Search Results (34)

Ship detection and identification play pivotal roles in ensuring navigation safety and facilitating efficient maritime traffic management. Aiming at ship detection in complex environments, which often faces problems such as the dense occlusion of ship targets, low detection accuracy, and variable environmental conditions, in this paper, we propose a ship detection algorithm CSD-YOLO (Context guided block module, Slim-neck, Deformable large kernel attention-You Only Look Once) based on the deformable large kernel attention (D-LKA) mechanism, which was improved based on YOLOv8 to enhance its performance. This approach integrates several innovations to bolster its performance. Initially, the utilization of the Context Guided Block module (CG block) enhanced the c2f module of the backbone network, thereby augmenting the feature extraction capabilities and enabling a more precise capture of the key image information. Subsequently, the introduction of a novel neck architecture and the incorporation of the slim-neck module facilitated more effective feature fusion, thereby enhancing both the accuracy and efficiency of detection. Furthermore, the algorithm incorporates a D-LKA mechanism to dynamically adjust the convolution kernel shape and size, thereby enhancing the model’s adaptability to varying ship target shapes and sizes. To address data scarcity in complex marine environments, the experiments utilized a fused dataset comprising the SeaShips dataset and a proprietary dataset. The experimental results demonstrate that the CSD-YOLO algorithm outperformed the YOLOv8n algorithm across all model evaluation metrics. Specifically, the precision rate (precision) was 91.5%, the recall rate (recall) was 89.5%, and the mean accuracy (mAP) was 91.5%. Compared to the benchmark algorithm, the Recall was improved by 0.7% and the mAP was improved by 0.4%. These results indicate that the CSD-YOLO algorithm can effectively meet the requirements for ship target recognition and tracking in complex marine environments. Full article

Effective lane detection technology plays an important role in the current autonomous driving system. Although deep learning models, with their intricate network designs, have proven highly capable of detecting lanes, there persist key areas requiring attention. Firstly, the symmetry inherent in visuals captured by forward-facing automotive cameras is an underexploited resource. Secondly, the vast potential of position information remains untapped, which can undermine detection precision. In response to these challenges, we propose FF-HPINet, a novel approach for lane detection. We introduce the Flipped Feature Extraction module, which models pixel pairwise relationships between the flipped feature and the original feature. This module allows us to capture symmetrical features and obtain high-level semantic feature maps from different receptive fields. Additionally, we design the Hierarchical Position Information Extraction module to meticulously mine the position information of the lanes, vastly improving target identification accuracy. Furthermore, the Deformable Context Extraction module is proposed to distill vital foreground elements and contextual nuances from the surrounding environment, yielding focused and contextually apt feature representations. Our approach achieves excellent performance with the F1 score of 97.00% on the TuSimple dataset and 76.84% on the CULane dataset. Full article

This study introduces an innovative approach for the reconstruction of wind turbine tower states using a tangential recursion algorithm. The primary objective is to enable real-time monitoring of the operational condition of wind turbine towers. The proposed method is rooted in strain–load theory, which enables the accurate identification of tower load states. The tangential recursion algorithm is utilized to translate the strain data acquired from strategically placed sensors into reconstructed point positions. The subsequent refinement of these positions incorporates considerations of torsional loads and geometric deformations, culminating in the comprehensive and precise reconstruction of the tower’s deformation behavior. Through the use of the OpenFAST V8 simulation software, a thorough analysis is conducted to investigate the load and deformation characteristics of the NREL 5 MW wind turbine tower across diverse operational scenarios. Furthermore, the load conditions corresponding to rated operating circumstances are applied to a finite element model constructed with the lumped mass method. The identification of tower load states and the comprehensive reconstruction of deformation patterns are realized through the extraction of strain data from critical points in the finite element model. The credibility and accuracy of the proposed method are rigorously evaluated by juxtaposing the identification and reconstruction outcomes with the results derived from the OpenFAST simulations and finite element analyses. Notably, the proposed method circumvents the requirement for external auxiliary calibration equipment for the tower, rendering it adaptable to a broader spectrum of operational contexts and making it consistent with unfolding trajectories in wind power advancement. Full article

