framework, aiming to achieve an optimal balance between inspection accuracy, model complexity, and inference speed. First, we design a novel lightweight module called IRB-GhostConv-C2f (IGC) to replace the C2f module in the backbone, thereby significantly minimizing redundant feature computations. Second, a CNN-based cross-scale feature fusion neck network, the CCFF-ISC neck, is proposed to reduce the redundant computation of low-level features and enhance the expression of multi-scale semantic information. Meanwhile, the novel IRB-SCSA-C2f (ISC) module replaces the C2f in the neck to further improve the efficiency of feature fusion. In addition, a novel dynamic head network, DyHeadv3, is integrated into the head structure, aiming to improve the small-scale target detection performance by dynamically adjusting the feature interaction mechanism. Finally, so as to comprehensively assess the proposed algorithm’s performance, an industrial dataset of wafer defects, WSDD, is constructed, which covers “broken edges”, “scratches”, “oil pollution”, and “minor defects”. The experimental results demonstrate that the CISC-YOLO model attains an mAP50 of 93.7%, and the parameter amount is reduced to 1.92 M, outperforming other mainstream leading algorithms in the field. The proposed approach provides a high-precision and low-latency real-time defect detection solution for semiconductor industry scenarios. Full article

Typical fertilizer applicators are often restricted in performance due to non-uniformity in distribution, required labor and time intensiveness, high discharge rate, chemical input wastage, and fostering weed proliferation. To address this gap in production agriculture, an automated variable-rate fertilizer applicator was developed for the cotton crop that is based on deep learning-initiated electronic control unit (ECU). The applicator comprises (a) plant recognition unit (PRU) to capture and predict presence (or absence) of cotton plants using the YOLOv7 recognition model deployed on-board Raspberry Pi microprocessor (Wale, UK), and relay decision to a microcontroller; (b) an ECU to control stepper motor of fertilizer metering unit as per received cotton-detection signal from the PRU; and (c) fertilizer metering unit that delivers precisely metered granular fertilizer to the targeted cotton plant when corresponding stepper motor is triggered by the microcontroller. The trials were conducted in the laboratory on a custom testbed using artificial cotton plants, with the camera positioned 0.21 m ahead of the discharge tube and 16 cm above the plants. The system was evaluated at forward speeds ranging from 0.2 to 1.0 km/h under lighting levels of 3000, 5000, and 7000 lux to simulate varying illumination conditions in the field. Precision, recall, F1-score, and mAP of the plant recognition model were determined as 1.00 at 0.669 confidence, 0.97 at 0.000 confidence, 0.87 at 0.151 confidence, and 0.906 at 0.5 confidence, respectively. The mean absolute percent error (MAPE) of 6.15% and 9.1%, and mean absolute deviation (MAD) of 0.81 g/plant and 1.20 g/plant, on application of urea and Diammonium Phosphate (DAP), were observed, respectively. The statistical analysis showed no significant effect of the forward speed of the conveying system on fertilizer application rate (p > 0.05), thereby offering a uniform application throughout, independent of the forward speed. The developed fertilizer applicator enhances precision in site-specific applications, minimizes fertilizer wastage, and reduces labor requirements. Eventually, this fertilizer applicator placed the fertilizer near targeted plants as per the recommended dosage. Full article

Drone-based target detection using visible and thermal (RGB-T) images is critical in disaster rescue, intelligent transportation, and wildlife monitoring. However, persons typically occupy fewer pixels and exhibit more varied postures than vehicles or large animals, making them difficult to detect in unmanned aerial vehicle (UAV) remote sensing images with complex backgrounds. We propose a novel progressive target-aware network (PTANet) for person detection using RGB-T images. A global adaptive feature fusion module (GAFFM) is designed to fuse the texture and thermal features of persons. A progressive focusing strategy is used. Specifically, we incorporate a person segmentation auxiliary branch (PSAB) during training to enhance target discrimination, while a cross-modality background mask (CMBM) is applied in the inference phase to suppress irrelevant background regions. Extensive experiments demonstrate that the proposed PTANet achieves high accuracy and generalization performance, reaching 79.5%, 47.8%, and 97.3% mean average precision (mAP)@50 on three drone-based person detection benchmarks (VTUAV-det, RGBTDronePerson, and VTSaR), with only 4.72 M parameters. PTANet deployed on an embedded edge device with TensorRT acceleration and quantization achieves an inference speed of 11.177 ms (640 × 640 pixels), indicating its promising potential for real-time onboard person detection. The source code is publicly available on GitHub. Full article

