Shimpei Aihara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shimpei Aihara has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Guanyu Chen
Graduate School of Systems Information Science, Future University Hakodate, 116-2 Kamedanakano-cho, Hakodate 041-8655, Hokkaido, Japan
3 shared publications - Ryosuke Katagiri
Faculty of Textile Science and Technology, Shinshu University, 3-15-1 Tokida, Ueda, Nagano 386-8567, Japan
3 shared publications - Tadaaki Sone
Department of Electrical, Electronic and Information Engineering, Faculty of Engineering, Kanagawa University, 3-27-1 Rokkakubashi, Kanagawa-ku, Yokohama 221-8686, Japan
3 shared publications - Yoshinari Takegawa
Graduate School of Systems Information Science, Future University Hakodate, 116-2 Kamedanakano-cho, Hakodate 041-8655, Hokkaido, Japan
3 shared publications - Akihiro Kawamura
Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan
2 shared publications - Masahito Yamamoto
Faculty of Information Science and Technology, Hokkaido University, Sapporo 060-0814, Japan
2 shared publications
Latest Publications
- 15 October 2026
- Published by Elsevier in Entertainment Computing
- Vol. 59
Curling of the future: A curling experience system facilitating play by throwing a stone and sweeping with a brush
- 15 October 2026
- Published by Elsevier in Entertainment Computing
- Vol. 59
Curling of the future: A curling experience system facilitating play by throwing a stone and sweeping with a brush
- Open Access
- 7 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (17) , 8877
Development and Field Evaluation of a Bolt-Type Force Measurement System for Sport Climbing Holds
Quantitative measurement of forces applied to climbing holds is important for biomechanical analysis and technique assessment in sport climbing. Existing measurement systems often require dedicated instrumented holds or force sensors inserted between the hold and the wall, which can restrict the selection of hold shapes or alter the wall–hold geometry. This study developed a bolt-type force measurement system in which strain-gauge-based sensors replace the bolts used to secure climbing holds. The sensor wiring passes through the bolt shaft and is routed to the rear side of the climbing wall, thereby reducing interference with the climber while preserving the external shape of the hold. Two bolt-type force sensors were calibrated using a reference six-axis force sensor and installed in two footholds on a standardized speed climbing wall. Within the calibration dataset, the error ratios in the principal loading direction, , were 2.9% and 5.1% for Foot 1 and Foot 2, respectively, whereas the error ratios in the least-loaded direction were higher, at 11.8% and 27.1%. Because the same calibration data were used to select the calibration matrices and calculate these errors, these values represent in-sample agreement rather than independent validation performance. A supplementary two-way hold-out analysis produced larger and split-dependent errors; for the principal loading direction, , the hold-out MAE ratios ranged from 3.5% to 7.5% for Foot 1 and from 7.4% to 11.3% for Foot 2, whereas the corresponding ratios ranged from 8.0% to 26.8% and from 45.9% to 87.5%, respectively. Field measurements were then conducted during 27 start trials performed by five competitive climbers. The system operated throughout all trials and recorded time-varying three-axis force estimates from both footholds without exposed wiring on the climbing side. For Foot 1, the estimated force components could be interpreted together with the observed start motion. For Foot 2, the climber’s foot may also have contacted the adjacent wall surface, so the sensor did not necessarily capture the entire foot reaction force. These results demonstrate the feasibility of deploying and operating the proposed system under actual speed-climbing conditions and provide a basis for future field-based biomechanical analyses.- 7 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (17) , 8877
Open AccessDevelopment and Field Evaluation of a Bolt-Type Force Measurement System for Sport Climbing Holds
Quantitative measurement of forces applied to climbing holds is important for biomechanical analysis and technique assessment in sport climbing. Existing measurement systems often require dedicated instrumented holds or force sensors inserted between the hold and the wall, which can restrict the selection of hold shapes or alter the wall–hold geometry. This study developed a bolt-type force measurement system in which strain-gauge-based sensors replace the bolts used to secure climbing holds. The sensor wiring passes through the bolt shaft and is routed to the rear side of the climbing wall, thereby reducing interference with the climber while preserving the external shape of the hold. Two bolt-type force sensors were calibrated using a reference six-axis force sensor and installed in two footholds on a standardized speed climbing wall. Within the calibration dataset, the error ratios in the principal loading direction, , were 2.9% and 5.1% for Foot 1 and Foot 2, respectively, whereas the error ratios in the least-loaded direction were higher, at 11.8% and 27.1%. Because the same calibration data were used to select the calibration matrices and