Search Results (97)

Object detection remains a fundamental challenge in computer vision and plays a pivotal role in safety-critical medical applications, including surgical instrument recognition and operating-room workflow automation. This study presents a comprehensive comparative evaluation of five attention mechanisms—Squeeze-and-Excitation (SE), Convolutional Block Attention Module (CBAM), Efficient Channel Attention (ECA), Simple Attention Module (SimAM), and an enhanced multi-kernel Spatial Pyramid Pooling Fast module (SPPF+)—integrated into the YOLOv26n backbone, together with two neck-level attention variants (ECA-Neck and CBAM-Neck). A total of 16 model configurations were systematically investigated on a 22-class dental surgical instrument detection dataset under both default training settings and hyperparameter configurations optimized using the Optuna Tree-structured Parzen Estimator (TPE), enabling a rigorous full-factorial ablation study. Experimental results demonstrate that TPE-based hyperparameter optimization consistently enhances detection performance across all architectures. Among the evaluated models, CBAM-Opt achieved the highest detection accuracy, attaining an mAP@50 of 0.959 and an F1-score of 0.913, although the margins among the top optimized configurations fall within run-to-run variability. In contrast, Base-Opt delivered the strongest strict-localization capability with an mAP@50–95 of 0.800, highlighting the competitive performance of the baseline architecture when appropriately optimized. Notably, the parameter-free SimAM module exhibited the largest improvement following optimization ($\Delta$mAP@50 = +0.040), indicating a pronounced sensitivity to training configuration. Furthermore, neck-level attention integration achieved performance comparable to backbone-based attention, with ECA-Neck-Opt reaching an mAP@50 of 0.959, suggesting an effective alternative that preserves pretrained feature representations while maintaining high detection accuracy. Beyond performance evaluation, this work provides a unified benchmarking framework for attention mechanisms in medical object detection, accompanied by computational complexity analysis and practical architectural insights. The findings establish evidence-based guidelines for selecting attention modules in resource-aware surgical vision systems and contribute toward the development of more accurate and reliable computer-assisted clinical workflows. Full article

Falls among older adults can cause serious injury and loss of independence. cStick 2.0 is a vision-enabled, IoMT-edge based smart walking-stick prototype that combines multimodal fall-risk classification with embedded obstacle awareness. The fall-risk classifiers were evaluated using a 9670-record development dataset, on which the compact DNN achieved 95.40% accuracy, 92.35% balanced accuracy, a macro F1-score of 93.90%, and a ROC-AUC of 97.44%. The Arduino Nicla Vision obstacle module used an INT8 Edge Impulse model with centroid-based direction assignment and time-of-flight distance sensing; 144 controlled trials produced 75.00% obstacle-presence accuracy at approximately 19–20 FPS. Sensor acquisition, GPS, display output, buzzer response, and CSV record accumulation were demonstrated at a prototype level. Synchronized older-adult evaluation, device-to-application communication, secure caregiver services, multimodal accessibility feedback, and longitudinal personalization remain future validation stages. Full article

Micro-expression recognition (MER) has a lot of applications in lie detection, education, healthcare, etc., as involuntary micro-expressions (MEs) may provide subtle facial cues associated with affective responses. With the development of deep learning, many studies have recently employed Vision Transformers (ViTs) to investigate MER, since ViTs show promising performance in various visual domains due to their excellent local–global modeling ability. However, such methods confront two fundamental challenges: First, fine-grained visual features are needed to capture the subtle facial movements of MEs, which ViTs relatively fall short on due to coarse patch resolution constrained by their quadratic complexity. Second, the data-intensive nature of ViTs impedes effective learning given the limited scale of ME data. To overcome the aforementioned limitations of using ViTs for MER, we propose the Prior-aware Sparse Transformer (PAST), a novel Transformer-based architecture integrating spatial and semantic prior knowledge synergistically into a sparse attention mechanism, enabling linear-complexity processing of large amounts of fine-grained features. Specifically, we first designed an extraction algorithm to generate a representative set of motion-intensive Principal Anchors, which are used to guide the model’s focus on biologically critical regions during sampling. Second, we introduced the Semantic Dictionary, which was trained with a carefully designed self-contrastive loss to embed task-invariant discriminative semantics of the anchors. Such global semantics further modulate patch sampling and attention weighting in the sparse attention procedure, achieving better training performance with limited ME data. Extensive evaluations on MEGC and CD6ME protocols demonstrate state-of-the-art performance, validating PAST’s efficacy for MER. Full article

