Search Results (25)

This paper proposes a prototype-level hierarchical visual–sensor framework for monitoring the Zamioculcas houseplant in complex indoor environments and supporting adaptive care-mode selection. The proposed framework combines a two-level visual pipeline, consisting of YOLO-based target plant detection and MobileViT-S-based leaf-condition classification, with a Plant Health Index (PHI) and a rule-based decision-support module for integrating visual and IoT-derived indicators. For the detection task, YOLOv8, YOLO12, and YOLO26 were compared, with YOLO26 showing the most balanced performance among the evaluated implementations. To improve robustness in real indoor scenes, negative training samples were added; this reduced the image-level false alarm rate on an independent negative-scene test set from 50.7% to 10.0% and increased specificity from 49.3% to 90.0%. For the second visual level, MobileViT-S achieved an accuracy of 0.9857 and an F1-score of 0.9857 on the independent cropped leaf test subset. To reduce the dependence of this result on a single data split, an additional 5-fold cross-validation experiment was conducted on the full cropped leaf dataset of 847 images, resulting in an accuracy of 0.9858 ± 0.0068 and an F1-score of 0.9853 ± 0.0070. To further address plant-level generalization, an additional unseen-plant validation subset of 60 newly collected cropped leaf images was evaluated, and MobileViT-S achieved an accuracy of 0.9500 and an F1-score of 0.9499. These results support the stability of the leaf-condition classifier within the available data, although larger external validation with strict plant-level and session-level separation remains necessary. In addition, an Arduino-based module-level validation was conducted using a capacitive soil-moisture sensor to verify the proposed sensor-based and Vision–IoT decision rules. The experiment demonstrated that the rule-based layer can distinguish dry, normal, and wet soil states and select conservative care actions depending on both soil moisture and visual-condition input. A brief real-time camera–sensor communication test further confirmed that live camera input, Arduino-based soil-moisture sensing, PHI computation, and care-mode selection can be connected within one decision-support pipeline. The proposed PHI and care-mode selection module are therefore presented as a formalized decision-support layer rather than as a fully validated autonomous irrigation system. Further calibration, actuator integration, and closed-loop validation remain necessary before practical autonomous deployment. Full article

The inherent redundancy in vehicle sensor data, coupled with constrained onboard resources and stringent latency requirements, renders traditional bit-oriented transmission paradigms inefficient for autonomous-driving perception tasks. Semantic communication offers a promising direction by shifting the focus from bit-level fidelity to task-level information delivery. In this paper, we propose a unified framework that integrates hierarchical transmission and online scheduling for Internet of Vehicles (IoV)-oriented collaborative perception. The proposed hierarchy separates information into two complementary layers: a coarse metadata layer (object bounding boxes) for latency-critical awareness, and fine-grained visual semantics (multi-scale region-of-interest (ROI) patches) for perception-intensive tasks. We formulate an online scheduling problem that jointly exploits Age of Information (AoI) and Channel State Information (CSI) to dynamically decide what to transmit and at what fidelity under per-frame budget constraints. To address cross-scheme fairness, we report resource utilization under a fixed kbps/fps physical budget and evaluate robustness using a combination of a lightweight task-proxy metric and COCO-style Average Recall (AR100) under ROI-only evaluation. The hierarchical transmission architecture, combined with AoI awareness, reduces global semantic staleness by approximately 78%. The Lyapunov-based online scheduler enables intelligent, signal-to-noise ratio (SNR)-adaptive switching between coarse and fine semantic levels, ensuring robust perception under varying channel quality. Under strict physical-budget constraints and unreliable channel conditions, joint source-channel coding (JSCC) exhibits significantly stronger task robustness than conventional schemes: at 0 dB SNR, the task-proxy detection rate improves by nearly 47 percentage points over the uncoded baseline. Full article