calculate these errors, these values represent in-sample agreement rather than independent validation performance. A supplementary two-way hold-out analysis produced larger and split-dependent errors; for the principal loading direction, , the hold-out MAE ratios ranged from 3.5% to 7.5% for Foot 1 and from 7.4% to 11.3% for Foot 2, whereas the corresponding ratios ranged from 8.0% to 26.8% and from 45.9% to 87.5%, respectively. Field measurements were then conducted during 27 start trials performed by five competitive climbers. The system operated throughout all trials and recorded time-varying three-axis force estimates from both footholds without exposed wiring on the climbing side. For Foot 1, the estimated force components could be interpreted together with the observed start motion. For Foot 2, the climber’s foot may also have contacted the adjacent wall surface, so the sensor did not necessarily capture the entire foot reaction force. These results demonstrate the feasibility of deploying and operating the proposed system under actual speed-climbing conditions and provide a basis for future field-based biomechanical analyses. - Open Access
- 31 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (15) , 7600
Development of a Monocular Camera-Based Sweep Analysis System in Curling
Curling requires precise sweeping to control both the speed and trajectory of a stone, making quantitative analysis of sweeping behavior an important challenge for performance evaluation and tactical support. However, existing curling studies have primarily focused on stone motion analysis, while automatic estimation of sweep positions and brush orientations from monocular video remains largely unexplored. To address this problem, this study proposes a vision-based system for estimating the position and orientation of curling brushes during sweeping using a single RGB camera. The proposed framework integrates a two-stage YOLOv8-OBB detection pipeline for identifying sweeping players and brush regions, ByteTrack-based multi-object tracking for temporal association, and a geometric calibration model that transforms image coordinates into real-world curling-sheet coordinates through nonlinear optimization. The system enables frame-by-frame reconstruction of sweeping trajectories and brush orientations without requiring specialized sensing equipment. Experiments were conducted at a curling facility using synchronized monocular video and a Qualisys Miqus M3 motion-capture system as ground truth. The proposed method achieved position estimation errors of 0.03–0.06 m and orientation estimation errors of 4.80°–5.10°, while maintaining a high detection rate of 0.96–0.99 over a measurement range of 15 m. Additional analyses showed that estimation accuracy was influenced by camera placement, sweep style, and the apparent size of the detected brush region. These results demonstrate that accurate sweep-position and orientation estimation can be achieved using only a monocular camera under realistic curling conditions. The proposed system provides a practical framework for objective sweep analysis and has potential applications in technical training, performance assessment, and tactical support in curling.
- 31 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (15) , 7600
Open AccessDevelopment of a Monocular Camera-Based Sweep Analysis System in Curling
Curling requires precise sweeping to control both the speed and trajectory of a stone, making quantitative analysis of sweeping behavior an important challenge for performance evaluation and tactical support. However, existing curling studies have primarily focused on stone motion analysis, while automatic estimation of sweep positions and brush orientations from monocular video remains largely unexplored. To address this problem, this study proposes a vision-based system for estimating the position and orientation of curling brushes during sweeping using a single RGB camera. The proposed framework integrates a two-stage YOLOv8-OBB detection pipeline for identifying sweeping players and brush regions, ByteTrack-based multi-object tracking for temporal association, and a geometric calibration model that transforms image coordinates into real-world curling-sheet coordinates through nonlinear optimization. The system enables frame-by-frame reconstruction of sweeping trajectories and brush orientations without requiring specialized sensing equipment. Experiments were conducted at a curling facility using synchronized monocular video and a Qualisys Miqus M3 motion-capture system as ground truth. The proposed method achieved position estimation errors of 0.03–0.06 m and orientation estimation errors of 4.80°–5.10°, while maintaining a high detection rate of 0.96–0.99 over a measurement range of 15 m. Additional analyses showed that estimation accuracy was influenced by camera placement, sweep style, and the apparent size of the detected brush region. These results demonstrate that accurate sweep-position and orientation estimation can be achieved using only a monocular camera under realistic curling conditions. The proposed system provides a practical framework for objective sweep analysis and has potential applications in technical training, performance assessment, and tactical support in curling.