In this paper, we evaluated image quality, algorithms and a workflow associated with matching horizons derived from 3D terrain data to ground imagery as a way to visually estimate a geographic position. The evaluation represented a passive, vision-based navigation technique using long-standoff (>1 KM) terrain features and a horizon detection algorithm hosted within an Android-based geospatial application. Our method involved quantitatively grading edge image feature quality based on pixel data between sky and terrain from high to poor. We tested the algorithm and processing to derive a position using images of varied quality, representing fine and gross, and near and far geographic terrain structures. The site chosen for our tests was located near the Organ Mountains in New Mexico to take advantage of largely unobstructed, long-distance features that challenged both image quality and horizon detection. Testing used the Samsung S23 Ultra (S23U) phone’s primary internal camera to acquire the necessary ground images and native compute power. Our evaluation workflow featured both pre-processing and near-real-time processing elements for position estimations. Pre-processing involved building a Geopackage containing geolocated, synthetic horizons extracted from available 3D terrain data of the test area and camera/sensor configuration data. These data were pre-loaded onto the phone to accomplish the live, near-real-time positional determinations matched to the extracted horizons generated from images acquired by the S23U camera. Our results showed that single-image processing, where only one high-quality ground photo was acquired, 75% of solutions were within 100 m of the actual camera position (compared with the internal sensor-based, Exchangeable Image File Format (EXIF) metadata). Single images of fair quality resulted in positional accuracies where only 38% of the solutions were within 100 m of the EXIF. Improvement was realized when four or more images from varying directions collected from a single location resulted in over 90% of positions falling within 100 m of the EXIF. Full article

Reverse engineering of printed circuit boards is still largely manual when original computer-aided design documentation is unavailable. This paper presents a semi-automatic vision-based pipeline that prepares an editable KiCad schematic draft for use in an Electronic Design Automation (EDA) workflow from paired TOP and BOTTOM board images. The method combines color-profile estimation, pad and through-hole detection, trace segmentation, optical character recognition, component inference, an explicit evidence graph and schematic export with drawn wires. A separate readability step aligns symbols to a grid and reroutes the reconstructed nets with orthogonal wires; it does not change the reconstructed netlist. The primary quantitative evaluation used twelve synthetic KiCad fixtures and three solver configurations: the default sequential pipeline, an opt-in global component solver and an opt-in probabilistic contact solver. These fixtures provide controlled regression cases and are complemented by a small exploratory acquisition trial on real photographed boards. All configurations completed all runs and passed the export round-trip validation without falling back to label-only connectivity. This round-trip check confirms consistency between the internal reconstruction and the exported schematic, but it is reported separately from electrical correctness against the KiCad reference design. The stricter reconstruction-quality criterion still failed on four stress cases involving repeated component chains, long meandering variable-width traces, circular distractors near pads and two-sided transistor layouts. The probabilistic contact solver was therefore kept as an opt-in diagnostic mode rather than enabled by default; it reduced the global pin-to-pin netlist edit distance from 642 to 525 while preserving schematic export checks. The real-board trial indicates that pad and hole detection can transfer to simple photographs, with trace extraction remaining sensitive to uncontrolled illumination and weak copper contrast. The results support the use of the system as a human-in-the-loop reconstruction assistant and identify component grouping, trace-contact reasoning, real-photograph benchmarking and safe missing-edge activation as the main remaining research problems. Full article