Infrared and visible image fusion aims to integrate complementary information from heterogeneous sensors for remote sensing and Earth-observation applications. To achieve a better balance between global contextual modeling and local structural preservation, we propose MSF-Net, a multi-scale frequency-aware fusion network with a hierarchical design. The proposed framework consists of two main stages: multi-scale feature extraction with frequency-domain interaction and hierarchical cross-modal fusion. Specifically, a hybrid spatial-frequency encoding block (HSFEB) is designed as the basic building unit, which combines a spatial-frequency interaction module (SFIM) for global context aggregation in the frequency domain and a structure-guided feature refinement module (SGFRM) for preserving local structural details. In addition, a hierarchical feature fusion module (HFFM) is introduced to progressively integrate cross-modal and cross-scale features in a coarse-to-fine manner. A joint loss function, composed of intensity and structural constraints, is adopted to supervise the fusion process. Extensive experiments on three public benchmarks, MSRS, M³FD, and TNO, demonstrate that MSF-Net achieves superior performance over nine SOTA methods in both qualitative and quantitative evaluations. The results show that the proposed method effectively enhances thermal targets, preserves structural details, and maintains good visual naturalness under diverse remote-sensing scenarios. Full article

Infrared and visible image fusion is a critical technology for enhancing the all-weather perception capabilities of autonomous driving systems. However, the inherent physical parallax of vehicle-mounted sensors combined with motion-induced vibrations makes it difficult to achieve strict alignment between the source images. Direct fusion of such misaligned pairs leads to ghosting artifacts, which significantly compromises driving safety. To address this challenge, this paper proposes a cascaded deep fusion framework tailored for autonomous driving scenarios. A dual-modal perception dataset is first constructed, incorporating realistic physical parallax and non-rigid deformations. Subsequently, a decoupled strategy is established, characterized by geometric correction followed by semantic fusion: the Static-Feature Recursive Registration (SFRR) network is utilized to explicitly correct the spatial misalignments caused by parallax, thereby establishing geometric consistency; then, the Hierarchical Invertible Block Fusion (HIBF) network achieves lossless integration of cross-modal features by combining spatial frequency separation with invertible interaction techniques. Experimental results demonstrate that the proposed method outperforms representative algorithms across several metrics, including Mutual Information (MI), Visual Information Fidelity (VIF), Structural Similarity (SSIM), and Correlation Coefficient (CC), producing high-quality fused images with clear structural definitions. Full article

4D millimeter-wave radar provides high-precision ranging capability and exhibits strong robustness under adverse weather and low-visibility conditions, but its point clouds are relatively sparse and suffer from severe elevation-angle measurement noise. Monocular cameras, by contrast, provide rich semantic information and high recall, yet are fundamentally limited by scale ambiguity. To exploit the complementary characteristics of these two sensors, this paper proposes a radar-camera fusion 3D multi-object tracking framework that does not rely on complex 3D annotated data. First, on the radar signal-processing side, a Gaussian distribution-based adaptive angle compression method and IMU-based velocity compensation are introduced to effectively suppress measurement noise, and an improved DBSCAN clustering scheme with recursive cluster splitting and historical static-box guidance is employed to generate high-quality radar detections. Second, a disparity-domain metric depth recovery method is proposed. This method uses filtered radar points as sparse metric anchors, performs robust fitting with RANSAC, and applies Kalman filtering for temporal smoothing, thereby converting the relative depth output of the visual foundation model Depth Anything V2 into metric depth. Finally, a hierarchical fusion strategy is designed at both the detection and tracking levels to achieve stable cross-modal state association. Experimental results on a self-collected dataset show that the proposed method achieves an overall MOTA of 77.93%, outperforming single-modality baselines and other comparison methods by 11 to 31 percentage points. This study provides an effective solution for low-cost and robust environment perception in complex dynamic scenarios. Full article