- Open Access
- 18 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 7204
Development of a Smart Shoe System Toward Evaluating Curling Skill and Ice Surface Conditions: A Sensor-Embedded Slider for Vibration-Based Characterization of Ice Surface Conditions
In curling, quantitative assessment of ice surface conditions during actual play is challenging, and existing sensor-on-stone approaches cannot simultaneously capture ice-contact vibration and athlete-related measurements. We developed a self-contained wearable slider unit embedding two IMUs (LSM6DSV16X), a wideband accelerometer (IIS3DWB), and plantar pressure sensors in a commercially compatible curling slider. Measurements were conducted with two participants under four ice surface conditions (used pebble, no-pebble, extra-fine, and coarse-fine pebble) at an actual curling hall. The root mean square (RMS) amplitude of the DC-subtracted IIS3DWB Z-axis vibration signal distinguished no-pebble from pebbled ice but did not distinguish among the three pebbled conditions. The spectral centroid of the no-pebble condition was also biased toward higher frequencies, although participant-dependent effects remained among pebbled conditions. The slider acquired plantar-pressure variation during delivery, and an exploratory pooled analysis showed a pattern consistent with greater right/left balance variation in trials with greater MOCAP-derived lateral wobble. Because only two participants were tested and the lateral pressure channels reached the calibration limit, participant-specific validation requires a wider measurement range and additional participants. These results support the feasibility of simultaneous ice-contact vibration and plantar-pressure measurement during curling delivery.
- 18 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 7204
Open AccessDevelopment of a Smart Shoe System Toward Evaluating Curling Skill and Ice Surface Conditions: A Sensor-Embedded Slider for Vibration-Based Characterization of Ice Surface Conditions
In curling, quantitative assessment of ice surface conditions during actual play is challenging, and existing sensor-on-stone approaches cannot simultaneously capture ice-contact vibration and athlete-related measurements. We developed a self-contained wearable slider unit embedding two IMUs (LSM6DSV16X), a wideband accelerometer (IIS3DWB), and plantar pressure sensors in a commercially compatible curling slider. Measurements were conducted with two participants under four ice surface conditions (used pebble, no-pebble, extra-fine, and coarse-fine pebble) at an actual curling hall. The root mean square (RMS) amplitude of the DC-subtracted IIS3DWB Z-axis vibration signal distinguished no-pebble from pebbled ice but did not distinguish among the three pebbled conditions. The spectral centroid of the no-pebble condition was also biased toward higher frequencies, although participant-dependent effects remained among pebbled conditions. The slider acquired plantar-pressure variation during delivery, and an exploratory pooled analysis showed a pattern consistent with greater right/left balance variation in trials with greater MOCAP-derived lateral wobble. Because only two participants were tested and the lateral pressure channels reached the calibration limit, participant-specific validation requires a wider measurement range and additional participants. These results support the feasibility of simultaneous ice-contact vibration and plantar-pressure measurement during curling delivery.