As a city undergoes large-scale construction and expansion, there is an urgent need to monitor the stability of the ground and infrastructure. The time-series InSAR technique is an effective tool for measuring surface displacements. However, interpreting these displacements in a built environment, where observed displacements consist of mixed signals, poses a challenge. This study uses principal component analysis (PCA) and the k-means clustering method for exploring deformation series within an unsupervised learning context. The PCA method extracts the dominant components in deformation series, whereas the clustering method identifies similar deformation series. This method was tested on Kunming City (KMC) using C-band Sentinel-1, X-band TerraSAR-X, and L-band ALOS-2 PALSAR-2 data acquired between 2017 to 2022. The experiment demonstrated that the suggested unsupervised learning approach can group PS points with similar kinematic characteristics. Five types of deformation kinematic characteristics were discovered in the three SAR datasets: upward, slight upward, stability, slight downward, and downward. According to the results, less than 20% of points exhibit significant motion trends, whereas 50% show small velocity values but still demonstrate movement trends. The remaining 30% are relatively stable. Similar clustering results were obtained from the three datasets using unsupervised methods, highlighting the effectiveness of identifying spatial–temporal patterns over the study area. Moreover, It was found that clustering based on kinematic characteristics enhances the interpretation of InSAR deformation, particularly for points with small deformation velocities. Finally, the significance of PCA decomposition in interpreting InSAR deformation was discussed, as it can better represent series with noise, enabling their accurate identification. Full article

Benefiting from the powerful feature extraction capability of deep learning, the Siamese tracker stands out due to its advanced tracking performance. However, constrained by the complex backgrounds of aerial tracking, such as low resolution, occlusion, similar objects, small objects, scale variation, aspect ratio change, deformation and limited computational resources, efficient and accurate aerial tracking is still difficult to realize. In this work, we design a lightweight and efficient adaptive temporal contextual aggregation Siamese network for aerial tracking, which is designed with a parallel atrous module (PAM) and adaptive temporal context aggregation model (ATCAM) to mitigate the above problems. Firstly, by using a series of atrous convolutions with different dilation rates in parallel, the PAM can simultaneously extract and aggregate multi-scale features with spatial contextual information at the same feature map, which effectively improves the ability to cope with changes in target appearance caused by challenges such as aspect ratio change, occlusion, scale variation, etc. Secondly, the ATCAM adaptively introduces temporal contextual information to the target frame through the encoder-decoder structure, which helps the tracker resist interference and recognize the target when it is difficult to extract high-resolution features such as low-resolution, similar objects. Finally, experiments on the UAV20L, UAV123@10fps and DTB70 benchmarks demonstrate the impressive performance of the proposed network running at a high speed of over 75.5 fps on the NVIDIA 3060Ti. Full article

A new utilization of entropy in the context of buckling is presented. The novel concept of connecting the strain energy and entropy for a pin-ended strut is derived. The entropy of the buckling mode is extracted through a surrogate model by decomposing the strain energy into entropy and virtual temperature. This concept rationalizes the ranking of buckling modes based on their strain energy under the assumption of given entropy. By assigning identical entropy to all buckling modes, they can be ranked according to their deformation energy. Conversely, with identical strain energy assigned to all the modes, ranking according to entropy is possible. Decreasing entropy was found to represent the scaling factors of the buckling modes that coincide with the measurement of the initial out-of-straightness imperfections in IPE160 beams. Applied to steel plane frames, scaled buckling modes can be used to model initial imperfections. It is demonstrated that the entropy (scale factor) for a given energy roughly decreases with the inverse square of the mode index. For practical engineering, this study presents the possibility of using scaled buckling modes of steel plane frames to model initial geometric imperfections. Entropy proves to be a valuable complement to strain energy in structural mechanics. Full article

