UAV Target Detection Method Based on PCCS-YOLOv8

This study empirically evaluated the effects of unmanned aerial vehicles (UAVs) applications and acceptable cost on intention to use UAVs in maritime shipping contexts. Factor analysis was employed to identify key UAVs applications (i.e. pollution forensics, supervision and service, search and rescue, humanitarian and emergency delivery, and safety and security), acceptable UAV cost, and intention to use UAVs. Survey data were collected from 201 respondents working for a maritime port corporation, shipping company, agency, and stevedoring company, and then hierarchical regression analysis was conducted to test research hypotheses and examine the effects of UAVs applications and acceptable cost dimensions on intention to use UAVs. The results suggested that the pollution forensics, supervision and service, search and rescue, humanitarian and emergency delivery, and safety and security dimensions positively affected intention to use UAVs. The study findings also revealed negative associations among seniority, turnover, and intention to use UAVs. Theoretical contributions and managerial implications are proposed to assist maritime port bureaus, corporations, and operating practice design in remaining competitive and efficient.

Weeds are one of the primary factors that reduce crop productivity by competing for nutrients and water, causing the plant to lose weight and resulting in reduced grain yield. Traditional agricultural practices often rely on uniform herbicide application, which can contaminate soil and raise costs. On agricultural land, selective weed treatment are an efficient and cost-effective way to control weeds that require a deep learning-based crop and weed segmentation system. Many existing crop and weed segmentation research works focus on achieving precise crop and weed segmentation results, rather than building lightweight models to deploy on edge devices. To attain this, we develop an effective and efficient convolutional neural network, namely the Concatenated Attention U-Net with Convolutional Block Attention Module (CAUC). By integrating Linear Concatenated Blocks (LCB), Attention Gate (AG) connections, and Convolutional Block Attention Module (CBAM), the proposed model efficiently utilizes feature maps among its architectural components to achieve superior performance. Depth-wise convolution layers and 1 × 1 convolution layers in LCBs reduce computational complexity. To enable the proposed model to identify the weed portions in multiple crop fields, we integrated three datasets in this research work, namely the Crop/Weed Field Image Dataset (CWFID), Sugar Beet, and Sunflower datasets. Experimental results on carrot, sugar beet, and sunflower crop datasets demonstrate high Accuracy (99.09%), MIoU (81.02%), and F1-score (99.06%), with a modest model size (5.6 MB) and computational parameters (0.377 million). We developed a lightweight computer vision application (13.7 MB) to demonstrate the model’s efficacy on low-computational devices.

Acquiring the growth information of tobacco plants quickly and accurately is an important prerequisite for their daily management. In view of the problem that the convolutional neural network is easily affected by background information, this study introduces the Convolutional Block Attention Module into the U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2-</sup> Net. This method is mainly composed of an encoder and a decoder. Before the feature map is decoded, it will go through the Convolutional Block Attention Module to filter more important features and inhibit the invalid features. In the decoder, in order to fuse the features of objects in different scales, the feature maps in the decoder are up-sampled and then concatenated. This information aggregation solves the problem of difficult object detection at different scales to some extent. The results of this method are compared with four current mainstream deep learning models(U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Net, DeeplabV3+, PSP-Net, U-Net). The result shows: 1) The U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Net network based on the Convolutional Block Attention Module has the highest extraction accuracy for the UAV visible light remote senseing of tobacco(accuracy was 98.53%, recall was 96.00%,F1-Score was 96.38%, kappa coefficient was 0.95, IOU was 93.02%); 2)In the extraction of the three test areas, the extraction value of this method is highly consistent with the label area value(the area ratios of a total of 13 plants in the three regions were kept between 90% and 100%),the effect is much higher than that of DeeplabV3+ and PSP-Net, and slightly higher than the extraction effect of U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Net and U-Net. 3)In the segmentation of three typical canopy closure regions of A, B, and C, most of the accuracy factors in different regions can reach 94% and above. It can be seen that the method in this study has certain advantages in feature extraction and has certain value in practical application.