Remote tele-rehabilitation requires objective pain assessment, but existing approaches fail in two distinct ways. Self-report scales such as the Visual Analog Scale and the Numeric Pain Rating Scale are easy to falsify, opening a special case of the Oracle problem in blockchain-based insurance. Cloud-based computer vision handles falsification but transmits raw biometric video off the patient’s device, violating privacy requirements. A decentralized Edge AI-Oracle architecture is proposed that combines MediaPipe Face Mesh landmark extraction with a recurrent classifier mapping Action-Unit feature sequences to a learned pain score aligned with the Prkachin and Solomon Pain Intensity scale. The recurrent cell is selected empirically across short-context (T = 2) and long-context (T = 120 frames at 24 fps) regimes, with a two-layer Long Short-Term Memory (LSTM) network adopted for deployment. Inference and Elliptic Curve Digital Signature Algorithm (ECDSA) signing run inside an ARM TrustZone Trusted Execution Environment (TEE). Biometric logs are stored off-chain on the InterPlanetary File System (IPFS). Smart contracts anchor results on-chain and open a 24 h optimistic verification window for an off-chain Watchtower auditor. On SynPAIN the LSTM reaches F1 = 0.683 on T = 120 video (leave-one-stratum-out), with a directional but non-significant advantage over Gated Recurrent Unit (GRU) (Wilcoxon p = 0.167). Cross-dataset validation on BioVid Heat Pain Database Part A (87 subjects, 174 paired observations, leave-one-subject-out) yields F1 = 0.519 for LSTM and 0.499 for GRU (Wilcoxon p = 0.549). A processor-only TEE surrogate benchmark estimates 1.96 ms (FP32) and 0.45 ms (INT8) inference latency at T = 120 with a 0.34 MB footprint and 707 µs ECDSA signing latency, leaving the INT8 inference latency more than an order of magnitude below the 33 ms per-frame budget. The dual-layer storage reduces gas costs by a factor of 23.4 (160,261 vs. 3,744,872 gas), corresponding to an illustrative mainnet cost of approximately 0.53 USD per submission at 1 gwei, rising to roughly 16 USD at a busier 30 gwei, and falling to approximately 0.005 USD on Arbitrum One (April 2026 reference parameters), so that continuous monitoring is economically practical on Layer-2. An adaptive-adversary analysis of the Watchtower shows that gross score tampering is detected at every usable operating threshold, whereas a rational adversary who inflates by less than the dispute threshold, or who shapes the injected score to fall just inside it, evades detection. Because the false-positive rate reaches zero only for $\mathsf{\delta }\gtrsim 0.15$, the protocol bounds rather than eliminates patient-side fraud and motivates a zero-knowledge proof-of-inference successor. The framework is architecturally and economically feasible as a cryptographically verifiable, privacy-preserving tele-rehabilitation substrate aligned with General Data Protection Regulation (GDPR) and Health Insurance Portability and Accountability Act (HIPAA) requirements through the Zero-Video Transmission principle, while remaining economically viable under post-Dencun mainnet and Layer-2 conditions. Recognition accuracy on real-world data and robustness to small-magnitude tampering remain limitations that the interchangeable recognition and audit components must improve before clinical deployment. Full article

Driven by global population aging, long-term in-home and institutional elderly care faces challenges in delivering continuous, privacy-aware, and resource-efficient safety and health monitoring. Existing edge-based solutions struggle to jointly balance detection accuracy, privacy, and resource overhead during continuous operation, and often have limited situational awareness and inflexible management. We propose EdgeElderCare, a resource-aware, scene-adaptive edge-cloud collaborative system for continuous elderly safety and health monitoring. Its contributions are threefold: (1) a scene-adaptive multi-sensor task-sharing architecture that deploys vision-based fall detection in public areas and privacy-aware millimeter-wave radar in private spaces. Combined with edge-side task scheduling, it provides spatially complementary coverage of public and private areas, mitigates the accuracy–privacy conflict, and reduces computing and bandwidth consumption relative to data-level fusion; (2) a lightweight myocardial infarction detection module deployed on an edge platform, enabling local ECG analysis with low resource overhead; (3) a 3D digital-twin edge-cloud management platform that maps multi-source sensing data to a virtual scene in real time and supports hierarchical visual alerting. Experiments in a real nursing home environment show that the system operated stably on resource-constrained edge hardware: UWB positioning achieved centimeter-level RMSE, visual fall detection reached a recall of 0.90, millimeter-wave radar fall detection achieved accuracy, and F1 above 0.90, and myocardial infarction detection exceeded 0.99 accuracy on the public PTB/PTB-XL benchmark. These results indicate an engineering-feasible approach to intelligent elderly care. Larger-scale and longer-term validation remains the focus of future work. Full article

Vision-based fall detection for smart-city CCTV must be fast, interpretable, and robust to nuisance alarms. In real surveillance scenes, false alarms are often caused by sitting, crouching, duplicate detections, short-lived pose noise, and brief posture changes that do not correspond to actual falls. This paper presents a lightweight CCTV fall-detection framework evaluated on URFD, Le2i, and UP-Fall. The proposed method combines teacher-guided distillation from ViTPose to a YOLO26s-pose student, custom person detection, full-body ROI extraction, nine interpretable posture features, Random Forest classification, tracking-based duplicate suppression, and post-event false-positive rejection. The distillation stage improves pose mAP50-95 from 66.8% to 70.9% and pose mAP50 from 88.9% to 91.2%. In the final stand/fall setting, Random Forest with false-positive rejection achieves 98.46% accuracy, 98.61% precision, 98.43% recall, and 98.52% F1-score. The main contribution of this work is a practical and interpretable surveillance framework that integrates distilled lightweight pose estimation, posture-based fall representation, and tracking-aware false-positive suppression for robust deployment-oriented fall detection. Full article