Shale oil represents a relatively new form of unconventional oil and gas resource, and the extensive exploration and development of shale oil resources carry significant implications for China’s oil and gas supply and demand dynamics. At present, within the realm of low-maturity shale oil extraction technologies, the reservoir must be subjected to elevated temperatures ranging between 400 to 60 °C. Prolonged exposure of wellbores to such high temperatures can result in a substantial decrease in cement strength, the formation of microcracks due to cement cracking, and damage stemming from thermal stresses on the casing. Casing damage stands out as a prominent factor contributing to wellbore integrity failures and well shutdowns within the context of shale oil development. Given the limited natural energy reservoirs of shale oil formations, it becomes necessary to supplement the reservoir’s energy during the development process. Furthermore, shale oil exhibits high viscosity and poor flowability, and conventional water injection methods yield limited efficacy. This situation can induce significant shifts in the stress field and rock mechanical parameters, potentially activating specific formations and complicating the load dynamics on the casing. Consequently, the risk of failure increases. In light of these considerations, this study uses numerical simulations to study the integrity of high-temperature injection and production wellbores in shale oil and aims to encompass a comprehensive evaluation and analysis of the principal factors that influence casing damage, the fluctuations in thermal stress, and the yield strength of various steel grades of casings exposed to alternating stress conditions. Subsequently, this paper developed a model for simulating the temperature and pressure within shale oil and steam injection wellbores to support engineering design analysis. The research results indicate that the application of pre-stress results in a significant increase in stress at the casing pipe head while causing a noticeable decrease in stress within the pipe wall. When N80 casing is used, the entire casing experiences thermal stresses surpassing the casing’s yield limit. Stress concentration may arise at both ends of the external seal, potentially leading to casing contraction, shear failure, and, under non-uniform stress conditions, casing bending deformation. The temperature of steam injection significantly influences the temperature field of the casing wall, with stress values experiencing a marked reduction when the steam injection temperature decreases from 350 °C to 200 °C, underscoring the substantial impact of temperature on casing thermal stress. As the steam injection process advances along with injection-production cycles, shear stresses at the interface can exceed the bond strength, resulting in relative slippage between the cement and the casing. The bonding force between the wellbore and the cement primarily depends on the interface’s friction, particularly in the context of friction during wellhead lifting. This study endeavors to determine rational injection and production parameters under varying conditions, optimize completion methods, reduce casing damage, and extend the casing’s operational life; it aims to offer critical technical support for the safe and efficient development of shale oil resources. Full article

With a larger field of view (FOV) than ordinary images, fisheye images are becoming mainstream in the field of autonomous driving. However, the severe distortion problem of fisheye images also limits its application. The performance of neural networks designed for narrow FOV images degrades drastically for fisheye images, and the use of large composite models can improve the performance, but it brings huge time overhead and hardware costs. Therefore, we decided to balance real time and accuracy by designing the deformable segmentation attention(DSA) module, a generalpurpose architecture based on a deformable attention mechanism and a spatial pyramid architecture. The deformable mechanism serves to accurately extract feature information from fisheye images, together with attention to learn the global context and the spatial pyramid structure to balance multiscale feature information, thus improving the perception of fisheye images by traditional networks without increasing the amount of excessive computation. Lightweight networks such as SegNeXt equipped with the DSA module enable effective and rapid multi-scale segmentation of fisheye images in complex scenes. Our architecture achieves outstanding results on the WoodScape dataset, while our ablation experiments demonstrate the effectiveness of various parts of the architecture. Full article

Artificial intelligence (AI) and computer vision technologies have gained significant prominence in the field of education. These technologies enable the detection and analysis of students’ classroom behaviors, providing valuable insights for assessing individual concentration levels. However, the accuracy of target detection methods based on Convolutional Neural Networks (CNNs) can be compromised in classrooms with multiple targets and varying scales, as convolutional operations may result in the loss of location information. In contrast, transformers, which leverage attention mechanisms, have the capability to learn global features and mitigate the information loss caused by convolutional operations. In this paper, we propose a students’ classroom behavior detection system that combines deformable DETR with a Swin Transformer and light-weight Feature Pyramid Network (FPN). By employing a feature pyramid structure, the system can effectively process multi-scale feature maps extracted by the Swin Transformer, thereby improving the detection accuracy for targets of different sizes and scales. Moreover, the integration of the CARAFE lightweight operator into the FPN structure enhances the network’s detection accuracy. To validate the effectiveness of our approach, extensive experiments are conducted on a real dataset of students’ classroom behavior. The experimental results demonstrate a significant 6.1% improvement in detection accuracy compared to state-of-the-art methods. These findings highlight the superiority of our proposed network in accurately detecting and analyzing students’ classroom behaviors. Overall, this research contributes to the field of education by addressing the limitations of CNN-based target detection methods and leveraging the capabilities of transformers to improve accuracy. The proposed system showcases the benefits of integrating deformable DETR, Swin Transformer, and the lightweight FPN in the context of students’ classroom behavior detection. The experimental results provide compelling evidence of the system’s effectiveness and its potential to enhance classroom monitoring and assessment practices. Full article