&lt;p&gt;In this paper, the performance of a 5-level cascaded H-bridge inverter in unmanned aerial vehicle (UAV) applications is analized to identify, at the converter design stage, the better device choice depending on different UAV operation scenarios. Considering that regardless of the specific application there are some typical operations, such as take-off, climb, land, cruise, and potential recurring climbs and descents, the results can support the choice by considering the typical working conditions of the specific application where the UAV would be used. The results have been obtained by simulating the H-bridge inverter considering the circuit models of insulated-gate bipolar transistors (IGBTs), GaN high-electron-mobility transistors (HEMTs), and Si and SiC metal-oxide-semiconductor field-effect transistors (MOSFETs) provided by manufacturers. The study has highlighted that the choice of the device depends on the UAV usage, switching frequency, and load conditions. More specifically, considering the typical devices and systems costs in the case of a selective harmonic elimination procedure operating at the fundamental switching frequency, the Si devices should be used. Moreover, the preference for using IGBTs or Si MOSFETs depends on the typical working conditions of the UAV application. In the case of phase-shift carrier modulation technique, at 4 kHz the MOSFET is the best device and the choice between Si and SiC devices depends on the UAV application's main operation scenarios. At 20 kHz the SiC MOSFET is the best device, while at higher frequencies the GaN HEMT cost should be faced to take advantage of its best performance.&lt;/p&gt;

As part of our recent research to assess the potential of low-cost navigation sensors for Unmanned Aerial Vehicle (UAV) applications, we investigated the potential of carrier-phase Global Navigation Satellite System (GNSS) for attitude determination and control of small size UAVs. Recursive optimal estimation algorithms were developed for combining multiple attitude measurements obtained from different observation points (i.e., antenna locations), and their efficiencies were tested in various dynamic conditions. The proposed algorithms converged rapidly and produced the required output even during high dynamics manoeuvres. Results of theoretical performance analysis and simulation activities are presented in this paper, with emphasis on the advantages of the GNSS interferometric approach in UAV applications (i.e., low cost, high data-rate, low volume/weight, low signal processing requirements, etc.). The simulation activities focussed on the AEROSONDE UAV platform and considered the possible augmentation provided by interferometric GNSS techniques to a low-cost and low-weight/volume integrated navigation system (presented in the first part of this series) which employed a Vision-Based Navigation (VBN) system, a Micro- Electro-Mechanical Sensor (MEMS) based Inertial Measurement Unit (IMU) and code-range GNSS (i.e., GPS and GALILEO) for position and velocity computations. The integrated VBN-IMU-GNSS (VIG) system was augmented using the inteferometric GNSS Attitude Determination (GAD)sensor data and a comparison of the performance achieved with the VIG and VIG/GAD integrated Navigation and Guidance Systems (NGS) is presented in this paper. Finally, the data provided by these NGS are used to optimise the design of a hybrid controller employing Fuzzy Logic and Proportional-Integral-Derivative (PID) techniques for the AEROSONDE UAV.

The inspection of power transmission towers, crucial for grid maintenance, has seen advances through unmanned aerial vehicles (UAVs) and neural networks. However, complex backgrounds, inaccurate semantic segmentation, and challenges in tilt calculation limit their practical use. This study introduces a non-contact tilt detection and quantification method based on an improved U-Net architecture. The model integrates Squeeze-Excitation (SE) and Convolutional Block Attention Module (CBAM) to enhance channel and spatial feature representation, addressing issues such as blurred edges and structural loss. Using the segmented binary mask, contour points are extracted, and Principal Component Analysis (PCA) determines the tower’s main orientation to compute its tilt relative to the vertical axis. Experimental results show that the proposed U-Net+SENet outperforms the baseline, increasing mean intersection over union (mIoU) and Dice coefficients by 1.08% and 4.57%, respectively. In complex cross-arm scenarios, exceeding those of both the baseline and CBAM-enhanced models. This approach improves segmentation accuracy and enables precise axis extraction and tilt estimation. Visualisation confirms the model’s superior detail extraction, verifying its effectiveness and reliability.

