Search Results (120)

Small-object details in high-resolution unmanned aerial vehicle (UAV) imagery are weakened when wide-area scenes are resized for detector input. Increasing input resolution or exhaustively processing local regions can recover spatial detail, but allocate computation without distinguishing regional value after global detection. This paper proposes MRU-YOLO, a selective local re-observation framework guided by marginal re-observation utility (MRU), which measures the expected detection benefit of reprocessing a candidate region after one global forward pass. MRU-YOLO constructs prediction-conditioned states for nine candidate regions from global detections and region geometry. A learned utility regressor ranks the candidates and selects the two highest-ranked regions for local inference. Source-aware fusion integrates complementary global and local predictions while resolving cross-source conflicts. The pipeline requires no modification to the detector backbone, neck, or detection head. Across three independent runs, MRU-YOLO reached mean mAP50–95 values of 41.82% on SeaDronesSee ODv2 and 21.72% on VisDrone2019-DET, improving YOLO11n-640 by 2.32 and 3.28 percentage points, respectively. Class-wise AP50–95 improved in four of five maritime categories and nine of ten urban categories, while the remaining urban category was effectively unchanged. Learned selection also achieved higher utility capture and normalized discounted cumulative gain at rank 2 (NDCG@2) than predicted density on both datasets. Under batch-1 FP16 inference on an NVIDIA GeForce RTX 3090, the end-to-end pipeline achieved 30.86 FPS on SeaDronesSee ODv2 and 33.24 FPS on VisDrone2019-DET. MRU-YOLO concentrates local inference on regions with the highest expected detection contribution under a fixed local-processing budget. Full article

In the context of the large-scale integration of high-proportion renewable energy into power grids, Power Conversion Systems (PCS) and Static Var Generator (SVG), as the core power electronic devices for ensuring grid frequency stability and power quality, demand high-level safety and reliability. To tackle challenges such as the wide range of defect sizes in PCS and SVG, the low recognition accuracy for microscopic fuzzy defects, and complex background interference, this paper presents a lightweight and high-precision defect recognition model (RD-YOLO) based on the latest YOLOv11 benchmark. First, an improved Mosaic algorithm is introduced. This algorithm utilizes conflict relationship tables to preserve physical context semantics during traditional non-discriminative data augmentation. Second, to surmount the limitations of scale-aware feature extraction, the YOLOv11 is re-engineered within the backbone network by integrating a Res2Net multi-scale cascaded mechanism. This enhances the network’s capacity to capture both fine-grained defect features and large-scale defect boundaries. Third, Focal Loss is employed for difficult sample detection. Nonlinear gradient modulation is utilized to guide the model to focus on ambiguous defect edges. Finally, the Soft-NMS post-processing strategy significantly enhances the regression accuracy in densely corroded regions. Experimental validation on a self-developed dataset consisting of 8500 high-resolution PCS and SVG defect images reveals that the enhanced RD-YOLO attains an average precision of 89.6% and a frame inference rate of 98 FPS (in RTX 3090), offering robust technical support for intelligent visual maintenance in renewable energy facilities. Full article

The accelerated pace of urbanization across the Global South calls for precise, real-time building footprint data to underpin effective urban governance and enhance disaster resilience. Conventional mapping approaches, however, suffer from inefficiency in data acquisition and updating. Although Volunteered Geographic Information (VGI) provides a crowdsourced solution for geospatial data collection, it is commonly hindered by significant heterogeneity—manifested in inconsistent data completeness, positional inaccuracies and poor topological consistency across different datasets. To address these critical limitations, this study proposes an intelligent geospatial agent framework designed to autonomously fuse building data from multiple heterogeneous sources, including VGI, Very High-Resolution (VHR) satellite imagery, and Light Detection and Ranging (LiDAR) data. This study’s core innovative points are embodied in three key modules: a supervised VGI quality verification module that leverages the Random Forest model to evaluate the reliability of individual building feature elements; a hybrid building extraction engine which integrates LiDAR data with the Segment Anything Model (SAM) to realize zero-shot building extraction; and a cognitive rule engine that adopts Multi-Criteria Decision Analysis (MCDA) for the intelligent resolution of spatial conflicts. Comprehensive validation experiments were conducted in two African cities experiencing rapid urbanization—Kigali and Dar es Salaam. The results show that the proposed framework boosts data completeness by more than 29% and attains a fused dataset F1-Score of 0.919, effectively converting incomplete VGI data into a geospatial resource with near-official authoritative quality. Full article