Human lifespan is increasing in parallel with the development levels of societies. Consequently, the number of elderly individuals worldwide is also rising day by day. One of the most significant risks these individuals face is falling. In this study, fall and daily activity data were collected from different home environments using a continuous-wave (CW) radar. Micro-Doppler signatures were generated from 700 data samples obtained from 10 individuals. Furthermore, the dataset was expanded by doubling the number of spectrogram images through data augmentation. The YOLO architecture, generally used in vision-based studies for object detection and tracking, was preferred for radar-based fall and activity detection. Classifications were performed with different YOLO structures, and comparative results are presented. At this stage, binary (fall/non-fall) and multi-class (seven different classes) classifications were carried out, achieving 100% accuracy for binary classification and 88.02% for multi-class classification. Additionally, the generalizability of the proposed architecture is demonstrated using the Leave-One-Subject-Out (LOSO) approach on the collected data and through the analysis of a public dataset. These results demonstrate the applicability of YOLO architectures in radar-based fall detection studies. Full article

Ensuring the visibility of road markings is critical for traffic safety, yet current inspection methods remain either prohibitively expensive (retroreflectivity) or subjective (manual assessment). This article introduces the Random Generated Reference (RGR) method, a novel automated solution for quantifying marking degradation using a standard on-board camera. The proposed pipeline is a complete protocol from video acquisition to road marking inspection and validation of the inspection that combines deep learning with computer vision: YOLOv8 is employed for robust detection, while a unique algorithm generates a “perfect virtual reference” that dynamically replicates the real scene’s geometry and illumination conditions, including shadows. By computing pixel-level deviations between the observed marking and this ideal reference, the system assigns a continuous degradation score aligned with the UK CS126 standard. Experimental validation was conducted on a real-world circuit yielding over 20,000 detections. Verification via Cochran sampling demonstrates that 68% of the automated assessments fall within one class of human inspection. This proof-of-concept confirms the viability of an approach based on generating the ground truth and scene conditions—such as illumination, shadows, rain, traffic, etc.—for road marking inspection. Full article

Falls are a leading cause of paediatric injuries, yet school-based prevention relies heavily on subjective observation rather than objective biomechanical assessment. This paper introduces the Safe Fall framework, integrating a judo-inspired educational programme with an occlusion-robust computer vision pipeline to quantify safe falling strategies. We analysed video recordings of 285 schoolchildren using a multi-stage architecture combining YOLOv8 for detection, SAM 2 for segmentation, and MMPose for skeletal tracking. The intervention yielded significant improvements in 60% of kinematic metrics ($p<0.05$), most notably a $+61.4\%$ increase in descent rate and expanded rolling ranges, indicating a shift from hazardous “freezing” behaviours to controlled energy dissipation. Unsupervised clustering confirmed a migration of students towards safe motor profiles, while a Random Forest classifier achieved an accuracy of 98.3% and an AUC of 0.998 in distinguishing fall quality. These findings demonstrate that integrating pedagogical training with automated vision modelling provides a scalable and evidence-based approach for reducing injury risk in real-world school environments. Full article

People affected by vision impairment experience significant challenges in mobility and daily life activities. In this paper, a smart assistive navigation system is proposed to address mobility challenges and to enhance the independence of visually impaired individuals. Three modules are integrated into the proposed system. The vision module detects obstacles and interactive objects such as doors, chairs, people, fire extinguishers, etc. The depth cam-based distance module provides the distance of detected objects and obstacles. The voice module provides auditory feedback to visually impaired individuals about the detected objects and obstacles that fall under the pre-defined threshold distance. Finally, the proposed system is optimized in terms of performance and user experience. Jetson Nano is used to reduce the cost of the overall system; however, it has compatibility issues with many of the latest object detection models. The YOLOv5n model is used considering compatibility for object detection, but it has low Mean Average Precision (mAP) and frame rate. To improve the performance of the vision module, various hyperparameters of YOLOv5n are fine-tuned along with transfer learning to enhance the mAP@50 from the original 0.457 to 0.845 and mAP@50-95 from 0.28 to 0.593. Tensor-RT optimization is employed to increase the frame rate to deploy the model in a real scenario. The real-time experimentation shows that the proposed system successfully alerts users to key objects, hazards, and obstacles which enables independent and confident navigation. Full article

