Search Results (1,687)

Underwater object detection using side-scan sonar (SSS) remains a significant challenge in marine exploration, especially for small objects. Conventional methods for small object detection face various obstacles, such as difficulties in feature extraction and the considerable impact of noise on detection accuracy. To address these issues, this study proposes an improved YOLOv11 network named YOLOv11-SDC. Specifically,a new Sparse Feature (SF) module is proposed, replacing the Spatial Pyramid Pooling Fast (SPPF) module from the original YOLOv11 architecture to enhance object feature selection. Furthermore, the proposed YOLOv11-SDC integrates a Dilated Reparam Block (DRB) with a C3k2 module to broaden the model’s receptive field. A Content-Guided Attention Fusion (CGAF) module is also incorporated prior to the detection module to assign appropriate weights to various feature maps, thereby emphasizing the relevant object information. Experimental results clearly demonstrate the superiority of YOLOv11-SDC over several iterations of YOLO versions in detection performance. The proposed method was validated through extensive real-world experiments, yielding a precision of 0.934, recall of 0.698, [email protected] of 0.825, and [email protected]:0.95 of 0.598. In conclusion, the improved YOLOv11-SDC offers a promising solution for detecting small objects in SSS images, showing substantial potential for marine applications. Full article

This paper proposes a bionic social learning strategy pigeon-inspired optimization (BSLSPIO) algorithm to tackle cooperative path planning for multiple unmanned aerial vehicles (UAVs) with cooperative detection. Firstly, a modified pigeon-inspired optimization (PIO) is proposed, which incorporates a bionic social learning strategy. In this modification, the global best is replaced by the average of the top-ranked solutions in the map and compass operator, while the global center is replaced by the local center in the landmark operator. The paper also proves the algorithm’s convergence and provides complexity analysis. Comparison experiments demonstrate that the proposed method searches for the optimal solution while guaranteeing fast convergence. Subsequently, a path-planning model, detection units’ network model, and cost estimation are constructed. The developed BSLSPIO is utilized to generate feasible paths for UAVs, adhering to time consistency constraints. The simulation results show that the BSLSPIO generates feasible paths at minimum cost and effectively solves the UAVs’ cooperative path-planning problem. Full article

Due to the large number of parameters and high computational complexity of current target detection models, it is challenging to perform fast and accurate target detection in side-scan sonar images under the existing technical conditions, especially in environments with limited computational resources. Moreover, since the original waterfall map of side-scan sonar only consists of echo intensity information, which is usually of a large size, it is difficult to fuse it with other multi-source information, which limits the detection accuracy of models. To address these issues, we designed DBnet, a lightweight target detector featuring two lightweight backbone networks (PP-LCNet and GhostNet) and a streamlined neck structure for feature extraction and fusion. To solve the problem of unbalanced aspect ratios in sonar data waterfall maps, DBnet employs the SAHI algorithm with sliding-window slicing inference to improve small-target detection accuracy. Compared with the baseline model, DBnet has 33% fewer parameters and 31% fewer GFLOPs while maintaining accuracy. Tests performed on two datasets (SSUTD and SCTD) showed that the mAP values improved by 2.3% and 6.6%. Full article

Maize is an excellent crop with high yields and versatility, and the extent and frequency of pest outbreaks will have a serious impact on maize yields. Therefore, helping growers accurately identify pest species is important for improving corn yields. Thus, in this study, we propose to use a pest detector called SMC-YOLO, which is proposed using You Only Look Once (YOLO) v8 as a reference model. First, the Spatial Pyramid Convolutional Pooling Module (SPCPM) is utilized in lieu of the Spatial Pyramid Pooling-Fast (SPPF) to enrich the diversity of feature information. Subsequently, a Multi-Dimensional Feature-Enhancement Module (MDFEM) is incorporated into the neck network. This module serves the purpose of augmenting the feature information associated with pests. Finally, a cross-scale feature-level non-local module (CSFLNLM) is incorporated in front of the detector head, which improves the global perception of the detector head. The results showed that SMC-YOLO achieved excellent results in several metrics, with its F1 Score (F1), mean Average Precision (mAP) @0.50, [email protected]:0.95 and [email protected] reaching 83.18%, 86.7%, 60.6% and 70%, respectively, outperforming YOLOv11. This study provides a more reliable method of pest identification for the development of smart agriculture. Full article

Underwater target detection exhibits extensive applications in marine target exploration and marine environmental monitoring. However, conventional images of underwater targets present challenges including blurred contour information, complex environmental conditions, and pronounced scattering effects. In this work, an underwater target detection method based on YOLOv10 is designed, and the detection performance is compared with the YOLOv5 model. Experimental results demonstrate that the YOLOv10 model has a mAP50 of 85.6% on the URPC 2020 dataset, improving the mAP50 by 1.2% than that of YOLOv5. This model exhibits high detection accuracy and high proceeding speed, which provides a promising support for precise and fast underwater target detection. Full article