Spinal cord injury (SCI) often results in long-term locomotor impairments, and strategies to enhance functional recovery remain limited. While epidural electrical stimulation (EES) has shown clinical promise, our understanding of the mechanisms by which it improves function remains incomplete. Here, we use genetic tools in an animal model to perform neuromodulation and treadmill rehabilitation in a manner similar to EES, but with the benefit of the genetic tools and animal model allowing for targeted manipulation, precise quantification of the cells and circuits that were manipulated, and the gathering of extensive kinematic data. We used a viral construct that selectively transduces large diameter afferent fibers (LDAFs) with a designer receptor exclusively activated by a designer drug (hM3Dq DREADD; a chemogenetic construct) to increase the excitability of large fibers specifically, in the rat contusion SCI model. As changes in locomotion with afferent stimulation can be subtle, we carried out a detailed characterization of the kinematics of locomotor recovery over time. Adult Long-Evans rats received contusion injuries and direct intraganglionic injections containing AAV2-hSyn-hM3Dq-mCherry, a viral vector that has been shown to preferentially transduce LDAFs, or a control with tracer only (AAV2-hSyn-mCherry). These neurons then had their activity increased by application of the designer drug Clozapine-N-oxide (CNO), inducing tonic excitation during treadmill training in the recovery phase. Kinematic data were collected during treadmill locomotion across a range of speeds over nine weeks post-injury. Data were analyzed using a mixed effects model chosen from amongst several models using information criteria. That model included fixed effects for treatment (DREADDs vs. control injection), time (weeks post injury), and speed, with random intercepts for rat and time point nested within rat. Significant effects of treatment and treatment interactions were found in many parameters, with a sometimes complicated dependence on speed. Generally, DREADDs activation resulted in shorter stance duration, but less reduction in swing duration with speed, yielding lower duty factors. Interestingly, our finding of shorter stance durations with DREADDs activation mimics a past study in the hemi-section injury model, but other changes, including the variability of anterior superior iliac spine (ASIS) height, showed an opposite trend. These may reflect differences in injury severity and laterality (i.e., in the hemi-section injury the contralateral limb is expected to be largely functional). Furthermore, as with that study, withdrawal of DREADDs activation in week seven did not cause significant changes in kinematics, suggesting that activation may have dwindling effects at this later stage. This study highlights the utility of high-resolution kinematics for detecting subtle changes during recovery, and will enable the refinement of neuromechanical models that predict how locomotion changes with afferent neuromodulation, injury, and recovery, suggesting new directions for treatment of SCI. Full article

Impurities in polypropylene random copolymer (PPR) raw materials can seriously affect the performance of the final product, and efficient and accurate impurity detection is crucial to ensure high production quality. In order to solve the problems of high small-target miss rates, weak anti-interference ability, and difficulty in balancing accuracy and speed in existing detection methods used in complex industrial scenarios, this paper proposes an enhanced machine vision detection algorithm based on YOLOv11. Firstly, the FasterLDConv module dynamically adjusts the position of sampling points through linear deformable convolution (LDConv), which improves the feature extraction ability of small-scale targets on complex backgrounds while maintaining lightweight features. The IR-EMA attention mechanism is a novel approach that combines an efficient reverse residual architecture with multi-scale attention. This combination enables the model to jointly capture feature channel dependencies and spatial relationships, thereby enhancing its sensitivity to weak impurity features. Again, a DC-DyHead deformable dynamic detection head is constructed, and deformable convolutions are embedded into the spatial perceptual attention of DyHead to enhance its feature modelling ability for anomalies and occluded impurities. We introduce an enhanced InnerMPDIoU loss function to optimise the bounding box regression strategy. This new method addresses issues related to traditional CIoU losses, including excessive penalties imposed on small targets and a lack of sufficient gradient guidance in situations where there is almost no overlap. The results indicate that the average precision (mAP@0.5) of the improved algorithm on the self-made PPR impurity dataset reached 88.6%, which is 2.3% higher than that of the original YOLOv11n, while precision (P) and recall (R) increased by 2.4% and 2.8%, respectively. This study provides a reliable technical solution for the quality inspection of PPR raw materials and serves as a reference for algorithm optimisation in the field of industrial small-target detection. Full article

