Tennis is a popular sport, and integrating modern technological advancements can greatly enhance player training. Human pose estimation has seen substantial developments recently, driven by progress in deep learning. The dataset described in this paper was compiled from videos of researchers’ friend playing tennis. These videos were retrieved frame by frame to categorize various tennis movements, and human skeleton joints were annotated using COCO-Annotator to generate labelled JSON files. By combining these JSON files with the classified image set, we constructed the dataset for this paper. This dataset enables the training and validation of four tennis postures, forehand shot, backhand shot, ready position, and serves, using deep learning models (such as OpenPose). The researchers believe that this dataset will be a valuable asset to the tennis community and human pose estimation field, fostering innovation and excellence in the sport.

The present five masks bottom gate and staggered amorphous silicon (a-Si) thin-film transistor (TFT) process flow is not suitable for indium–gallium–zinc-oxide (IGZO) TFT because of its vulnerability to post etching process during the source/drain pattern. Bottom gate and coplanar IGZO TFTs were made feasible through the reverse of second (channel layer) and third (source/drain electrodes) masks process flow to avoid etching damage problem. Besides, the post IGZO nitrous oxygen (N₂O) plasma treatment was employed to improve the stress instability. On the basis of secondary ion mass spectrometry (SIMS) and X-ray spectroscopy (XPS) results, it is believed that the post N₂O plasma treatment passivates the interface states and converts the inhomogeneous and low quality IGZO to the homogeneous and high quality IGZO. In the end, a 5-in. IGZO active-matrix liquid crystal display was demonstrated via five masks bottom gate and coplanar TFT configuration.

Tennis is a popular sport, and the introduction of technology has allowed players to diversify their training. Tennis ball tracking is currently a focal point, serving not only to assist referees but also to enhance sports analysis. We introduce the Tennis Shot Side-View and Top-View Dataset, which serves as an invaluable resource for analyzing tennis movements and verifying landing positions after flight. This dataset combines side-view and top-view video clips, capturing various shot types and player movements from both outdoor and indoor fields. The dataset includes the actual ball positions of each clip for verification purposes. The Tennis Shot Side-View and Top-View Dataset represents a significant advancement in tennis research. Its multidimensional nature opens doors for in-depth player analysis, performance enhancement, and strategy development. We believe that this dataset will be a valuable asset to the tennis community, fostering innovation and excellence in the sport.

Precise timing of ball-racket contact is a critical determinant of stroke performance in tennis, yet few studies have objectively quantified this variable across different players’ groups. This study developed and validated a hybrid vision-based framework combining K-nearest neighbors (KNN) background subtraction with Hue-Saturation-Value (HSV) color segmentation to analyze the spatial relationship between the contact point and the apex of the ball’s trajectory. Twelve participants were recruited and stratified by skill level and gender, each performing 30 forehand and 30 backhand strokes, yielding 720 stroke events. Contact point overlap ratios and vertical height distributions were extracted, and two-way ANOVA was used to examine main and interaction effects. Results indicated a significant effect of the skill level, with top-level players demonstrating higher overlap ratios and reduced vertical deviations compared to average-level players (p < 0.001, partial η² = 0.386). Gender differences were negligible among top-level players but pronounced in the average-level group, particularly for backhand strokes (p < 0.001). These findings highlight the skill level as the dominant factor influencing contact point precision, while gender disparities emerge primarily among less experienced athletes. The proposed computer vision approach offers a low-cost and scalable tool for objective stroke assessment and has potential applications in individualized training feedback and performance monitoring.