Multistage text-to-image generation algorithms have shown remarkable success. However, the images produced often lack detail and suffer from feature loss. This is because these methods mainly focus on extracting features from images and text, using only conventional residual blocks for post-extraction feature processing. This results in the loss of features, greatly reducing the quality of the generated images and necessitating more resources for feature calculation, which will severely limit the use and application of optical devices such as cameras and smartphones. To address these issues, the novel High-Detail Feature-Preserving Network (HDFpNet) is proposed to effectively generate high-quality, near-realistic images from text descriptions. The initial text-to-image generation (iT2IG) module is used to generate initial feature maps to avoid feature loss. Next, the fast excitation-and-squeeze feature extraction (FESFE) module is proposed to recursively generate high-detail and feature-preserving images with lower computational costs through three steps: channel excitation (CE), fast feature extraction (FFE), and channel squeeze (CS). Finally, the channel attention (CA) mechanism further enriches the feature details. Compared with the state of the art, experimental results obtained on the CUB-Bird and MS-COCO datasets demonstrate that the proposed HDFpNet achieves better performance and visual presentation, especially regarding high-detail images and feature preservation. Full article

Seed quality testing is crucial for ensuring food security and stability. To accurately detect the germination status of corn seeds during the paper medium germination test, this study proposes a corn seed germination status detection model based on YOLO v8n (CSGD-YOLO). Initially, to alleviate the complexity encountered in conventional models, a lightweight spatial pyramid pooling fast (L-SPPF) structure is engineered to enhance the representation of features. Simultaneously, a detection module dubbed Ghost_Detection, leveraging the GhostConv architecture, is devised to boost detection efficiency while simultaneously reducing parameter counts and computational overhead. Additionally, during the downsampling process of the backbone network, a downsampling module based on receptive field attention convolution (RFAConv) is designed to boost the model’s focus on areas of interest. This study further proposes a new module named C2f-UIB-iAFF based on the faster implementation of cross-stage partial bottleneck with two convolutions (C2f), universal inverted bottleneck (UIB), and iterative attention feature fusion (iAFF) to replace the original C2f in YOLOv8, streamlining model complexity and augmenting the feature fusion prowess of the residual structure. Experiments conducted on the collected corn seed germination dataset show that CSGD-YOLO requires only 1.91 M parameters and 5.21 G floating-point operations (FLOPs). The detection precision(P), recall(R), mAP_0.5, and mAP_0.50:0.95 achieved are 89.44%, 88.82%, 92.99%, and 80.38%. Compared with the YOLO v8n, CSGD-YOLO improves performance in terms of accuracy, model size, parameter number, and floating-point operation counts by 1.39, 1.43, 1.77, and 2.95 percentage points, respectively. Therefore, CSGD-YOLO outperforms existing mainstream target detection models in detection performance and model complexity, making it suitable for detecting corn seed germination status and providing a reference for rapid germination rate detection. Full article

The issue of power quality disturbances in modern power systems has become increasingly complex and severe, with multiple disturbances occurring simultaneously, leading to a decrease in the recognition accuracy of traditional algorithms. This paper proposes a composite power quality disturbance identification method based on the integration of improved Complementary Ensemble Empirical Mode Decomposition (CEEMDAN), Hilbert Transform (HT), and Extreme Learning Machine (ELM). Addressing the limitations of traditional signal processing techniques in handling nonlinear and non-stationary signals, this study first preprocesses the collected initial power quality signals using the improved CEEMDAN method to reduce modal aliasing and spurious components, thereby enabling a more precise decomposition of noisy signals into multiple Intrinsic Mode Functions (IMFs). Subsequently, the HT is utilized to conduct a thorough analysis of the reconstructed signals, extracting their time-amplitude information and instantaneous frequency characteristics. This feature information provides a rich data foundation for subsequent classification and identification. On this basis, an improved ELM is introduced as the classifier, leveraging its powerful nonlinear mapping capabilities and fast learning speed to perform pattern recognition on the extracted features, achieving accurate identification of composite power quality disturbances. To validate the effectiveness and practicality of the proposed method, a simulation experiment is designed. Upon examination, the approach introduced in this study retains a fault diagnosis accuracy exceeding 95%, even amidst significant noise disturbances. In contrast to conventional techniques, such as Convolutional Neural Network (CNN) and Support Vector Machine (SVM), this method achieves an accuracy enhancement of up to 5%. Following optimization via the Particle Swarm Optimization (PSO) algorithm, the model’s accuracy is boosted by 3.6%, showcasing its favorable adaptability. Full article