Accurate detection and counting of wheat spikes are crucial for yield estimation and variety selection in precision agriculture. However, challenges such as complex field environments, morphological variations, and small target sizes hinder the performance of existing models in real-world applications. This study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices. The architecture integrates four key modules: (1) FEMANet, a mixed aggregation feature enhancement network with Efficient Multi-scale Attention (EMA) for improved small-target representation; (2) BiAFA-FPN, a bidirectional asymmetric feature pyramid network for efficient multi-scale feature fusion; (3) ADown, an adaptive downsampling module that preserves structural details during resolution reduction; and (4) GSCDHead, a grouped shared convolution detection head for reduced parameters and computational cost. Evaluated on a hybrid dataset combining GWHD2021 and a self-collected field dataset, FEWheat-YOLO achieved a COCO-style AP of 51.11%, AP@50 of 89.8%, and AP scores of 18.1%, 50.5%, and 61.2% for small, medium, and large targets, respectively, with an average recall (AR) of 58.1%. In wheat spike counting tasks, the model achieved an R² of 0.941, MAE of 3.46, and RMSE of 6.25, demonstrating high counting accuracy and robustness. The proposed model requires only 0.67 M parameters, 5.3 GFLOPs, and 1.6 MB of storage, while achieving an inference speed of 54 FPS. Compared to YOLOv11n, FEWheat-YOLO improved AP@50, AP_s, AP_m, AP_l, and AR by 0.53%, 0.7%, 0.7%, 0.4%, and 0.3%, respectively, while reducing parameters by 74%, computation by 15.9%, and model size by 69.2%. These results indicate that FEWheat-YOLO provides an effective balance between detection accuracy, counting performance, and model efficiency, offering strong potential for real-time agricultural applications on resource-limited platforms. Full article

The complex environment along railway lines, characterized by low imaging quality, strong background interference, and densely distributed small objects, causes existing detection models to suffer from low accuracy in practical applications. To tackle these challenges, this study aims to develop a robust and lightweight insulator detection model specifically optimized for these challenging railway scenarios. To this end, we release a dedicated comprehensive dataset named complexRailway that covers typical railway scenarios to address the limitations of existing insulator datasets, such as the lack of small-scale objects in high-interference backgrounds. On this basis, we present CutP5-LargeKernelAttention-SIoU (C5LS), an improved YOLOv8 variant with three key improvements: (1) optimized YOLOv8’s detection head by removing the P5 branch to improve feature extraction for small- and medium-sized targets while reducing computational redundancy, (2) integrating a lightweight Large Separable Kernel Attention (LSKA) module to expand the receptive field and improve contextual modeling, (3) and replacing CIoU with SIoU loss to refine localization accuracy and accelerate convergence. Experimental results demonstrate that it reaches 94.7% in mAP@0.5 and 65.5% in mAP@0.5–0.95, outperforming the baseline model by 1.9% and 3.5%, respectively. With an inference speed of 104 FPS and a model size of 13.9 MB, the model balances high precision and lightweight deployment. By providing stable and accurate insulator detection, C5LS not only offers reliable spatial positioning basis for subsequent defect identification but also builds an efficient and feasible intelligent monitoring solution for these failure-prone insulators, thereby effectively enhancing the operational safety and maintenance efficiency of the railway power system. Full article