Although underwater gliders are highly energy-efficient platforms capable of long-duration and large-scale ocean observation, their lack of self-propulsion requires external assistance for recovery upon mission completion. In harsh and dynamic marine environments, reliably detecting the glider and accurately estimating its three-dimensional position are critical to ensuring the recovery operations are safe and efficient. This paper proposes a perception framework based on deep learning to detect underwater glider hulls and estimate their three-dimensional relative positions using camera–sonar multi-sensor fusion. This approach integrates a hierarchical convolutional neural network (CNN) vision encoder and a transformer-based architecture to estimate the glider’s spatial location and heading direction simultaneously. The hierarchical CNN encoder extracts multi-level, semantically rich visual features, thereby improving robustness to visual degradation and environmental disturbances common in underwater settings. Additionally, the transformer incorporates a variable mixture-of-experts (vMoE) mechanism that adaptively allocates expert networks across layers, enhancing representational capacity while maintaining computational efficiency. The resulting pose estimates enable precise, collision-free ROV navigation for automated recovery and onboard sensor inspection tasks. Experimental results, including ablation studies, validate the effectiveness of the proposed components and demonstrate their contributions to accurate glider hull detection and three-dimensional localization. Overall, the proposed framework provides a scalable, reliable perception solution that allows for the safe, autonomous recovery of underwater gliders with an ROV in realistic ocean environments. Full article

The rapid expansion of low-altitude unmanned aerial vehicles demands robust obstacle detection and avoidance systems capable of operating under diverse environmental conditions. This paper proposes a multimodal fusion attention network that integrates visual imagery and Light Detection and Ranging (LiDAR) point cloud data for real-time obstacle perception. The architecture incorporates a bidirectional cross-modal attention mechanism that learns dynamic correspondences between heterogeneous sensor modalities, enabling adaptive feature integration based on contextual reliability. An adaptive weighting component automatically modulates modal contributions according to estimated sensor confidence under varying environmental conditions. The network further employs gated fusion units and multi-scale feature pyramids to ensure comprehensive obstacle representation across different distances. A hierarchical avoidance decision framework translates detection outputs into executable control commands through threat assessment and graduated response strategies. Experimental evaluation on both public benchmarks and a purpose-collected low-altitude obstacle dataset demonstrates that the proposed method achieves 84.9% mean Average Precision (mAP) while maintaining 47.3 frames per second (FPS) on Graphics Processing Unit (GPU) hardware and 23.6 FPS on embedded platforms. Ablation studies confirm the contribution of each architectural component, with cross-modal attention providing the most substantial performance improvement. Full article

All-sky cameras provide continuous hemispherical observations essential for atmospheric monitoring and observatory operations; however, automated classification of sky conditions in tropical environments remains challenging due to strong illumination variability, atmospheric scattering, and overlapping thin-cloud structures. This study proposes EfficientNet-Attention-SPP Multi-scale Network (EASMNet), a physics-aware deep learning framework for robust all-sky scene classification using hemispherical imagery acquired at the Thai National Observatory. The proposed architecture integrates Squeeze-and-Excitation (SE) blocks for radiometric channel stabilization, the Convolutional Block Attention Module (CBAM) for spatial–semantic refinement, and Spatial Pyramid Pooling (SPP) for hemispherical multi-scale context aggregation within a fully fine-tuned EfficientNetB7 backbone, forming a domain-aware atmospheric representation framework. A large-scale dataset comprising 122,660 RGB images across 13 day–night sky-scene categories was curated, capturing diverse tropical atmospheric conditions including humidity, haze, illumination transitions, and sensor noise. Extensive experimental evaluations demonstrate that the EASMNet achieves 93% overall accuracy, outperforming representative convolutional (VGG16, ResNet50, DenseNet121) and transformer-based architectures (Swin Transformer, Vision Transformer). Ablation analyses confirm the complementary contributions of hierarchical attention and multi-scale aggregation, while class-wise evaluation yields F1-scores exceeding 0.95 for visually distinctive categories such as Day Humid, Night Clear Sky, and Night Noise. Residual errors are primarily confined to physically transitional and low-contrast atmospheric regimes. These results validate the EASMNet as a reliable, interpretable, and computationally feasible framework for real-time observatory dome automation, astronomical scheduling, and continuous atmospheric monitoring, and provide a scalable foundation for autonomous sky-observation systems deployable across diverse climatic regions. Full article