Owing to the stringent spatio-temporal coupling and kinematic constraints, the task allocation problem for heterogeneous unmanned aerial vehicle (UAV) swarms is generally regarded as an NP-hard problem. To address this, this paper proposes the Sequentially Extended Consensus-Based Bundle Algorithm (SECBBA), a deadlock-free distributed scheduling framework. First, a multi-task allocation model is established by incorporating constraints associated with payload resources, task scheduling, and threat zone. Subsequently, the conventional Consensus-Based Bundle Algorithm (CBBA) is extended through the integration of a deadlock detection and resolution mechanism based on directed graph Depth-First Search (DFS), thereby guaranteeing conflict-free task allocation. Furthermore, a sequential hierarchical strategy is introduced to transform global temporal dependencies into tractable soft time-window constraints. Finally, to ensure physical feasibility, Dubins curves are tightly coupled with the allocation process, enabling nonholonomic path planning for fixed-wing UAVs. Simulation results demonstrate that SECBBA reduces global task costs by 13.3%, 22.7%, and 39.4% compared to the Consensus-Based Bundle Algorithm with Temporal Consistency Constraints (CBBA-TCC), Improved Genetic Algorithm (IGA) and Q-Learning baselines, respectively. It consistently maintains performance advantage of 9.8%, 23.2% and 19.0% under variable weights with high computational efficiency, significantly enhancing swarm timeliness in complex, coupled multi-task scenarios. Full article

This paper presents a distributed coordination framework for simultaneous multi-target tracking using a mobile wireless sensor network (MWSN) based on discrete-event-system principles. The proposed framework employs a finite-state-machine architecture, where autonomous mobile sensors sequentially process detection and tracking events. Unlike passive tracking approaches that react to target loss after it occurs, the proposed strategy implements predictive handover through Extended-Kalman-Filter-based uncertainty propagation. This enables sensors to anticipate target loss and to reposition auxiliary sensors in advance, acquiring targets along their predicted trajectories. A bidding-based allocation mechanism coordinates sensor assignments by evaluating four competing objectives: network preservation, spatial proximity to handover points, temporal mission feasibility, and estimation uncertainty. The proposed framework integrates four components: EKF-convergence-triggered proactive handover, multi-objective competitive bidding, distributed min–max conflict resolution, and fusion-driven proportional navigation. Unlike existing methods, auxiliary sensors navigate using confidence-weighted EKF estimates shared by neighboring sensors rather than their own measurements. An ablation study over ten Monte Carlo trials confirms that each component contributes independently, with EKF-based predictive triggering identified as the dominant performance driver. Full article

Unmanned Aerial Vehicle (UAV) image object detection holds significant application value in the low-altitude economy, traffic monitoring, intelligent agriculture, and disaster rescue. However, due to the top-down perspective, UAV images typically suffer from challenges such as small target scales, dense object distribution, severe occlusions, and complex backgrounds. These issues often limit the recall and localization accuracy of general-purpose detectors when they are directly applied to UAV small-object detection scenarios. To address these aforementioned challenges, this paper proposes an Adaptive Dynamic Aggregation YOLO network, termed ADA-YOLO. The novelty of ADA-YOLO lies in its highly efficient combinatorial design specifically tailored for UAV small object detection, while retaining the efficient backbone of YOLOv8, we systematically reconstruct the neck and detection head to improve accuracy. Specifically, a high-resolution P2 detection branch is incorporated to construct a P2–P5 multi-scale prediction structure. Furthermore, the lightweight DySample dynamic upsampling module is adopted to replace traditional upsampling methods, and an Adaptive Spatial Feature Fusion (ASFF) mechanism is introduced to alleviate semantic conflicts and noise interference during multi-scale feature fusion. This synergistic combination explicitly addresses multi-scale representation challenges and enhances small-object detection performance in complex scenes. Comparative experiments with the baseline YOLOv8n on the VisDrone2019 dataset demonstrate that ADA-YOLO achieves an improvement of 11.3% in mAP@0.5 and 8.2% in mAP@0.5:0.95. The improved model achieves these performance gains with a modest parameter increase and acceptable computational complexity. Finally, ablation experiments further validate the effectiveness of each individual module and their synergistic gains. Full article