Addressing the challenge of acquiring high-precision leader Unmanned Ground Vehicle (UGV) pose information in real time for communication-denied leader–follower formations, this study proposed Pillar-Bin, a 3D object detection algorithm based on the PointPillars framework. Pillar-Bin introduced an Interval Discretization Strategy (Bin) within the detection head, mapping critical target parameters (dimensions, center, heading angle) to predefined intervals for joint classification-residual regression optimization. This effectively suppresses environmental noise and enhances localization accuracy. Simulation results on the KITTI dataset demonstrate that the Pillar-Bin algorithm significantly outperforms PointPillars in detection accuracy. In the 3D detection mode, the mean Average Precision (mAP) increased by 2.95%, while in the bird’s eye view (BEV) detection mode, mAP was improved by 0.94%. With a processing rate of 48 frames per second (FPS), the proposed algorithm effectively enhanced detection accuracy while maintaining the high real-time performance of the baseline method. To evaluate Pillar-Bin’s real-vehicle performance, a leader UGV pose extraction scheme was designed. Real-vehicle experiments show absolute X/Y positioning errors below 5 cm and heading angle errors under 5° in Cartesian coordinates, with the pose extraction processing speed reaching 46 FPS. The proposed Pillar-Bin algorithm and its pose extraction scheme provide efficient and accurate leader pose information for formation control, demonstrating practical engineering utility. Full article

CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats)-Cas (CRISPR-associated) systems, originally identified as prokaryotic adaptive immune mechanisms, have rapidly evolved into powerful tools for molecular diagnostics. Leveraging their precise nucleic acid targeting capabilities, CRISPR diagnostics offer rapid, sensitive, and specific detection solutions for a wide array of targets. This review delves into the fundamental principles of various Cas proteins (e.g., Cas9, Cas12a, Cas13a) and their distinct mechanisms of action (cis- and trans-cleavage). It highlights the diverse applications spanning infectious disease surveillance, cancer biomarker detection, and genetic disorder screening, emphasizing key advantages such as speed, high sensitivity, specificity, portability, and cost-effectiveness, particularly for point-of-care (POC) testing in resource-limited settings. The report also addresses current challenges, including sensitivity limitations without pre-amplification, specificity issues, and complex sample preparation, while exploring promising future trajectories like the integration of artificial intelligence (AI) and the development of universal diagnostic platforms to enhance clinical translation. Full article

This article proposes an improved Visible Light Communication (VLC) solution that, besides the indoor lighting and data transfer, offers an energy-efficient alternative for modern workspaces. Unlike Light-Fidelity (LiFi), designed for high-speed data communication, VLC primarily targets applications where fast data rates are not essential. The developed prototype ensures reliable communication under variable lighting conditions, addressing low-speed requirements such as test bench monitoring, occupancy detection, remote commands, logging or access control. Although the tested data rate was limited to 100 kb/s with a Bit Error Rate (BER) below 10⁻⁷, the key innovation is the light dimming dynamic adaptation. Therefore, the system self-adjusts the LED duty cycle between 10% and 90%, based on natural or artificial ambient light, to maintain a minimum illuminance of 300 lx at the workspace level. Additionally, this work includes a scalability analysis through simulations conducted in an office scenario with up to six users. The results show that the system can adjust the lighting level and maintain the connectivity according to users’ presence, significantly reducing energy consumption without compromising visual comfort or communication performance. With this light intensity regulation algorithm, the proposed solution demonstrates real potential for implementation in smart indoor environments focused on sustainability and connectivity. Full article

Mine fire is caused by external heat source or coal seam spontaneous combustion, and there are serious hidden dangers in mining operation. The existing detection methods have high cost, limited coverage and delayed response. An edge intelligent fire detection system based on multi-source information fusion is proposed. We enhance the YOLOv5s backbone network by (1) optimized small-target detection and (2) adaptive attention mechanism to improve recognition accuracy. In order to overcome the limitation of video only, a dynamic weighting algorithm combining video and multi-sensor data is proposed, which adjusts the strategy according to the real-time fire risk index. Deploying quantitative models on edge devices can improve underground intelligence and response speed. The experimental results show that the improved YOLOv5s is 7.2% higher than the baseline, the detection accuracy of the edge system in the simulated environment is 8.28% higher, and the detection speed is 26% higher than that of cloud computing. Full article