- Open Access
- 10 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 6943
Building an All-Shot Expected-Score Distribution Model from Real-Match Curling Boards: Shot-Wise Accuracy and Plausibility Analysis
Curling is a strategic sport in which shot decisions involve both expected rewards and inherent risks; expected-score distributions (ESDs)—probability distributions over possible final scores—capture this uncertainty as a risk-aware strategic indicator. Although unified frameworks predicting ESDs across all shots have been proposed, their internal behavior and learned output characteristics have not been systematically examined. We construct an all-shot ESD prediction framework grounded entirely in real-match board configurations drawn from World Curling Federation championship events and conduct a shot-wise analysis along two complementary axes: accuracy, the model’s reproduction of its training targets, and plausibility, the validity of those targets at aggregate and in-match scales. Accuracy degrades monotonically with shot number; only shot 16 admits comparison with an independent reference, while intermediate-shot labels are bootstrap rollouts of the next-shot model. An independent ground-truth probe at the first backward step (shot 15,500 boards × 95 contexts) bounds the consequence of this bootstrap structure: the resulting deviation is a small selection-induced hammer-underestimation bias common to both FiLM and concatenation chains, whose magnitude is more than an order of magnitude larger than the FiLM chain versus concatenation chain stage difference, and full multi-step verification beyond the first step is structurally out of reach. Within this scope the aggregate ESD shares the gross shape of the empirical end-score distribution and the qualitative hammer/non-hammer ordering, with a hammer-favorable offset attributed—after disentangling intent from execution on the shot-percentage 100% subset—to a label execution-noise envelope that is tighter than the realized play of top-tier matches. Within real matches the chain responds smoothly to each delivered stone and, at the directly validated terminal shot, assigns mean probability – to the realized end score under intended execution (against for a marginal-frequency baseline), transferring from senior to junior populations. The framework is best read as an internally coherent chain anchored to a directly validated final-shot calibration, statistically plausible under intended execution with a clear boundary at execution failure. Two structural limitations remain: rare high-magnitude outcomes are scarce in real data and produce a heavy upper tail of accuracy errors, and a single fixed execution-noise envelope that is tighter than top-tier realized play accounts for the aggregate hammer-side offset and motivates recalibration against real-match execution statistics.- 10 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 6943
Open AccessBuilding an All-Shot Expected-Score Distribution Model from Real-Match Curling Boards: Shot-Wise Accuracy and Plausibility Analysis
Curling is a strategic sport in which shot decisions involve both expected rewards and inherent risks; expected-score distributions (ESDs)—probability distributions over possible final scores—capture this uncertainty as a risk-aware strategic indicator. Although unified frameworks predicting ESDs across all shots have been proposed, their internal behavior and learned output characteristics have not been systematically examined. We construct an all-shot ESD prediction framework grounded entirely in real-match board configurations drawn from World Curling Federation championship events and conduct a shot-wise analysis along two complementary axes: accuracy, the model’s reproduction of its training targets, and plausibility, the validity of those targets at aggregate and in-match scales. Accuracy degrades monotonically with shot number; only shot 16 admits comparison with an independent reference, while intermediate-shot labels are bootstrap rollouts of the next-shot model. An independent ground-truth probe at the first backward step (shot 15,500 boards × 95 contexts) bounds the consequence of this bootstrap structure: the resulting deviation is a small selection-induced hammer-underestimation bias common to both FiLM and concatenation chains, whose magnitude is more than an order of magnitude larger than the FiLM chain versus concatenation chain stage difference, and full multi-step verification beyond the first step is structurally out of reach. Within this scope the aggregate ESD shares the gross shape of the empirical end-score distribution and the qualitative hammer/non-hammer ordering, with a hammer-favorable offset attributed—after disentangling intent from execution on the shot-percentage 100% subset—to a label execution-noise envelope that is tighter than the realized play of top-tier matches. Within real matches the chain responds smoothly to each delivered stone and, at the directly validated terminal shot, assigns mean probability – to the realized end score under intended execution (against for a marginal-frequency baseline), transferring from senior to junior populations. The framework is best read as an internally coherent chain anchored to a directly validated final-shot calibration, statistically plausible under intended execution with a clear boundary at execution failure. Two structural limitations remain: rare high-magnitude outcomes are scarce in real data and produce a heavy upper tail of accuracy errors, and a single fixed execution-noise envelope that is tighter than top-tier realized play accounts for the aggregate hammer-side offset and motivates recalibration against real-match execution statistics. - Open Access