Vision-based identification of lane area and lane marking on the road is an indispensable function for intelligent driving vehicles, especially for localization, mapping and planning tasks. However, due to the increasing complexity of traffic scenes, such as occlusion and discontinuity, detecting lanes and lane markings from an image captured by a monocular camera becomes persistently challenging. The lanes and lane markings have a strong position correlation and are constrained by a spatial geometry prior to the driving scene. Most existing studies only explore a single task, i.e., either lane marking or lane detection, and do not consider the inherent connection or exploit the modeling of this kind of relationship between both elements to improve the detection performance of both tasks. In this paper, we establish a novel multi-task encoder–decoder framework for the simultaneous detection of lanes and lane markings. This approach deploys a dual-branch architecture to extract image information from different scales. By revealing the spatial constraints between lanes and lane markings, we propose an interactive attention learning for their feature information, which involves a Deformable Feature Fusion module for feature encoding, a Cross-Context module as information decoder, a Cross-IoU loss and a Focal-style loss weighting for robust training. Without bells and whistles, our method achieves state-of-the-art results on tasks of lane marking detection (with 32.53% on IoU, 81.61% on accuracy) and lane segmentation (with 91.72% on mIoU) of the BDD100K dataset, which showcases an improvement of 6.33% on IoU, 11.11% on accuracy in lane marking detection and 0.22% on mIoU in lane detection compared to the previous methods. Full article

Civil infrastructure monitoring with the aim of early damage detection and acquiring the data required for urban management not only prevents sudden infrastructure collapse and increases service life and sustainability but also facilitates the management of smart cities including smart transportation sectors. In this context, smart geosynthetics can act as vital arteries for extracting and transmitting information about the states of the strain, stress, damage, deformation, and temperature of the systems into which they are incorporated in addition to their traditional infrastructural roles. This paper reviews the wide range of technologies, manufacturing techniques and processes, materials, and methods that have been used to date to develop smart geosynthetics to provide rational arguments on the current trends and utilise the operational trends as a guide for predicting what can be focused on in future researches. The various multifunctional geosynthetic applications and future challenges, as well as operational solutions, are also discussed and propounded to pave the way for developing applicable smart geosynthetics. This critical review will provide insight into the development of new smart geosynthetics with the contribution to civil engineering and construction industries. Full article

This study aimed to evaluate the effect of the synthesis parameters and the incorporation of natural polyphenolic extract within hydrogel networks on the mechanical and morphological properties of physically cross-linked xanthan gum/poly(vinyl alcohol) (XG/PVA) composite hydrogels prepared by multiple cryo-structuration steps. In this context, the toughness, compressive strength, and viscoelasticity of polyphenol-loaded XG/PVA composite hydrogels in comparison with those of the neat polymer networks were investigated by uniaxial compression tests and steady and oscillatory measurements under small deformation conditions. The swelling behavior, the contact angle values, and the morphological features revealed by SEM and AFM analyses were well correlated with the uniaxial compression and rheological results. The compressive tests revealed an enhancement of the network rigidity by increasing the number of cryogenic cycles. On the other hand, tough and flexible polyphenol-loaded composite films were obtained for a weight ratio between XG and PVA of 1:1 and 10 v/v% polyphenol. The gel behavior was confirmed for all composite hydrogels, as the elastic modulus (G′) was significantly greater than the viscous modulus (G″) for the entire frequency range. Full article