In remote sensing imagery, objects smaller than $32\times 32$ pixels suffer from three persistent challenges that existing detectors inadequately resolve: (1) their weak signal is easily submerged in background clutter, causing high miss rates; (2) the scarcity of valid pixels yields few geometric or textural cues, hindering discriminative feature extraction; and (3) successive down-sampling irreversibly discards high-frequency details, while multi-scale pyramids still fail to compensate. To counteract these issues, we propose MS-YOLOv11, an enhanced YOLOv11 variant that integrates “frequency-domain detail preservation, lightweight receptive-field expansion, and adaptive cross-scale fusion.” Specifically, a 2D Haar wavelet first decomposes the image into multiple frequency sub-bands to explicitly isolate and retain high-frequency edges and textures while suppressing noise. Each sub-band is then processed independently by small-kernel depthwise convolutions that enlarge the receptive field without over-smoothing. Finally, the Mix Structure Block (MSB) employs the MSPLCK module to perform densely sampled multi-scale atrous convolutions for rich context of diminutive objects, followed by the EPA module that adaptively fuses and re-weights features via residual connections to suppress background interference. Extensive experiments on DOTA and DIOR demonstrate that MS-YOLOv11 surpasses the baseline in mAP@50, mAP@95, parameter efficiency, and inference speed, validating its targeted efficacy for small-object detection. Full article

This study addresses the applicability of conventional marine acoustic technologies for detecting non-metal artifacts. Based on the typical environment in Xiamen Bay, we evaluated the detection efficacy of common multibeam sonar, side-scan sonar, and sub-bottom profiling sonar through a controlled model experiment system. We employed ceramic artifact replicas (ranging in size from 10 to 70 cm) and incorporated acoustic parameter optimization to elucidate the applicability boundaries of different technologies. The results indicate that multibeam sonar can identify clustered targets larger than 0.5 m, but is limited in resolving small individual targets (less than 30 cm) due to terrain detail constraints. Side-scan sonar, under low-speed (less than 4 knots) and near-bottom operating conditions, effectively captures the high-intensity echo characteristics of ceramic targets, achieving a maximum effective detection range of more than 40 m. High-frequency sub-bottom profiler (94–110 kHz) offers resolution advantages for exposed artifacts, while low-frequency signals (5–15 kHz) provide theoretical support for detecting subsequently buried targets. Furthermore, the study quantifies the coupling effects of substrate type, target size, and surface roughness on acoustic responses. We propose a synergistic detection workflow comprising “multibeam initial screening—side-scan fine mapping—sub-bottom profiling validation,” which provides empirical support for the optimization and standardization of underwater archeological technologies in complex marine environments. Full article

Cloud detection is an indispensable step in satellite remote sensing of cloud properties and objects under the influence of cloud occlusion. Nevertheless, interfering targets such as snow and haze pollution are easily misjudged as clouds for most of the current algorithms. Hence, a robust cloud detection algorithm is urgently needed, especially for regions with high latitudes or severe air pollution. This paper demonstrated that the passive satellite detector Advanced Geosynchronous Radiation Imager (AGRI) onboard the FY-4A satellite has a great possibility to misjudge the dense aerosols in haze pollution as clouds during the daytime, and constructed an algorithm based on the spectral information of the AGRI’s 14 bands with a concise and high-speed calculation. This study adjusted the previously proposed cloud mask rectification algorithm of Moderate-Resolution Imaging Spectroradiometer (MODIS), rectified the MODIS cloud detection result, and used it as the accurate cloud mask data. The algorithm was constructed based on adjusted Fisher discrimination analysis (AFDA) and spectral spatial variability (SSV) methods over four different underlying surfaces (land, desert, snow, and water) and two seasons (summer and winter). This algorithm divides the identification into two steps to screen the confident cloud clusters and broken clouds, which are not easy to recognize, respectively. In the first step, channels with obvious differences in cloudy and cloud-free areas were selected, and AFDA was utilized to build a weighted sum formula across the normalized spectral data of the selected bands. This step transforms the traditional dynamic-threshold test on multiple bands into a simple test of the calculated summation value. In the second step, SSV was used to capture the broken clouds by calculating the standard deviation (STD) of spectra in every 3 × 3-pixel window to quantify the spectral homogeneity within a small scale. To assess the algorithm’s spatial and temporal generalizability, two evaluations were conducted: one examining four key regions and another assessing three different moments on a certain day in East China. The results showed that the algorithm has an excellent accuracy across four different underlying surfaces, insusceptible to the main interferences such as haze and snow, and shows a strong detection capability for broken clouds. This algorithm enables widespread application to different regions and times of day, with a low calculation complexity, indicating that a new method satisfying the requirements of fast and robust cloud detection can be achieved. Full article