Unmanned Aerial Vehicles (UAVs) integrated with lightweight visual cameras hold significant promise in renewable energy asset inspection and monitoring. This study presents an AI-assisted soiling detection methodology for inspecting solar photovoltaic (PV) panels, using UAV-captured RGB images. The proposed scheme introduces an autonomous end-to-end soiling detection model for common types of soiling in solar panel installations, including bird droppings and dust. Detecting soiling, particularly bird droppings, is critical due to their pronounced negative impact on power generation, primarily through hotspot formation and their resistance to natural cleaning processes such as rain. A dataset containing aerial RGB images of PV panels with dust and bird droppings is collected as a prerequisite. This study addresses the unique challenges posed by the small size and indistinct features of bird droppings in aerial imagery in contrast to relatively large-sized dust regions. To overcome these challenges, we developed a custom model, named SDS-YOLO (Soiling Detection System YOLO), which features a Convolutional Block Attention Module (CBAM) and two dedicated detection heads optimized for dust and bird droppings. The SDS-YOLO model significantly improves detection accuracy for bird droppings while maintaining robust performance for the dust class, compared with YOLOv5, YOLOv8, and YOLOv11. With the integration of CBAM, we achieved a substantial 40.2% increase in mean Average Precision (mAP50) and a 26.6% improvement in F1 score for bird droppings. Dust detection metrics also benefited from this attention-based refinement. These results underscore the CBAM's role in improving feature extraction and reducing false positives, particularly for challenging soiling types. Additionally, the SDS-YOLO parameter count is reduced by 24%, thus enhancing its suitability for edge computing applications.

Small target detection in Unmanned Aerial Vehicle (UAV) applications is often plagued by inherent challenges such as small object sizes, sparse information, and complex background interference. Traditional detection algorithms and existing YOLO series models suffer from limitations in detection accuracy and fine-grained detail preservation. To address this, this paper proposes YOLO-DSNet, a small target detection network based on YOLOv13n. First, we introduce the dual-stream attention module (DSAM), which enhances discriminative features by leveraging bidirectional context modeling. Second, we design the Multi-scale Attention C2f (MSA-C2f) module—an adaptive architecture that optimizes feature extraction via multi-scale enhancement, effectively preserving and integrating small target information. Finally, through dataset augmentation, we significantly improve the model’s detection performance. The proposed YOLO-DSNet achieves a mAP@0.5 improvement from 30.8% to 40.1% on the VisDrone2019 dataset with only 0.8 million additional parameters, yielding a 30% accuracy gain while increasing computational overhead by merely 11.6 Gigaflops (GFLOPs). Experiments demonstrate YOLO-DSNet’s effectiveness in small target detection tasks such as UAV aerial photography and remote sensing imagery, successfully balancing accuracy and efficiency with high practical value.

With the continuous development of deep learning technologies, fault prediction techniques based on various neural networks have been evolving. The deep learning modules based on U-Net residual networks have shown significant advantages in both learning efficiency and effectiveness. In this paper, we propose a deep learning model that integrates a 3D U-Net residual architecture, Convolutional Block Attention Module (CBAM), and Multi-scale Enhanced Global Attention (MEGA) module for automatic seismic fault detection and segmentation. This model can effectively handle complex 3D seismic data, fully exploiting both spatial and channel information, significantly improving the prediction accuracy for small faults, while only slightly increasing the computational cost.Firstly, the model uses the 3D U-Net as the backbone framework, where the residual blocks (BasicRes) extract features through multiple convolution layers. The CBAM module is incorporated to apply attention weighting, enhancing the model's ability to focus on critical information. The CBAM module combines channel attention and spatial attention, effectively adjusting the importance of feature maps from different dimensions, enabling the model to identify potential fault features in complex seismic data.Secondly, the MEGA module is introduced into the model, which further improves the model's feature representation ability by fusing multi-scale features and applying a global attention mechanism. By weighting global information, the MEGA module helps the model better capture key seismic fault features during feature fusion. This design allows the model to focus not only on local details but also to fully utilize the global contextual information in 3D data, thereby enhancing the accuracy of fault detection.After validation, the model achieved promising results in seismic fault detection tasks, automatically identifying and segmenting fault structures in seismic data. The accuracy was improved from 80% with the original 3D U-Net residual network to 85%-87%. This provides strong support for applications such as seismic exploration and subsurface imaging.Keywords: Seismic Fault Detection, 3D U-Net, Convolutional Block Attention Module (CBAM), Multi-scale Enhanced Global Attention (MEGA), Deep Learning