The semantic segmentation of remote sensing images is a significant research direction in digital image processing. The complex background environment, irregular size and shape of objects, and similar appearance of different categories of remote sensing images have brought great challenges to remote sensing image segmentation tasks. Traditional convolutional-neural-network-based models often ignore spatial information in the feature extraction stage and pay less attention to global context information. However, spatial context information is important in complex remote sensing images, which means that the segmentation effect of traditional models needs to be improved. In addition, neural networks with a superior segmentation performance often suffer from the problem of high computational resource consumption. To address the above issues, this paper proposes a combination model of a modified multiscale deformable convolutional neural network (mmsDCNN) and dense conditional random field (DenseCRF). Firstly, we designed a lightweight multiscale deformable convolutional network (mmsDCNN) with a large receptive field to generate a preliminary prediction probability map at each pixel. The output of the mmsDCNN model is a coarse segmentation result map, which has the same size as the input image. In addition, the preliminary segmentation result map contains rich multiscale features. Then, the multi-level DenseCRF model based on the superpixel level and the pixel level is proposed, which can make full use of the context information of the image at different levels and further optimize the rough segmentation result of mmsDCNN. To be specific, we converted the pixel-level preliminary probability map into a superpixel-level predicted probability map according to the simple linear iterative clustering (SILC) algorithm and defined the potential function of the DenseCRF model based on this. Furthermore, we added the pixel-level potential function constraint term to the superpixel-based Gaussian potential function to obtain a combined Gaussian potential function, which enabled our model to consider the features of various scales and prevent poor superpixel segmentation results from affecting the final result. To restore the contour of the object more clearly, we utilized the Sketch token edge detection algorithm to extract the edge contour features of the image and fused them into the potential function of the DenseCRF model. Finally, extensive experiments on the Potsdam and Vaihingen datasets demonstrated that the proposed model exhibited significant advantages compared to the current state-of-the-art models. Full article

Dams are essential structures in the growth of a region due to their ability to store large amounts of water and manage it for different social activities, mainly for human consumption. The study of the structural behavior of dams during their useful life is a fundamental factor for their safety. In terms of structural monitoring, classic terrestrial techniques are usually costly and require much time. Interferometric synthetic aperture radar (InSAR) technology through the persistent scatterer interferometry (PSI) technique has been widely applied to measure millimeter displacements of a dam crest. In this context, this paper presents an investigation about the structural monitoring of the crest of the Sanalona dam in Mexico, applying two geodetic satellite techniques and mathematical modeling to extract the risk of the dam–reservoir system. The applicability of the InSAR technique for monitoring radial displacements in dams is evaluated and compared with both GPS systems and an analytical model based on the finite element method (FEM). The radial displacements of the Sanalona dam follow a seasonal pattern derived from the reservoir level, reaching maximum radial magnitudes close to 13 mm in November when the rainy season ends. GPS recorded and FEM simulated maximum displacements of 7.3 and 6.7 mm, respectively. InSAR derived radial displacements, and the reservoir water level presented a high similarity with a correlation index equal to 0.8. In addition, it was found that the Sanalona dam presents the greatest deformation in the central zone of the crest. On the other hand, based on the reliability analysis, the probability of failure values lower than 8.3 × ${10}^{-2}$ was obtained when the reservoir level was maximum, which means that the radial displacements did not exceed the limit states of the dam–reservoir system in the evaluated period. Finally, the extracted values of the probability of failure demonstrated that the Sanalona dam does not represent a considerable risk to society. Full article

Forest fires have continually endangered personal safety and social property. To reduce the occurrences of forest fires, it is essential to detect forest fire smoke accurately and quickly. Traditional forest fire smoke detection based on convolutional neural networks (CNNs) needs many hand-designed components and shows poor ability to detect small and inconspicuous smoke in complex forest scenes. Therefore, we propose an improved early forest fire smoke detection model based on deformable transformer for end-to-end object detection (deformable DETR). We use deformable DETR as a baseline containing the best sparse spatial sampling for smoke with deformable convolution and relation modeling capability of the transformer. We integrate a Multi-scale Context Contrasted Local Feature module (MCCL) and a Dense Pyramid Pooling module (DPPM) into the feature extraction module for perceiving features of small or inconspicuous smoke. To improve detection accuracy and reduce false and missed detections, we propose an iterative bounding box combination method to generate precise bounding boxes which can cover the entire smoke object. In addition, we evaluate the proposed approach using a quantitative and qualitative self-made forest fire smoke dataset, which includes forest fire smoke images of different scales. Extensive experiments show that our improved model’s forest fire smoke detection accuracy is significantly higher than that of the mainstream models. Compared with deformable DETR, our model shows better performance with improvement of mAP (mean average precision) by 4.2%, AP_S (AP for small objects) by 5.1%, and other metrics by 2% to 3%. Our model is adequate for early forest fire smoke detection with high detection accuracy of different-scale smoke objects. Full article