In this paper, the application is investigated of fast Fourier transform filtering (FFT-FR) to high spatial resolution digital terrain models (HR-DTM) derived from LiDAR sensors, assessing its efficacy in identifying genuine relief elements, including both natural geological features and anthropogenic landforms. The suitability of the derived filtered geomorphic references (FGRs) is evaluated through spatial correlation with ground truths (GTs) extracted from the topographical and geological geodatabases of Santander Bay, Northern Spain. In this study, it is revealed that existing artefacts, derived from vegetation or human infrastructures, pose challenges in the units’ construction, and large physiographic units are better represented using low-pass filters, whereas detailed units are more accurately depicted with high-pass filters. The results indicate a propensity of high-frequency filters to detect anthropogenic elements within the DTM. The quality of GTs used for validation proves more critical than the geodatabase scale. Additionally, in this study, it is demonstrated that the footprint of buildings remains uneliminated, indicating that the model is a poorly refined digital surface model (DSM) rather than a true digital terrain model (DTM). Experiments validate the DTM’s capability to highlight contacts and constructions, with water detection showing high precision (≥60%) and varying precision for buildings. Large units are better captured with low filters, whilst high filters effectively detect anthropogenic elements and more detailed units. This facilitates the design of validation and correction procedures for DEMs derived from LiDAR point clouds, enhancing the potential for more accurate and objective Earth surface representation. Full article

The accuracy and stability of front-end point cloud registration algorithms are crucial for the mapping and localization precision in laser SLAM (simultaneous localization and mapping) systems. Traditional point-to-line and point-to-plane iterative closest point (ICP) registration algorithms, widely used in SLAM front ends, often suffer from low efficiency, significant data dependency during the matching process, and a propensity for local optima. This registration method exhibits a more pronounced local optimum issue in large-scale SLAM mapping, thereby diminishing matching accuracy and increasing reliance on initial values. To address these limitations, this paper introduces NI-LIO, a novel SLAM algorithm that integrates ICP with normal distributions transform (NDT) to enhance localization accuracy, computational efficiency and robustness. By combining the precision of ICP with the robustness of NDT, the proposed algorithm significantly improves system stability and localization accuracy. The analysis of mapping and localization experiments indicates a significant reduction in errors compared to traditional SLAM algorithms, with experiments showing a REMS value decrease of over 20%. Compared to ALOAM, FAST_LIO2 and Lego-LOAM algorithms, the new NI-LIO algorithm shows improvements in both accuracy and stability, enabling the construction of a more precise and consistent global map. This algorithm exhibits excellent adaptability to various environments. Full article

Food sustainability has become a major global concern in recent years. Multiple complimentary strategies to deal with this issue have been developed; one of these approaches is regenerative farming. The identification and analysis of crop type phenology are required to achieve sustainable regenerative faming. Earth Observation (EO) data have been widely applied to crop type identification using supervised Machine Learning (ML) and Deep Learning (DL) classifications, but these methods commonly rely on large amounts of ground truth data, which usually prevent historical analysis and may be impractical in very remote, very extensive or politically unstable regions. Thus, the development of a robust but intelligent unsupervised classification model is attractive for the long-term and sustainable prediction of agricultural yields. Here, we propose FastDTW-HC, a combination of Fast Dynamic Time Warping (DTW) and Hierarchical Clustering (HC), as a significantly improved method that requires no ground truth input for the classification of winter food crop varieties of barley, wheat and rapeseed, in Norfolk, UK. A series of variables is first derived from the EO products, and these include spectral indices from Sentinel-2 multispectral data and backscattered amplitude values at dual polarisations from Sentinel-1 Synthetic Aperture Radar (SAR) data. Then, the phenological patterns of winter barley, winter wheat and winter rapeseed are analysed using the FastDTW-HC applied to the time-series created for each variable, between Nov 2019 and June 2020. Future research will extend this winter food crop mapping analysis using FastDTW-HC modelling to a regional scale. Full article

Software-defined networking (SDN) offers an effective solution for flexible management of Wireless Sensor Networks (WSNs) by separating control logic from sensor nodes. This paper tackles the challenge of timely recovery from SDN controller failures and proposes a game theoretic model for multi-domain controllers. A game-enhanced autonomous fault recovery algorithm for SDN controllers is proposed, which boasts fast fault recovery and low migration costs. Taking into account the remaining capacity of controllers and the transition relationships between devices, the target controller is first selected to establish a controller game domain. The issue of mapping the out-of-control switches within the controller game domain to the target controller is transformed into a linear programming problem for solution. A multi-population particle swarm optimization algorithm with repulsive interaction is employed to iteratively evolve the optimal mapping between controllers and switches. Finally, migration tasks are executed based on the optimal mapping results, and the role transition of the target controller is completed. Comparative experimental results demonstrate that, compared to existing SDN controller fault recovery algorithms, the proposed algorithm can balance the migration cost of switches and the load pressure on controllers while reducing propagation delay in SDN controllers, significantly decreasing the fault recovery time. Full article