Recent advances in roadside sensing technologies, including camera-based systems, radar, and LiDAR, have enabled high-resolution sampling of vehicle trajectories, overcoming the temporal and spatial limitations of traditional data collection methods. Among these, LiDAR sensing has been widely adopted for traffic monitoring and surrogate safety analysis due to its high spatial accuracy and temporal resolution. However, sensor noise and occlusion in roadside LiDAR frequently introduce tracking point offsets and trajectory discontinuities, reducing the reliability of vehicle counts, traffic state estimation, and conflict analysis. To address these challenges, this study proposes a post-processing method based on time–space analysis to detect and correct occlusion-induced trajectory discontinuities. By exploiting the inherent spatiotemporal consistency of vehicle movements, the proposed approach identifies fragmented trajectories, reconstructs continuous vehicle paths, and recovers realistic traffic patterns. Validated on real-world LiDAR data collected at an urban intersection in Reno, Nevada, across four 30 min traffic periods covering AM and PM peak conditions on weekdays and weekends, the proposed method achieves an average precision of 0.989 and an average F1-score of 0.948, outperforming IMM, GNN-RM, and HMM + Viterbi benchmark methods. Count accuracy improved from 85.5% to 97.4% across all evaluated periods, confirming the method’s effectiveness under occlusion conditions. Full article

Small object detection in UAV aerial imagery poses significant challenges due to sparse pixel representation and ambiguous object boundaries. Through systematic analysis, we identify three critical degradation stages during forward propagation in deep detection networks: edge attenuation during feature extraction, semantic conflict during feature fusion, and detail loss during feature reconstruction. Existing methods address these stages in isolation or implicitly, lacking collaborative and stage-aware repair strategies. To address this issue, we propose EAGLE-DET, a novel detection framework based on sparse multi-scale attention and refined transformation. Specifically, the framework comprises three core modules: (1) the Cross-stage Multi-resolution Edge Enhancement Network (CMENet), which preserves small object edge representations via adaptive high-low frequency decomposition; (2) the Attention-guided Multi-scale Feature Fusion Network (AMFFN), which resolves cross-scale semantic conflicts through pyramidal sparse attention and multi-scale spatial decoupling; (3) the Enhanced Upsampling with Channel Bridging and Spatial Coordination module (EUCBSC), which recovers spatial detail fidelity via bidirectional channel shift mixing. Extensive experiments on three benchmark datasets—VisDrone-2019, UAVDT, and DOTA1.0—demonstrate the effectiveness of EAGLE-DET, which achieves improvements of 4.5% AP50 and 2.9% AP50:95 on VisDrone-2019 over the baseline, while maintaining inference at 71.7 FPS, achieving an optimal accuracy–efficiency trade-off. Full article

Salient object detection in optical remote sensing images remains challenging due to complex backgrounds, blurred boundaries, small objects, unstable foreground–background contrast, and dense object distributions. Existing convolution-based methods are effective at modeling local structures, but they are limited in capturing long-range dependencies, whereas Transformer-based approaches usually incur substantial computational cost when handling high-resolution remote sensing imagery. To address these issues, this paper proposes EGMamba-Net, an edge-guided global–local collaborative network for salient object detection in optical remote sensing images. Specifically, a hybrid global–local backbone is first constructed to preserve shallow texture, edge, and geometric details while introducing Mamba-based global modeling in deeper stages for efficient long-range dependency representation. An Edge Prior Enhancement Module (EPEM) is then designed to explicitly extract boundary priors from shallow features and refine feature representations through edge-guided modulation. To alleviate the representation conflict between global semantics and local details, a Global–Local Interaction Module (GLIM) is further developed, where convolutional local modeling and Mamba-based global modeling interact through cross-gating for complementary feature learning. Moreover, a Region-Adaptive Routing Decoder (RARD) is introduced to dynamically assign different refinement paths according to regional saliency response, boundary intensity, and contextual complexity, thereby improving the recovery of small, low-contrast, and densely distributed objects. In addition, a Difficulty-Aware Joint Loss (DAJL) is designed to enhance optimization on boundary regions and hard samples, improving robustness under challenging conditions. Extensiveexperiments on ORSSD, EORSSD, and ORSI-4199 datasets demonstrate the superiority of the proposed method. In particular, on the more challenging EORSSD dataset, EGMamba-Net achieves 0.9389 S-measure, 0.8972 max F-measure, and 0.0066 MAE. Compared with the representative remote-sensing method DAF-Net, it improves S-measure and max F-measure by 0.0223 and 0.0358, respectively, indicating stronger capability in background suppression, structural preservation, and boundary recovery. Full article