Flowering is a crucial developing stage for rapeseed (Brassica napus L.) plants. Flowers develop on the main and branch inflorescences of rapeseed plants and then grow into siliques. The seed yield of rapeseed heavily depends on the total flower numbers per area throughout the whole flowering period. The number of rapeseed inflorescences can reflect the richness of rapeseed flowers and provide useful information for yield prediction. To count rapeseed inflorescences automatically, we transferred the counting problem to a detection task. Then, we developed a low-cost approach for counting rapeseed inflorescences using YOLOv5 with the Convolutional Block Attention Module (CBAM) based on unmanned aerial vehicle (UAV) Red-Green-Blue (RGB) imagery. Moreover, we constructed a Rapeseed Inflorescence Benchmark (RIB) to verify the effectiveness of our model. The RIB dataset captured by DJI Phantom 4 Pro V2.0, including 165 plot images and 60,000 manual labels, is to be released. Experimental results showed that indicators R2 for counting and the mean Average Precision (mAP) for location were over 0.96 and 92%, respectively. Compared with Faster R-CNN, YOLOv4, CenterNet, and TasselNetV2+, the proposed method achieved state-of-the-art counting performance on RIB and had advantages in location accuracy. The counting results revealed a quantitative dynamic change in the number of rapeseed inflorescences in the time dimension. Furthermore, a significant positive correlation between the actual crop yield and the automatically obtained rapeseed inflorescence total number on a field plot level was identified. Thus, a set of UAV- assisted methods for better determination of the flower richness was developed, which can greatly support the breeding of high-yield rapeseed varieties.

This study presents an experimental investigation of blade-shaped riblets for drag reduction in unmanned aerial vehicle (UAV) applications. UAVs have gained significant attention since they can perform various missions, including surveillance, reconnaissance, and package delivery. However, their aerodynamic performance, specifically the high drag associated with their exposed surfaces, remains a key challenge for enhancing their efficiency and extending their flight endurance. To address this issue, riblet geometries are proposed as a potential solution, which can reduce the turbulent skin friction drag by up to 8%. The experimental investigation involves wind tunnel testing of blade-shaped riblets, with various spacing-to-height (s/h) ratios and constant groove cross-sectional area (Ag). The riblets are designed for application on the wing, empennage, and fuselage surfaces of a UAV. The investigations are performed on a flat plate for various flow conditions, including different freestream velocities, to evaluate the drag reduction effectiveness of the riblet configuration. The drag force is measured using a force balance system and flow visualization techniques are employed to assess the position where the boundary layer has transitioned to fully turbulent. The results demonstrate the drag-reducing effect of blade-shaped and trapezoidal riblets and the different performances observed for the various s/h ratios. The cases with s/h=1 result in the smallest drag coefficients, while the cases with s/h=2 have significantly increased drag values, compared to the smooth flat plate, due to the increased wetted surface area. These findings highlight the potential of riblets as an effective drag-reduction technique for UAV applications, enabling increased endurance and/or enhanced payload capacity.

To overcome challenges associated with crop species identification in unmanned aerial vehicle (UAV) imagery—specifically missed detections of small-sized targets, disturbances caused by intricate environmental elements, and suboptimal computational efficiency of detection models—this study introduces a streamlined detection framework that integrates YOLOv9 with Convolutional Block Attention Module (CBAM) and Spatial Channel Reconstruction Convolution (SCConv). Initial modifications involve embedding CBAM within the YOLOv9 backbone architecture. This enhancement exploits the collaborative functioning of channel-wise and spatial attention mechanisms to amplify the model's sensitivity toward critical localized crop characteristics, such as panicle morphological structures and foliar texture patterns, while concurrently mitigating noise interference from soil surfaces and weed vegetation. Subsequent improvements involve substituting conventional convolutional layers with Spatial Channel Reconstruction Convolution. This substitution capitalizes on the module's adaptive feature reorganization capabilities to achieve parameter reduction without compromising feature representation capacity, thereby substantially enhancing operational efficiency during edge device deployment. Empirical evaluations conducted on a proprietary dataset comprising 1,000 UAV-captured images representing seven distinct crop types demonstrate that the optimized model attains a mean Average Precision (mAP) of 94.5% when applying a 50% Intersection over Union threshold—a performance gain of 2.2 percentage points compared to the baseline YOLOv9 architecture. These results confirm the system's capability to meet real-time recognition demands within complex agricultural landscapes. The proposed methodology presents a cost-effective, high-accuracy monitoring solution for UAV-based precision agriculture applications, holding significant practical value for advancing intelligent management systems in modern agricultural practices.