- 9 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 6886
A Resilient and Extensible Digital Curling Platform Using Server-Sent Events and REST APIs
Curling is strategically complex, yet data-driven strategic AI is limited by the scarcity of large-scale match data with shot-by-shot states and histories. Digital Curling provides such an environment, but no prior system has combined match resumption after failures, centralized state persistence, and a decoupled simulator into a single, reusable research platform. We propose and implement a new Digital Curling platform that improves resilience and extensibility through a stateless server, database-backed state persistence, REST APIs and Server-Sent Events (SSE), and a decoupled simulator, supporting both the standard four-player and mixed-doubles formats. In a 24 h experiment, the system recovered from all 290 timeout-induced communication failures with 100% reconnection success and a mean recovery time of about 1 s. In a server-restart experiment (), it resumed every match with full state consistency, and it ran for about 60 h over six days at Expo 2025 Osaka, Kansai, with no system-attributable failures. A load evaluation further shows that the platform sustains concurrent load and scales near-linearly, achieving 1.97× throughput across two server workers. Under these controlled conditions, the platform offers a promising foundation for continuous match operation and future strategic AI research in curling.- 9 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (14) , 6886
Open AccessA Resilient and Extensible Digital Curling Platform Using Server-Sent Events and REST APIs
Curling is strategically complex, yet data-driven strategic AI is limited by the scarcity of large-scale match data with shot-by-shot states and histories. Digital Curling provides such an environment, but no prior system has combined match resumption after failures, centralized state persistence, and a decoupled simulator into a single, reusable research platform. We propose and implement a new Digital Curling platform that improves resilience and extensibility through a stateless server, database-backed state persistence, REST APIs and Server-Sent Events (SSE), and a decoupled simulator, supporting both the standard four-player and mixed-doubles formats. In a 24 h experiment, the system recovered from all 290 timeout-induced communication failures with 100% reconnection success and a mean recovery time of about 1 s. In a server-restart experiment (), it resumed every match with full state consistency, and it ran for about 60 h over six days at Expo 2025 Osaka, Kansai, with no system-attributable failures. A load evaluation further shows that the platform sustains concurrent load and scales near-linearly, achieving 1.97× throughput across two server workers. Under these controlled conditions, the platform offers a promising foundation for continuous match operation and future strategic AI research in curling. - Open Access
Development of an Instrumented Climbing Hold with an Embedded Six-Axis Force Sensor for Speed Climbing
Understanding the interaction forces between climbers and climbing holds is important for motion analysis and performance evaluation in sport climbing. In particular, force measurement during speed climbing can provide valuable insights into explosive movements and athlete performance. However, many existing measurement systems require modifications to the climbing wall structure or sensors installed behind the wall, which limits their applicability to existing speed climbing facilities. This study proposes a wireless instrumented climbing hold for speed climbing that enables force-related measurement without modifying the wall structure. The proposed system integrates a six-axis force sensor, a microcomputer, a wireless communication module, and a battery inside the climbing hold. This self-contained configuration allows the hold to wirelessly transmit force and moment data during climbing while maintaining compatibility with standard speed climbing walls and competition environments. In addition, the system enables an estimation of the point of force application on the hold surface by combining measured force and moment data with the three-dimensional hold geometry. Experimental evaluations were conducted to verify the feasibility and performance of the system. External load tests using a digital force gauge confirmed that the embedded sensor can measure static loads and respond to rapidly changing loads with sufficient temporal responsiveness, and the estimated point of force application corresponded closely to the actual loading point. Furthermore, measurements on an actual speed climbing wall demonstrated that the proposed system can successfully capture interaction forces during climbing movements. These results indicate that the proposed system is a practical tool for force-based motion analysis in speed climbing.