Unsignalized intersections involve complex interactions among heterogeneous road users and are associated with elevated safety risks. Although surrogate safety measures derived from high-resolution trajectories enable proactive safety assessment, such data are not widely available in routine monitoring systems, which often provide only coarse-grained traffic observations. This study examines how the inferability of surrogate safety information changes as the available traffic data become progressively coarser. Using the high-resolution inD dataset, we implement a controlled feature degradation framework across three nested levels of data granularity and develop intersection-specific models for three tasks: critical conflict detection, dominant direction classification, and vulnerable road user (VRU) involvement identification. Model performance and changes in variable importance are evaluated using PR-AUC and SHAP analysis. The results show clear task-dependent degradation. Models based on high-granularity data achieve strong overall performance, with an average PR-AUC above 0.88. Dominant direction classification remains relatively robust as data granularity decreases, with PR-AUC declining from 0.970 to 0.893, whereas VRU involvement identification deteriorates substantially, from 0.991 to 0.697. The results further indicate that vehicle-based traffic variables retain meaningful predictive value for conflict detection and direction classification but are insufficient for reliable inference of VRU-related risk. Interpretability analysis shows a progressive shift in model reliance from kinematic interaction variables to coarser exposure-related and structural descriptors as observability decreases. These findings clarify the relationship between data granularity and task-dependent surrogate safety inference at unsignalized intersections. Full article

The large-scale operation of multiple fixed-wing unmanned aerial vehicles (UAVs) in shared airspace requires efficient flight conflict detection and resolution to ensure aviation safety. However, existing research predominantly lacks collaborative optimization of multi-dimensional maneuver recommendations and struggles with dynamic priority allocation in complex multi-UAV scenarios, leaving a critical gap in the field. To bridge this gap, this paper proposes a Complex Network-Based Multi-UAV Conflict Resolution (NCR) method, which first constructs a three-dimensional (3D) flight conflict detection and resolution model for fixed-wing UAVs. The core innovation lies in mapping dynamic multi-UAV conflict scenarios into a flight conflict network, where UAVs serve as nodes and conflict urgencies act as edge weights. By calculating network and node robustness, the method accurately identifies key UAVs requiring immediate maneuver. Subsequently, taking the minimum variation in the velocity vector as the core objective, NCR iteratively searches for optimal resolution recommendations for these key UAVs using an improved fitness function until the conflict network collapses. Simulation and comparative experiments in 3D airspace, including evaluations against serial-based resolution, random-recommendation resolution, and a classical reactive baseline, demonstrate that NCR efficiently resolves multi-UAV conflicts with minimal trajectory deviations and fewer maneuvering UAVs. Furthermore, a macro-micro bi-level validation architecture based on a six-degree-of-freedom (6-DOF) aerodynamic platform is introduced to verify the physical executability of the proposed strategies. Results demonstrate that by incorporating a dynamic aerodynamic compensation margin, the inevitable trajectory tracking deviations caused by system inertia are enveloped within the safety threshold, ensuring absolute flight safety in engineering practice. Notably, as conflict complexity increases, NCR exhibits prominent advantages in reducing velocity variation costs, minimizing the number of maneuvering UAVs, and avoiding unnecessary trajectory deviations. Full article

LiDAR is widely used in robotics because it provides reliable range data for navigation and mapping. On a small embedded robot, however, there is a practical conflict between scan resolution and reaction speed. Dense scans provide better environmental detail, but they take too long for fast obstacle avoidance, whereas sparse scans are faster but can miss obstacles if the spacing between adjacent rays is too large. This paper presents an Interleaved Sparse–Dense Scanning method for a servo-actuated single-point time-of-flight LiDAR mounted on an embedded mobile robot. A dense nested pan–tilt sweep is used for three-dimensional mapping, while a sparse forward scan is inserted between dense rows for obstacle detection and motion control. A geometric model is derived to relate sensing range, beam spacing, and minimum detectable object width. That model is then linked to zone-based safety constraints and to the distance the robot can travel before the next obstacle update. For the robot used in this study, the resulting sparse configuration is a 7-point forward scan over a 180° field of view. Experiments in a real indoor environment showed that this configuration reliably detected target blocking obstacles and reduced decision latency by 6.2 times compared with waiting for a complete dense scan before each navigation update. The proposed method provides a practical balance between reactive obstacle avoidance and useful 3D mapping on a low-cost embedded platform, while making the system’s timing and safety limits explicit. Full article