Background: Falls are a leading cause of morbidity and mortality among older adults, creating a need for technologies that can automatically detect falls and summon timely assistance. The rapid evolution of sensor technologies and artificial intelligence has led to a proliferation of fall detection systems (FDS). This systematic review synthesizes the recent literature to provide a comprehensive overview of the current technological landscape. Objective: The objective of this review is to systematically analyze and synthesize the evidence from the academic literature on fall detection technologies. The review focuses on three primary areas: the sensor modalities used for data acquisition, the computational models employed for fall classification, and the emerging trend of shifting from reactive detection to proactive fall risk prediction. Methods: A systematic search of electronic databases was conducted for studies published between 2008 and 2025. Following the PRISMA guidelines, 130 studies met the inclusion criteria and were selected for analysis. Information regarding sensor technology, algorithm type, validation methods, and key performance outcomes was extracted and thematically synthesized. Results: The analysis identified three dominant categories of sensor technologies: wearable systems (primarily Inertial Measurement Units), ambient systems (including vision-based, radar, WiFi, and LiDAR), and hybrid systems that fuse multiple data sources. Computationally, the field has shown a progression from threshold-based algorithms to classical machine learning and is now dominated by deep learning architectures, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Many studies report high performance, with accuracy, sensitivity, and specificity often exceeding 95%. An important trend is the expansion of research from post-fall detection to proactive fall risk assessment and pre-impact fall prediction, which aim to prevent falls before they cause injury. Conclusions: The technological capabilities for fall detection are well-developed, with deep learning models and a variety of sensor modalities demonstrating high accuracy in controlled settings. However, a critical gap remains; our analysis reveals that 98.5% of studies rely on simulated falls, with only two studies validating against real-world, unanticipated falls in the target demographic. Future research should prioritize real-world validation, address practical implementation challenges such as energy efficiency and user acceptance, and advance the development of integrated, multi-modal systems for effective fall risk management. Full article

Planar mirrors play a crucial role in autocollimation testing and optical beam relay systems of telescopes and other fields. However, for the next-generation large-aperture telescopes, typical monolithic planar mirrors fall short in meeting anticipated performance requirements, owing to their high costs and fabrication limitations. Here, a new integrated multimodal testing method for 3–4 m-class segmented planar mirrors is proposed. The presented system utilizes an innovative keystone architecture with a central mirror and keystone-shaped segments, which is superior to the traditional hexagonal architecture. To facilitate rapid coarse alignment, a machine vision system based on edge detection is investigated. Furthermore, the dispersed fringe technique is used for robust co-phasing. By using a segmented planar mirror designed with sub-aperture stitching strategy and combining local apertures, the system cost was reduced and high-precision measurement was achieved. Eventually, the alignment, co-focus and co-phasing measurements based on the proposed concept were completed, and the transfer characteristics were determined by analyzing the Optical Transfer Function (OTF). Test data shows co-phasing accuracy of better than 30 nm RMS (root-mean-square) and alignment accuracy less than 10 arcseconds. In addition, the system uses small-aperture mirrors in autocollimation testing to facilitate flexible alignment and testing of individual segments. The test optical path is configured to match the effective focal length of the system under test, and the optical lever effect of reflectors enhances the alignment sensitivity. The method combines autocollimation and wavefront sensing which allows the approach to provide high-precision control of co-focus, co-phasing, and surface errors correction. Full article

Soft robotic grippers provide compliant and adaptive manipulation, but most existing designs address actuation speed, adaptability, modularity, or sensing individually rather than in combination. This paper presents an electro-actuated customizable stacked Fin Ray gripper that integrates these capabilities within a single design. The gripper employs a compact solenoid for fast grasping, multiple vertically stacked Fin Ray segments for improved 3D conformity, and interchangeable silicone or TPU fins that can be tuned for task-specific stiffness and geometry. In addition, a light-guided, vision-based sensing approach is introduced to capture deformation without embedded sensors. Experimental studies—including free-fall object capture and optical shape sensing—demonstrate rapid solenoid-driven actuation, adaptive grasping behavior, and clear visual detectability of fin deformation. Complementary simulations using Cosserat-rod modeling and bond-graph analysis characterize the deformation mechanics and force response. Overall, the proposed gripper provides a practical soft-robotic solution that combines speed, adaptability, modular construction, and straightforward sensing for diverse object-handling scenarios. Full article