Open AccessDevelopment of an Instrumented Climbing Hold with an Embedded Six-Axis Force Sensor for Speed Climbing
Understanding the interaction forces between climbers and climbing holds is important for motion analysis and performance evaluation in sport climbing. In particular, force measurement during speed climbing can provide valuable insights into explosive movements and athlete performance. However, many existing measurement systems require modifications to the climbing wall structure or sensors installed behind the wall, which limits their applicability to existing speed climbing facilities. This study proposes a wireless instrumented climbing hold for speed climbing that enables force-related measurement without modifying the wall structure. The proposed system integrates a six-axis force sensor, a microcomputer, a wireless communication module, and a battery inside the climbing hold. This self-contained configuration allows the hold to wirelessly transmit force and moment data during climbing while maintaining compatibility with standard speed climbing walls and competition environments. In addition, the system enables an estimation of the point of force application on the hold surface by combining measured force and moment data with the three-dimensional hold geometry. Experimental evaluations were conducted to verify the feasibility and performance of the system. External load tests using a digital force gauge confirmed that the embedded sensor can measure static loads and respond to rapidly changing loads with sufficient temporal responsiveness, and the estimated point of force application corresponded closely to the actual loading point. Furthermore, measurements on an actual speed climbing wall demonstrated that the proposed system can successfully capture interaction forces during climbing movements. These results indicate that the proposed system is a practical tool for force-based motion analysis in speed climbing.
- Open Access
- 18 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (10) , 5034
Curling Stone Trajectory and Collision Prediction Using a Hybrid Model Integrating Physical Models and Machine Learning
This study proposes and evaluates a hybrid framework for predicting curling stone motion by combining physical models with machine learning. Motion capture data from a curling sheet were used to train modules for sliding trajectory prediction and post-impact collision prediction. These modules were connected in an integrated rollout from a single preprocessed-frame state 1 m before the tee line to predict resting position and in-play/out-of-play status. Huber regression was used for trajectory prediction and random forest regression for collision prediction, with hybrid variants learning residual corrections to physical-model outputs. The framework was evaluated using five-fold cross-validation. In trajectory prediction, ML and hybrid variants reduced velocity error relative to the default physical model, while the tuned physical model remained competitive for direction-angle estimation. In collision prediction, ML and hybrid models improved direction-angle and angular-velocity prediction over the perfectly elastic baseline. In the integrated simulation, 867 trials were evaluated after excluding 21 trials with both measured stones out of play. The hybrid rollout achieved the lowest stop-position MAE and SD for the colliding stone and, for the collided stone, an MAE comparable to that of the ML model with the lowest SD. These results show that residual correction of simple physics-based baselines improves local prediction and final-position stability.
- 18 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (10) , 5034
Open AccessCurling Stone Trajectory and Collision Prediction Using a Hybrid Model Integrating Physical Models and Machine Learning
This study proposes and evaluates a hybrid framework for predicting curling stone motion by combining physical models with machine learning. Motion capture data from a curling sheet were used to train modules for sliding trajectory prediction and post-impact collision prediction. These modules were connected in an integrated rollout from a single preprocessed-frame state 1 m before the tee line to predict resting position and in-play/out-of-play status. Huber regression was used for trajectory prediction and random forest regression for collision prediction, with hybrid variants learning residual corrections to physical-model outputs. The framework was evaluated using five-fold cross-validation. In trajectory prediction, ML and hybrid variants reduced velocity error relative to the default physical model, while the tuned physical model remained competitive for direction-angle estimation. In collision prediction, ML and hybrid models improved direction-angle and angular-velocity prediction over the perfectly elastic baseline. In the integrated simulation, 867 trials were evaluated after excluding 21 trials with both measured stones out of play. The hybrid rollout achieved the lowest stop-position MAE and SD for the colliding stone and, for the collided stone, an MAE comparable to that of the ML model with the lowest SD. These results show that residual correction of simple physics-based baselines improves local prediction and final-position stability.