Remote sensing image super-resolution (RSISR) aims to reconstruct high-resolution images from low-resolution observations of remote sensing data to enhance the visual quality and usability of remote sensors. Real world RSISR is challenging owing to the diverse degradations like blur, noise, compression, and atmospheric distortions. We propose hierarchical multi-task super- resolution framework including degradation-aware modeling, dual-decoder reconstruction, and static regularization-guided generation. Speciffcally, the degradation-wise module adaptively characterizes multiple types of degradation and provides effective conditional priors for reconstruction. The dual-decoder platform incorporates both convolutional and Transformer branches to match local detail preservation as well as global structural consistency. Moreover, the static regularizing guided generation introduces prior constraints such as total variation and gradient consistency to improve robustness to varying degradation levels. Extensive experiments on two public remote sensing datasets show that our method achieves performance that is robust against varying degradation conditions. Full article

The grid-forming static var generator (SVG) is a key device that supports the stable operation of power grids with a high penetration of renewable energy. The cooling efficiency of its forced water-cooling system directly determines the reliability of the entire unit. However, existing wired monitoring methods suffer from complex cabling and limited capacity to provide a full perception of the water-cooling condition. To address these limitations, this study develops a wireless monitoring system based on multi-source information fusion for real-time evaluation of cooling efficiency and early fault warning. A heterogeneous wireless sensor network was designed and implemented by deploying liquid-level, vibration, sound, and infrared sensors at critical locations of the SVG water-cooling system. These nodes work collaboratively to collect multi-physical field data—thermal, acoustic, vibrational, and visual information—in an integrated manner. The system adopts a hybrid Wireless Fidelity/Bluetooth (Wi-Fi/Bluetooth) networking scheme with electromagnetic interference-resistant design to ensure reliable data transmission in the complex environment of converter valve halls. To achieve precise and robust diagnosis, a three-layer hierarchical weighted fusion framework was established, consisting of individual sensor feature extraction and preliminary analysis, feature-level weighted fusion, and final fault classification. Experimental validation indicates that the proposed system achieves highly reliable data transmission with a packet loss rate below 1.5%. Compared with single-sensor monitoring, the multi-source fusion approach improves the diagnostic accuracy for pump bearing wear, pipeline micro-leakage, and radiator blockage to 98.2% and effectively distinguishes fault causes and degradation tendencies of cooling efficiency. Overall, the developed wireless monitoring system overcomes the limitations of traditional wired approaches and, by leveraging multi-source fusion technology, enables a comprehensive assessment of cooling efficiency and intelligent fault diagnosis. This advancement significantly enhances the precision and reliability of SVG operation and maintenance, providing an effective solution to ensure the safe and stable operation of both grid-forming SVG units and the broader power grid. Full article

To address the limitations of single-sensor perception in inland vessel monitoring and the lack of robustness of traditional tracking methods in occlusion and maneuvering scenarios, this paper proposes a hierarchical multi-target tracking framework that fuses Light Detection and Ranging (LiDAR) data with Automatic Identification System (AIS) information. First, an improved adaptive LiDAR tracking algorithm is introduced: stable trajectory tracking and state estimation are achieved through hybrid cost association and an Adaptive Kalman Filter (AKF). Experimental results demonstrate that the LiDAR module achieves a Multi-Object Tracking Accuracy (MOTA) of 89.03%, an Identity F1 Score (IDF1) of 89.80%, and an Identity Switch count (IDSW) as low as 5.1, demonstrating competitive performance compared with representative non-deep-learning-based approaches. Furthermore, by incorporating a fusion mechanism based on improved Dempster–Shafer (D-S) evidence theory and Covariance Intersection (CI), the system achieves further improvements in MOTA (90.33%) and IDF1 (90.82%), while the root mean square error (RMSE) of vessel size estimation decreases from 3.41 m to 1.97 m. Finally, the system outputs structured three-level tracks: AIS early-warning tracks, LiDAR-confirmed tracks, and LiDAR-AIS fused tracks. This hierarchical design not only enables beyond-visual-range (BVR) early warning but also enhances perception coverage and estimation accuracy. Full article

