Search Results (140)

In-wheel motor bearings in electric vehicles operate in harsh environments where strong background noise often masks early fault features, limiting the accuracy of traditional diagnostic methods. This study proposes an intelligent fault diagnosis framework integrating improved Successive Variational Mode Decomposition (SVMD) with a ResNet–Kolmogorov–Arnold Network (ResNet-KAN). To enhance feature extraction, a multi-strategy Crested Porcupine Optimizer (CPO) is employed to adaptively optimise SVMD parameters. Subsequently, a Gramian angular difference field (GADF) reconstruction strategy transforms one-dimensional vibration signals into two-dimensional images to improve spatial distinguishability. Finally, a ResNet-KAN model, featuring a ReLU-based non-linear classification head, is developed to capture complex fault boundaries more effectively than traditional linear layers. Experimental results demonstrate that the CPO-SVMD method increases the kurtosis of extracted components by at least 25.6% compared to traditional optimisation methods. Furthermore, the ResNet-KAN model achieves an identification accuracy exceeding 98% on the in-wheel motor bearing dataset, outperforming 2DCNN, ResNet, and ViT models by at least 2%. This integrated approach provides a robust, high-precision solution for the intelligent condition monitoring and early warning of in-wheel motor drive systems under complex, high-noise operating conditions. Full article

The gradual increase in man-made objects in the space surrounding our planet is becoming increasingly evident. This significant rise in terrestrial materials is reflected in a greater presence of artificial satellites, space debris and waste from space missions. These objects orbiting close to Earth pose a significant risk in the event of uncontrolled re-entry, as well as collisions between the artificial satellites themselves, launch vehicles and space stations in Earth orbit. This article presents the experimental progress achieved during the prototype phase of a new model of robotic satellite observatory (SRO), featuring significant advances in its design and capabilities. These new SROs are intended to have dual capability to operate simultaneously in both scientific and military contexts. The possibility of forming a network with these devices will provide a system that substantially improves orbital determination and the identification of space objects of interest. The result presented here is an advanced model of the SRO, featuring substantial design improvements from both an ergonomic and economic perspective, as well as a significant enhancement in its ability to monitor and track space objects of uncertain origin that may be of interest or considered a threat to security, thereby expanding its Space Situational Awareness (SSA). Full article

Rear-view human tracking and re-identification remain critical challenges for robotic visual sensing in unmanned vehicles, particularly under adverse weather conditions and severe occlusion. Conventional deep learning models often suffer from feature contamination and trajectory drift under dynamic illumination. To overcome these bottlenecks, we propose a lightweight tracking framework driven by spatiotemporal prediction and multimodal feature fusion. Specifically, an ego-motion-aware Kalman prediction mechanism maintains temporal continuity during complete occlusions. Upon target reappearance, a multi-factor descriptor—fusing color histograms with geometric constraints—is employed within a dynamic Mahalanobis search region. This is coupled with a specular-reflection-penalized adaptive learning rate (η_k) that actively freezes template updates during severe environmental degradation conditions. Evaluated on a custom Mecanum-wheeled robot, the proposed method achieves a peak precision of 94.2% and a tracking success rate of 93.4%. Extensive experiments in extreme rainy night scenarios demonstrate a 35% reduction in average tracking error, maintaining a Center Location Error (CLE) below 11 pixels. Furthermore, the system achieves a rapid target re-identification response of 72.83 ms during occlusion phases. Ultimately, this framework delivers a highly robust and real-time solution for autonomous navigation in complex dynamic environments. Full article

This article draws on public opinion surveys conducted as part of the AV-PL-ROAD project, “Polish Road to Automation of Road Transport”. Although selected findings from this survey material were published in 2023, the earlier study was limited to descriptive statistical analysis. The present paper re-examines the same empirical dataset through a different analytical framework focused on latent-structure reconstruction, using a different analytical framework focused on latent-structure reconstruction, providing a more structured and informative interpretation of perceptions of autonomous vehicles in Poland. The study combines within-respondent standardization, Principal Component Analysis (PCA), and k-means clustering to identify the dominant dimensions of perception and recurring perception profiles, complemented by qualitative insights from focus group interviews (FGI) used to support interpretation. The results indicate that perceptions of autonomous vehicles are not one-dimensional, but are organized around three main axes: systemic benefits versus implementation barriers, technological trust and information security, and regulatory-ethical readiness linked to deployment conditions. The analysis also reveals four recurring perception profiles that do not map directly onto simple demographic divisions and are better understood in relation to operational and institutional context. In addition, statistically significant differences between clusters were confirmed using nonparametric tests (Kruskal–Wallis with Dunn–Šidák post hoc analysis). The main contribution of the paper is methodological: it illustrates that previously analyzed survey data can yield structurally informative insights, including the identification of latent dimensions, perception profiles, and statistically significant differences between clusters when reinterpreted through a latent-space approach rather than conventional descriptive methods. The findings provide additional evidence on the social and institutional conditions of transport automation in Poland and provide a more robust analytical basis for future mobility policy and implementation strategies. Full article