- Open Access
- 24 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (9) , 4181
TabletStone: Role-Aware, Rotation-Robust On-Stone Visualization for Curling Training
Real-time feedback is increasingly valued in sports training, yet in curling it is commonly delivered through off-stone displays or post hoc review, forcing disruptive gaze shifts while athletes track a moving and continuously rotating stone, especially during collaborative sweeping. To address this gap, we present TabletStone, a stone-mounted tablet interface that provides in situ, glanceable feedback with role-aware layouts and rotation-robust visualization. TabletStone is implemented as a lightweight, UDP-driven endpoint that renders upstream training signals on the stone while adapting the UI to throwers and sweepers. To preserve readability under rotation, we formalize an absolute-position fixation strategy based on an on-device yaw estimate and counter-rotation transforms. We evaluate TabletStone through an initial controlled user study with six experienced curlers performing sweeping while reading on-stone values under two conditions (baseline and absolute-position fixation). The study showed higher subjective readability together with improved accuracy and recall for absolute-position fixation, while precision remained high in both conditions; missed readouts remained the dominant failure mode under workload. Overall, these results support the feasibility and potential usefulness of combining role-aware UI/UX with rotation-aware stabilization for on-object feedback in curling training, while broader training effects remain to be validated.
- 24 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (9) , 4181
Open AccessTabletStone: Role-Aware, Rotation-Robust On-Stone Visualization for Curling Training
Real-time feedback is increasingly valued in sports training, yet in curling it is commonly delivered through off-stone displays or post hoc review, forcing disruptive gaze shifts while athletes track a moving and continuously rotating stone, especially during collaborative sweeping. To address this gap, we present TabletStone, a stone-mounted tablet interface that provides in situ, glanceable feedback with role-aware layouts and rotation-robust visualization. TabletStone is implemented as a lightweight, UDP-driven endpoint that renders upstream training signals on the stone while adapting the UI to throwers and sweepers. To preserve readability under rotation, we formalize an absolute-position fixation strategy based on an on-device yaw estimate and counter-rotation transforms. We evaluate TabletStone through an initial controlled user study with six experienced curlers performing sweeping while reading on-stone values under two conditions (baseline and absolute-position fixation). The study showed higher subjective readability together with improved accuracy and recall for absolute-position fixation, while precision remained high in both conditions; missed readouts remained the dominant failure mode under workload. Overall, these results support the feasibility and potential usefulness of combining role-aware UI/UX with rotation-aware stabilization for on-object feedback in curling training, while broader training effects remain to be validated.
- Open Access
- 2 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (7) , 3453
Extraction of Stone Positions from a Sheet Image for Curling Match Database Construction
Curling is a sport in which two teams take turns delivering stones on ice and compete for total scores. It is a highly strategic sport, often referred to as “Chess on Ice”. In recent years, research on curling AI and statistical analysis aimed at tactical evaluation has been active. Decision-making in curling highly depends on the current stone position state, so obtaining stone positions is essential for tactical analysis. This study proposes an object detection model capable of acquiring stone coordinates with high accuracy and generality from stone position images of actual games. The proposed model was realized with a small amount of manually annotated data and pseudo-labeled images. Using the active testing method, the image-level accuracy of data—a strict criterion requiring perfect detection of all stones in a single image—for approximately 100,000 items was estimated to be 99.37%. Furthermore, we measured the positional error of the detected stones and found an average result of 0.472 px. We determined that this model had sufficient accuracy for practical use, so we decided to store the acquired coordinates in a database and use them as training data for the curling AI and statistical analysis.
- 2 April 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16  (7) , 3453
Open AccessExtraction of Stone Positions from a Sheet Image for Curling Match Database Construction
Curling is a sport in which two teams take turns delivering stones on ice and compete for total scores. It is a highly strategic sport, often referred to as “Chess on Ice”. In recent years, research on curling AI and statistical analysis aimed at tactical evaluation has been active. Decision-making in curling highly depends on the current stone position state, so obtaining stone positions is essential for tactical analysis. This study proposes an object detection model capable of acquiring stone coordinates with high accuracy and generality from stone position images of actual games. The proposed model was realized with a small amount of manually annotated data and pseudo-labeled images. Using the active testing method, the image-level accuracy of data—a strict criterion requiring perfect detection of all stones in a single image—for approximately 100,000 items was estimated to be 99.37%. Furthermore, we measured the positional error of the detected stones and found an average result of 0.472 px. We determined that this model had sufficient accuracy for practical use, so we decided to store the acquired coordinates in a database and use them as training data for the curling AI and statistical analysis.