Design coordination is a critical process for avoiding spatial conflicts and ensuring design alignment in large-scale construction projects. While Building Information Modelling (BIM) tools have improved coordination through 3D model integration and clash detection, inefficiencies persist due to fragmented workflows, frequent tool switching, and challenges with issue documentation. Cloud-based BIM collaboration tools offer a promising alternative by enabling real-time model sharing, centralized issue tracking, and enhanced stakeholder communication. However, empirical evidence on their practical implementation and effects on coordination processes remains limited. Unlike prior cloud-BIM reviews that focus on technical capabilities or adoption barriers in isolation, this study provides an empirically grounded framework that links specific tool features to observable workflow changes and their downstream impacts on coordination outcomes. This study investigates the impact of cloud-based BIM collaboration tools on the design coordination process, with a focus on issue identification, resolution, and documentation. A framework was developed using a mixed-methods approach comprising action research, an ethnographic case study, and comparative analysis of three large infrastructure projects to categorize workflow changes resulting from tool adoption. The findings indicate that cloud-based BIM tools streamline coordination by reducing manual transitions, automating documentation, and improving information accessibility during meetings. Nevertheless, their effectiveness is constrained by organizational structures and contract limitations. This study provides a validated process-change framework and practical insights for engineering managers seeking to align digital collaboration tools with project delivery strategies, contributing to both theory and practice in BIM-based coordination and digital transformation in the AEC industry. Full article

The remain well clear (RWC) function of a detect-and-avoid (DAA) system provides guidance to a remote pilot (RP) of a remotely piloted aircraft to prevent a conflict from developing into a collision hazard. The ACAS Xu standard is a decision support system that uses RWC bands to advise a RP which headings to avoid. A recent A* DAA system is a resolution support system that advises a RP which route to take. The objective of this study is to achieve structured feedback by professional RPs on the horizontal RWC guidance of both systems. Nine RPs participated in on-line experiments, where they were shown videos of DAA displays of encounter scenarios between two aircraft. At various stages the RPs were asked for their opinion about transparency, pilot manoeuvring, situation awareness, display orientation, risk perception, competence, trust, and overall system preference. The results show that the scores for competence, trust and pilot manoeuvring were significantly higher, and the score for perceived risk was significant lower for the RWC route guidance. Overall, 89% of the RPs preferred the RWC route guidance, while one RP had no preference. An implication of the uncertainty in pilot behaviour is that ACAS Xu model-based optimisation may provide suboptimal RWC guidance strategies, while the A* DAA optimisation can be managed effectively. Full article

Remote sensing image change detection serves as a core technology in environmental monitoring. While the widespread availability of high-resolution remote sensing data provides essential support for detailed detection, it also presents technical challenges such as complex terrain interference, subtle change recognition, and large-scale scene processing. Current mainstream deep learning methods, despite their global modeling advantages, demonstrate limitations in cross-temporal fine-grained correlation mining and are prone to ambiguous edge localization in changing areas due to spatial detail loss. This paper proposes a high-resolution change detection network (TiBT-Net) that integrates bi-temporal space enhancement with token interaction. The model achieves precise change detection through dynamic token interaction and adaptive enhancement (TDIAE), utilizing deformable attention to capture semantic correlations. It constructs a Bi-Temporal Information Interaction Module (BTII) that enhances spatial details via multi-scale convolutions and channel attention, while introducing a delayed fusion mechanism (DLF) to dynamically balance dual-branch feature contributions. Experimental validations on LEVIR-CD, WHU-CD, and DSIFN-CD datasets achieved F1 scores of 90.38%, 86.74% and 96.28%, respectively, with Intersection-Union Ratios (IoU) of 82.46%, 76.59% and 92.82%. The overall accuracy (OA) reached up to 99.04%. This model effectively resolves the integration conflict between semantic information and spatial details, providing a reliable technical solution for high-precision change detection in complex scenarios. Full article