To address the core challenges in air-to-ground target re-identification (ReID), including network focus on invalid background information, poor adaptability to nonlinear feature distribution, and insufficient cross-domain generalization, this paper proposes a novel air-to-ground ReID framework based on Neighborhood Feature Centralization Attention (NFCA). On the basis of Coordinate Attention, the framework introduces a parameter-free Neighborhood Feature Centralization mechanism to build a lightweight attention module, which enhances cross-feature semantic interaction and suppresses background noise while retaining precise position encoding. It achieves end-to-end direct optimization of sample pair similarity through binary cross-entropy loss, eliminating the proxy task bias of traditional classification loss and adapting to the nonlinear structure of feature space. A multi-source data-driven training strategy is constructed by fusing ReID datasets and general classification datasets, which expands the coverage of feature space and narrows the distribution gap between training data and real air-to-ground scenarios without additional manual annotation. Experiments show that the proposed method achieves leading mAP values on the self-developed UAV air-to-ground dataset JC-1, the public person ReID dataset Market-1501, and the public vehicle ReID dataset VehicleID. Sufficient statistical validation, ablation experiments and cross-domain tests verify the advancement, reliability and generalization of the proposed method in complex air-to-ground scenarios. Full article

To address the challenge that prolonged interruptions of Global Navigation Satellite System (GNSS) signals—such as those caused by urban obstructions—hinder signal re-locking and thereby reduce the number of available satellites for integrity monitoring algorithms, this study proposes an inertial navigation-assisted GNSS re-locking method based on vehicle motion information constraints. This method leverages vehicle motion constraints to confine the primary direction of Inertial Navigation System (INS) velocity errors to the vehicle’s forward direction. Upon GNSS signal recovery, frequency error compensation is employed to mitigate Doppler errors of the previously obstructed satellites. Simulation results show that this method significantly improves the re-lock capability after a long period of satellite signal interruption, increasing the number of available satellites from 7 to 10 and optimizing the satellite geometry. At a horizontal alarm threshold of 80 m, the availability of the GNSS integrity monitoring algorithm reaches 95.7%, which is 53.7 percentage points higher than the unassisted scheme. Moreover, it can achieve 100% fault detection and identification rate even with a pseudorange deviation of 82 m, significantly improving the performance of the integrity monitoring algorithm. Full article

Multi-Object Tracking (MOT) is a fundamental research topic in the field of computer vision, with broad application potential in unmanned aerial vehicle (UAV) videos. However, existing methods still face significant challenges in detection discriminability and identity association stability due to the small scale and weak appearance of objects under aerial viewpoints, as well as complex background interference. To address these issues, we propose an Edge-Graph Enhanced Network (EGEN) for UAV aerial MOT, aiming to improve the performance of small object detection (SOD) and tracking in complex scenes. The framework follows a one-step tracking paradigm and consists of three main components: object detection, embedding feature extraction, and data association. In the detection stage, we design an Edge-Guided Gaussian Enhancement Module (EGGEM), which models edge relationships between objects and backgrounds from a global perspective and selectively enhances Gaussian features guided by edge information, thereby strengthening key structural features of small objects while suppressing background interference. In the embedding feature extraction stage, we develop a Graph-Guided Embedding Enhancement Module (GGEEM), which explicitly represents re-identification (ReID) embeddings as a graph structure and jointly models nodes and their neighborhood relationships to fully capture inter-object associations and enhance embedding discriminability. In the data association stage, we introduce a hierarchical two-stage association strategy to match objects with different confidence levels separately, improving tracking stability and robustness. Extensive experiments on the VisDrone, UAVDT, and self-constructed WildDrone datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both SOD and MOT, demonstrating strong generalization and practical applicability. Full article

Intelligent transportation systems (ITSs) are crucial for modern traffic management and law enforcement. This paper addresses the challenge of monitoring and managing extensive vehicle traffic in large cities like Lahore, Pakistan. We propose a deep learning based ITS utilizing Vision Transformers combined with convolutional feature extraction to accurately identify vehicle type, color, make/model, and license plates. Experiments were conducted on a comprehensive dataset collected from multiple checkpoints across Lahore under varying environmental conditions. Our proposed model achieved high accuracy rates: 98.0% for vehicle type classification, 96.0% for color detection, 95.0% for make/model identification, and 89.0% for license plate recognition. These results demonstrate the system’s potential to significantly enhance traffic management and road safety and support law enforcement operations in developing urban environments. Full article