Parthenium weed (Parthenium hysterophorus L.) is one of the most noxious and fast-spreading invasive alien species, posing a major threat to ecosystems, agriculture, and public health worldwide. Mechanistic and correlative species distribution models are commonly employed to determine the potential habitat suitability of parthenium weed. However, a comparative analysis of these two approaches for parthenium weed is lacking, leaving a gap in understanding their relative effectiveness and ability to describe habitat suitability of parthenium weed. This study compared the mechanistic model CLIMEX with random forest (RF), the best-performing of a suite of correlative models. When compared against occurrence records and pseudo-absences, measured by area under the receiver operating characteristic curve, true skill statistic, sensitivity, and specificity, the results revealed higher performance of RF compared to CLIMEX. Globally, RF predicted 7 million km² (2% of the total land mass) as suitable for parthenium weed, while CLIMEX predicted 20 million km² (13%). Based on binary maps, RF and CLIMEX identified 67 and 20 countries as suitable, respectively. For Bhutan, globally trained RF predicted 8919 km² (23% of the country’s total 38,394 km²) as currently suitable, with high suitability in the southern, west–central, central, and eastern districts, particularly along major highways. For the future, the 10 general circulation models downscaled to Bhutan showed a decrease in suitability across four scenarios (SSP126, SSP245, SSP370, SSP585) and three periods (2021–2050, 2051–2080, 2071–2100), with a northward shift in suitable habitats ranging from 2 to 76 km. Additionally, 2049 (23%) km² of agricultural land is currently at risk of being invaded by parthenium weed. Correlative and mechanistic models are based on different niche concepts (i.e., realized and fundamental, respectively), and therefore combining them can provide a better understanding of actual and potential species distributions. Given the high suitability of parthenium weed under the current climate and its potential negative impacts in Bhutan, early action such as early detection and control of infested areas, regular survey and monitoring, and creating public awareness are proposed as risk mitigation strategies. Full article

Sustainable agriculture is pivotal to global food security and economic stability, with plant disease detection being a key challenge to ensuring healthy crop production. The early and accurate identification of plant diseases can significantly enhance agricultural practices, minimize crop losses, and reduce the environmental impacts. This paper presents an innovative approach to sustainable development by leveraging machine learning models to detect plant diseases, focusing on tomato crops—a vital and globally significant agricultural product. Advanced object detection models including YOLOv8 (minor and nano variants), Roboflow 3.0 (Fast), EfficientDetV2 (with EfficientNetB0 backbone), and Faster R-CNN (with ResNet50 backbone) were evaluated for their precision, efficiency, and suitability for mobile and field applications. YOLOv8 nano emerged as the optimal choice, offering a mean average precision (MAP) of 98.6% with minimal computational requirements, facilitating its integration into mobile applications for real-time support to farmers. This research underscores the potential of machine learning in advancing sustainable agriculture and highlights future opportunities to integrate these models with drone technology, Internet of Things (IoT)-based irrigation, and disease management systems. Expanding datasets and exploring alternative models could enhance this technology’s efficacy and adaptability to diverse agricultural contexts. Full article

The coastal zone of the Sea of Azov is a dynamic environment influenced by various natural and anthropogenic factors, including wind, wave action, beach material removal, and cultivation on cliff edges. The coastal zone of freezing seas is also influenced by ice cover during winter. This study investigates the dynamics of the Sea of Azov’s coastal zone during winter (2014–2023), focusing on the impacts of waves and ice, to identify the most vulnerable coastal areas. We analyzed high-resolution satellite imagery and employed mathematical modeling to obtain data on ice pile-up, fast ice formation, wind patterns, and storm wave dynamics within the shallow coastal zone. Long-term wind data revealed an increase in maximum wind speeds in December and January, while February and March showed a decrease or no significant trend across most coastal observation stations. Storm waves (significant wave height) during the cold season can reach heights of 3.26 m, contributing to coastal erosion and instability. While the overall ice cover in the Sea of Azov is decreasing, with fast ice rarely exceeding 0.85% of the total sea area, ice pile-up still occurs almost annually, with the eastern part of Taganrog Bay exhibiting the highest probability of these events. Our analysis identified the primary impacts affecting the shallow coastal zone of the Sea of Azov between 2014 and 2023. A map was generated to illustrate these impacts, revealing that nearly the entire coastline is subject to varying degrees of wave and ice impact. Exceptions include the eastern coast, which experiences minimal fast ice and ice pile-up, with average or lower dynamic loads, and the southern coast, where wind–wave action is the dominant factor. Full article