In the contemporary context, pest detection is progressively moving toward automation and intelligence. However, current pest detection algorithms still face challenges, such as lower accuracy and slower operation speed in detecting small objects. To address this issue, this study presents a crop pest target detection algorithm, GLU-YOLOv8, designed for complex scenes based on an enhanced version of You Only Look Once version 8 (YOLOv8). The algorithm introduces the SCYLLA-IOU (SIOU) loss function, which enhances the model generalization to various pest sizes and shapes by ensuring smoothness and reducing oscillations during training. Additionally, the algorithm incorporates the Convolutional Block Attention Module (CBAM) and Locality Sensitive Kernel (LSK) attention mechanisms to boost the pest target features. A novel Gated Linear Unit CONV (GLU-CONV) is also introduced to enhance the model’s perceptual and generalization capabilities while maintaining performance. Furthermore, GLU-YOLOv8 includes a small-object detection layer with a feature map size of 160 × 160 to extract more features of small-target pests, thereby improving detection accuracy and enabling more precise localization and identification of small-target pests. The study conducted a comparative analysis between the GLU-YOLOv8 model and other models, such as YOLOv8, Faster RCNN, and RetinaNet, to evaluate detection accuracy and precision. In the Scolytidae forestry pest dataset, GLU-YOLOv8 demonstrated an improvement of 8.2% in mAP@0.50 for small-target detection compared to the YOLOv8 model, with a resulting mAP@0.50 score of 97.4%. Specifically, on the IP102 dataset, GLU-YOLOv8 outperforms the YOLOv8 model with a 7.1% increase in mAP@0.50 and a 5% increase in mAP@0.50:0.95, reaching 58.7% for mAP@0.50. These findings highlight the significant enhancement in the accuracy and recognition rate of small-target detection achieved by GLU-YOLOv8, along with its efficient operational performance. This research provides valuable insights for optimizing small-target detection models for various pests and diseases.

Fuel cells (FCs) are clean and green power sources. The reported FCs in vehicle applications include three types: (1) hydrogen FCs, (2) methanol FCs, and (3) solid oxide FCs. In terms of unmanned aerial vehicle (UAV) applications, using the hydrogen FCs to achieve the power supply is the easiest and most commonly used scheme. In addition, the methanol and solid oxide FCs also have their special applications as major or auxiliary power sources in UAVs. This chapter focuses on the related technologies and crucial issues of the commonly used FCs in UAV applications. The discussions include the simplified working principles and analyses of the above three types of FCs, onboard hydrogen fuel storage styles, auxiliary or complementary power sources, topologies and power control of FC hybrid power systems, and crucial issues of current FC technologies. At last, conclusions and future breakthrough directions are given, which would be very useful for developing novel and high-performance FC power systems for UAVs.KeywordsUnmanned aerial vehiclesFuel cellsOnboard hydrogen fuel storageAuxiliary power sourceTopologies and power control

MRI image classification of brain tumors is critical for accurate and early diagnosis. New developments in deep learning have revealed that inserting attention mechanisms into convolutional neural networks can greatly improve classification performance. This work assesses the effectiveness of Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) integrated with the ResNet50 model for brain tumor classification. The SE module recalibrates channel-wise feature responses, while CBAM enhances feature representation by combining channel and spatial attention. The SE and CBAM are combined with ResNet50, greatly increasing classification accuracy, precision, and recall when compared to the basic model, according to experimental results on MRI datasets. The suggested model employs attention mechanisms to focus valuable information selectively and suppress irrelevant information. The experiments on publicly available brain tumor datasets display great improvements over basic CNN models, with precision, recall, accuracy, as well as F1 score at 0.9914, 0.9903, 0.9945, and 0.9908, respectively. From these results, the importance of attention mechanisms in deep learning models for medical imaging is highlighted, which suggests that SE and CBAM modules can be available as more dependable and effective instruments for brain tumor classification in clinical settings. Future studies should investigate transformer-based and hybrid attention techniques to enhance automated brain tumor categorization.