Urban tunnel portals constitute critical safety zones for autonomous vehicles, where abrupt luminance transitions, shortened sight distances, and densely distributed structural and traffic elements pose considerable challenges to perception reliability. Existing driving scenario datasets are rarely tailored to tunnel environments and have not quantitatively evaluated how specific infrastructure components influence perception latency in autonomous systems. This study develops a requirement-driven framework for the identification and sensitivity ranking of information perception elements within urban tunnel portals. Based on expert evaluations and a combined function–safety scoring system, nine key elements—including road surfaces, tunnel portals, lane markings, and vehicles—were identified as perception-critical. A “mandatory–optional” combination rule was then applied to generate 48 logical scene types, and 376 images after brightness (30–220 px), blur (Laplacian variance ≥ 100), and occlusion filtering (≤0.5% pixel error) were obtained after luminance and occlusion screening. A ResNet50–PSPNet convolutional neural network was trained to perform pixel-level segmentation, with inference rate adopted as a quantitative proxy for perceptual sensitivity. Field experiments across ten urban tunnels in China indicate that the model consistently recognized road surfaces, lane markings, cars, and motorcycles with the shortest inference times (<6.5 ms), whereas portal structures and vegetation required longer recognition times (>7.5 ms). This sensitivity ranking is statistically stable under clear, daytime conditions (p < 0.01). The findings provide engineering insights for optimizing tunnel lighting design, signage placement, and V2X configuration, and offers a pilot dataset to support perception-oriented design and evaluation of urban tunnel portals in semi-enclosed environments. Unlike generic segmentation datasets, this study quantifies element-specific CNN latency at tunnel portals for the first time. Full article

Vehicle re-identification (re-ID) across disparate sensing modalities remains a fundamental challenge for transportation research. In this work, we introduce a deep multi-view vehicle re-ID framework that leverages Siamese networks to compare pairs of vehicle images and produce matching scores, enabling robust association across drastically different viewpoints such as those from UAVs, surveillance cameras, and ground sensors. The model exploits convolutional neural networks to learn features that remain discriminative under changes in angle, distance, and illumination, supporting more generalizable re-ID performance. As part of this effort, we also developed an automated pipeline to synchronize roadside and UAV video streams, producing a multi-perspective dataset that complements preexisting real collections and a synthetic dataset generated in this study. Together, these contributions advance the capability to re-identify vehicles across wide viewing baselines; establish a foundation for scalable, reproducible research in vehicle re-ID; and open pathways for future applications, such as inferring routine behaviors, movement patterns, and daily habits of the individual associated with the vehicle. Full article

The development of detection and identification technologies for biofouling organisms on marine aquaculture cages is of paramount importance for the automation and intelligence of cleaning processes by Autonomous Underwater Vehicles (AUVs). The present study proposes a methodology for the detection of fouling shellfish on marine aquaculture cages. This methodology is based on an improved version of a symmetric Faster R-CNN: The original Visual Geometry Group 16-layer (VGG16) network is replaced with a 50-layer Residual Network with Aggregated Transformations (ResNeXt50) architecture, incorporating a Convolutional Block Attention Module (CBAM) to enhance feature extraction capabilities; In addition, the anchor box dimensions must be optimised concurrently with the Intersection over Union (IoU) threshold. This is to ensure the adaptation to the scale of the object; combined with the Multi-Scale Retinex with Single Scale Component and Color Restoration (MSRCR) algorithm with a view to achieving image enhancement. Experiments demonstrate that the enhanced model attains an average precision of 94.27%, signifying a 10.31% augmentation over the original model whilst necessitating a mere one-fifth of the original model’s weight. At an intersection-over-union (IoU) value of 0.5, the model attains a mean average precision (mAP) of 93.14%, surpassing numerous prevalent detection models. Furthermore, the employment of an image-enhanced dataset during the training of detection models has been demonstrated to yield an average precision that is 11.72 percentage points higher than that achieved through training with the original dataset. In summary, the technical approach proposed in this paper enables accurate and efficient detection and identification of fouling shellfish on marine aquaculture cages. Full article