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems. Full article

Farmland ecosystems present complex pest–predator co-occurrence patterns, posing significant challenges for image-based multitarget recognition and ecological modeling in sensor-driven computer vision tasks. To address these issues, this study introduces a tree-guided Transformer framework enhanced with a knowledge-augmented co-attention mechanism, enabling effective feature extraction from sensor-acquired images. A hierarchical ecological taxonomy (Phylum–Family Species) guides prompt-driven semantic reasoning, while an ecological knowledge graph enriches visual representations by embedding co-occurrence priors. A multimodal dataset containing 60 pest and predator categories with annotated images and semantic descriptions was constructed for evaluation. Experimental results demonstrate that the proposed method achieves 90.4% precision, 86.7% recall, and 88.5% F1-score in image classification, along with 82.3% hierarchical accuracy. In detection tasks, it attains 91.6% precision and 86.3% mAP@50, with 80.5% co-occurrence accuracy. For hierarchical reasoning and knowledge-enhanced tasks, F1-scores reach 88.5% and 89.7%, respectively. These results highlight the framework’s strong capability in extracting structured, semantically aligned image features under real-world sensor conditions, offering an interpretable and generalizable approach for intelligent agricultural monitoring. Full article

Pansharpening fuses multispectral (MS) and panchromatic (PAN) remote sensing images to generate outputs with high spatial resolution and spectral fidelity. Nevertheless, conventional methods relying primarily on convolutional neural networks or unimodal fusion strategies frequently fail to bridge the sensor modality gap between MS and PAN data. Consequently, spectral distortion and spatial degradation often occur, limiting high-precision downstream applications. To address these issues, this work proposes a Hybrid Spectral–Structural Transformer Network (HSSTN) that enhances multi-level collaboration through comprehensive modelling of spectral–structural feature complementarity. Specifically, the HSSTN implements a three-tier fusion framework. First, an asymmetric dual-stream feature extractor employs a residual block with channel attention (RBCA) in the MS branch to strengthen spectral representation, while a Transformer architecture in the PAN branch extracts high-frequency spatial details, thereby reducing modality discrepancy at the input stage. Subsequently, a target-driven hierarchical fusion network utilises progressive crossmodal attention across scales, ranging from local textures to multi-scale structures, to enable efficient spectral–structural aggregation. Finally, a novel collaborative optimisation loss function preserves spectral integrity while enhancing structural details. Comprehensive experiments conducted on QuickBird, GaoFen-2, and WorldView-3 datasets demonstrate that HSSTN outperforms existing methods in both quantitative metrics and visual quality. Consequently, the resulting images exhibit sharper details and fewer spectral artefacts, showcasing significant advantages in high-fidelity remote sensing image fusion. Full article

Visual body-tracking techniques have seen widespread adoption in applications such as motion analysis, human–machine interaction, tele-robotics and extended reality (XR). These systems typically provide 2D landmark coordinates corresponding to key limb positions. However, to construct a meaningful 3D kinematic model for body joint reconstruction, a mapping must be established between these visual landmarks and the underlying joint parameters of individual body parts. This paper presents a method for constructing a 3D kinematic model of the human hand using calibrated 2D landmark-tracking data augmented with depth information. The proposed approach builds a hierarchical model in which the palm serves as the root coordinate frame, and finger landmarks are used to compute both forward and inverse kinematic solutions. Through step-by-step examples, we demonstrate how measured hand landmark coordinates are used to define the palm reference frame and solve for joint angles for each finger. These solutions are then used in a visualization framework to qualitatively assess the accuracy of the reconstructed hand motion. As a future work, the proposed model offers a foundation for model-based hand kinematic estimation and has utility in scenarios involving occlusion or missing data. In such cases, the hierarchical structure and kinematic solutions can be used as generative priors in an optimization framework to estimate unobserved landmark positions and joint configurations. The novelty of this work lies in its model-based approach using real sensor data, without relying on wearable devices or synthetic assumptions. Although current validation is qualitative, the framework provides a foundation for future robust estimation under occlusion or sensor noise. It may also serve as a generative prior for optimization-based methods and be quantitatively compared with joint measurements from wearable motion-capture systems. Full article