This study proposes an integrated agility assessment system that combines Millimeter-Wave (MMW) radar, Ultra-Wideband (UWB) ranging, and Mixed Reality (MR) technologies to quantitatively evaluate athlete performance with high accuracy. The system utilizes the fine motion-tracking capability of MMW radar and the immersive real-time visualization provided by MR to ensure reliable operation under low-light conditions and multi-object occlusion, thereby enabling precise measurement of mobility, reaction time, and movement distance.To address the challenge of player identification during doubles testing, a one-to-one UWB configuration was adopted, in which each base station was paired with a wearable tag to distinguish individual athletes. UWB identification was not required during single-player tests. The experimental protocol included three specialized agility assessments—Table Tennis Agility Test I (TTAT I), Table Tennis Doubles Agility Test II (TTAT II), and the Agility T-Test (ATT)—conducted with more than 80 table tennis players of different technical levels (80% male and 20% female). Each athlete completed two sets of two trials to ensure measurement consistency and data stability.Experimental results demonstrated that the proposed system effectively captured displacement trajectories, movement speed, and reaction time. The MMW radar achieved an average measurement error of less than 10%, and the overall classification model attained an accuracy of 91%, confirming the reliability and robustness of the integrated sensing pipeline. Beyond local storage and MR-based live visualization, the system also supports cloud-based data uploading for graphical analysis and enables MR content to be mirrored on connected computer displays. This feature allows coaches to monitor performance in real time and provide immediate feedback.By integrating the environmental adaptability of MMW radar, the real-time visualization capability of MR, UWB-assisted athlete identification, and cloud-based data management, the proposed system demonstrates strong potential for professional sports training, technical diagnostics, and tactical optimization. It delivers timely and accurate performance metrics and contributes to the advancement of data-driven sports science applications.

The integration of sensor technology and artificial intelligence is revolutionizing athletic training. This paper presents a novel cost-effective smart table tennis racket embedded with a nine-axis inertial measurement unit (IMU) for real-time stroke classification directly on the device. Unlike systems that are reliant on external computation, our approach leverages Tiny Machine Learning (TinyML) to deploy a customized Convolutional Neural Network (CNN) model onto a microcontroller unit (STM32F7), enabling real-time inference at the edge. The system captures accelerometer and gyroscope data, which is automatically segmented via a recursive algorithm and classified into six fundamental strokes (e.g., forehand/backhand stroke, pull, and chop) or a non-swing state. The classified results are wirelessly transmitted to a computer application for real-time feedback. Experimental results with actual players demonstrate that the optimized CNN model achieves an average classification accuracy of 98.3% in controlled tests and over 94% in mixed-stroke scenarios, validating the system’s high accuracy and robustness. This work exemplifies the practical implementation of an end-to-end intelligent sensor system, highlighting the potential of TinyML to enable advanced, low-power motion analysis in sports.

Low-light image enhancement (LLIE) is a fundamental task in computer vision, required for restoring luminance, contrast, and structural fidelity in images captured under suboptimal lighting environments. This paper introduces an optimization-driven, scene-adaptive LLIE framework, designated as $O{M}_{\mathrm{I}\mathrm{D}\mathrm{C}\mathrm{P}}^{\mathrm{G}\mathrm{C}\mathrm{G}\mathrm{L}}$, which exploits the optical duality between low-light inversion and atmospheric scattering. The proposed methodology transforms low-light inputs into quasi-haze representations through an optical inversion process, followed by structural restoration using an Improved Dark Channel Prior ($M_{\mathrm{I}\mathrm{D}\mathrm{C}\mathrm{P}}$) baseline. To refine the restored output, a Gamma Correction with Global Limits (GCGL) module is integrated as a boundary constraint to mitigate localized over-exposure and preserve chromatic consistency. A core novelty of this framework lies in the deployment of metaheuristic optimization algorithms (MOAs)—specifically the Gray Wolf Optimizer (GWO), Harris Hawks Optimization (HHO), and Marine Predators Algorithm (MPA)—to autonomously resolve optimal, image-specific parameter configurations. This search paradigm is guided by perception-driven fitness functions, namely the Patch-based Contrast Quality Index (PCQI) or the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Quantitative and qualitative evaluations across a comprehensive pool of 1092 benchmark images demonstrate that the proposed framework exhibits robust statistical resilience and cross-dataset generalization compared to four state-of-the-art deep learning methods. While data-driven deep learning architectures retain localized superiority under the extreme degradation boundaries of the DARK FACE dataset, the proposed physics-inspired optimization framework achieves the leading overall cross-dataset aggregate ranking ($\overline{R}=2.467$) across diverse evaluation environments due to its per-image dynamic solution space mapping.