Unmanned Aerial Vehicle (UAV)-based inspection of transmission line insulators faces significant challenges due to complex backgrounds, variable imaging conditions, and diverse defect characteristics. Existing deep learning approaches often fail to balance detection accuracy with computational efficiency for edge deployment. This paper presents MCP-YOLO (Multi-scale Complex-background Pruned YOLO), a lightweight yet accurate detection framework specifically designed for real-time insulator defect identification. The proposed framework introduces three key innovations: (1) MS-EdgeNet module that enhances multi-granularity edge features through grouped convolution, improving detection robustness in cluttered environments; (2) Dynamic Feature Pyramid Network (DyFPN) that combines dynamic upsampling with re-parameterized multi-branch architecture, enabling effective multi-scale defect detection; (3) Auxiliary detection head that provides additional supervision during training while maintaining inference efficiency. Furthermore, Group SLIM pruning is employed to achieve model compression without sacrificing accuracy. Extensive experiments on a real-world dataset of 3091 UAV-captured images demonstrate that MCP-YOLO achieves 92.1% mAP@0.5, 90.5% precision, and 89.0% recall, while maintaining only 8.65 M parameters. Compared to state-of-the-art detectors, the proposed method achieves superior detection performance with significantly reduced computational overhead, reaching 250 FPS inference speed. The model size reduction of 37.3% from the baseline, coupled with enhanced detection capabilities, validates MCP-YOLO’s suitability for practical deployment in automated power grid inspection systems. Full article

This study proposes a methodological approach to the redesign of a 1980s vehicle, the Lancia Beta HPE, integrating the TRIZ (Theory of Inventive Problem Solving) and the Industrial Design Structure (IDeS) frameworks within the design process. The redesign process focused on both the external morphology of the vehicle and its propulsion system, aligning the outcome with contemporary trends in market evolution, societal shifts, and environmental considerations. The objective of the project was to reinterpret stylistic elements that were typical of 1980s automotive design through a contemporary lens, while incorporating characteristics of the current aesthetic of electric vehicles (EVs). A pivotal element of the research involved a comparative stylistic analysis of past and present vehicle design languages. This facilitated the identification of design guidelines for adapting formal and stylistic details to the electric mobility paradigm, with emphasis on contemporary aesthetics and energy efficiency. The transition from internal combustion to electric propulsion necessitated a comprehensive re-evaluation of the vehicle’s key exterior features, encompassing the front end, body shape, and lighting systems, in order to reflect a novel ecological identity and convey technological advancement. In order to inform stylistic choices, an in-depth exploration of electric propulsion principles was conducted, leveraging AI-based tools such as GPT to support TRIZ-guided problem-solving. Full article

The article addresses the problem of modelling instantaneous CO₂ emissions from a specific motor vehicle equipped with an internal combustion engine. The article’s concept is based on a review of current research, which led to the identification of a list of variables essential to constructing the numerical model. Data was collected through recording selected vehicle parameters during test drives using the OBD diagnostic interface. The article describes the model development process and presents the results of CO₂ emission modelling using MLP neural networks. The performance of various architectures was examined, considering the number of hidden layers (1, 2, 3), the number of neurons in each layer (from 10 to 267), and different activation functions (such as sigmoid, hyperbolic tangent, and ReLU). Consistency in the values of the MSE, RMSE, and MAE indicators during both validation and testing phases demonstrates the accuracy of the models. High R² values of around 0.8 confirm that MLP networks can effectively model CO₂ emissions from motor vehicles. Full article

Ginkgo biloba L. plays an important role in biodiversity conservation. Accurate identification of Ginkgo in forest environments remains challenging due to its visual similarity to other broad-leaved species during the green-leaf period and to species with yellow foliage during autumn. In this study, we propose a novel two-stage segment-then-classify (STC) strategy to improve the accuracy of Ginkgo identification from unmanned aerial vehicle (UAV) imagery. First, the Segment Anything Model (SAM) was fine-tuned for canopy segmentation across the green-leaf stage and the yellow-leaf stage. A post-processing pipeline was developed to optimize mask quality, ensuring independent and complete tree crown segmentation. Subsequently, a ResNet-101-based classification model was trained to distinguish Ginkgo from other tree species. The experimental results showed that the STC strategy achieved significant improvements compared to the YOLOv8 model. In the yellow-leaf stage, it reached an F1-score of 92.96%, improving by 24.50 percentage points over YOLOv8. In the more challenging green-leaf stage, the F1-score improved by 31.27 percentage points, surpassing YOLOv8’s best performance in the yellow-leaf stage. These findings demonstrate that the STC framework provides a reliable solution for high-precision identification of Ginkgo in forest ecosystems, offering valuable support for biodiversity monitoring and forest management. Full article