VR rehabilitation is a rapidly evolving field, with increasing research and development aimed at improving its effectiveness, accessibility, and integration into mainstream healthcare systems. While there are some commercially available VR rehabilitation programs, their adoption and use in clinical practice are still limited. One of the limitations is defined as cybersickness, which is dependent on human contact with virtual reality products. The purpose of this essay is to raise awareness of the associated elements that contribute to cybersickness in rehabilitation using immersive VR. The common factors that influence the amount of cybersickness are user characteristics and device software and hardware. The Simulator Sickness Questionnaire (SSQ) was used as one of the formal models for determining the variables related to virtual reality sickness. The systematic review of the literature and the meta-analysis were chosen by whether the Simulator Sickness Questionnaire in the articles matched the research criteria. Based on PRISMA guidelines, a systematic review of the literature was conducted. Twenty-six publications from the recent past were totaled, comprising 862 individuals with ages ranging from 19 to 95, and 49% were female. The highest overall SSQ mean score for different kinds of symptoms was determined to be 21.058 for brain injuries, with a 95% confidence interval (CI) of 15.357 to 26.760. Time, content, locomotion, control, and display types were other elements that contributed to cybersickness and had significant p-values in the SNK Q-test. The future direction of immersive VR rehabilitation involves the development of immersive and interactive environments that simulate real-world situations, providing patients with a safe and controlled environment in which to practice new skills and movements.

Human pose estimation has a wide range of applications in the field of computer vision, especially in sports event analysis where its importance is increasingly prominent. This study aims to optimize the basketball player detection model based on OpenPose, improving its performance in real-world scenarios. Firstly, we replace the VGG19 network in Openpose with a lightweight MobileNet structure to increase computational efficiency and reduce model parameters. Secondly, we introduce the Pyramid Spatial Attention (PSA) module into MobileNet to better capture local and global contextual information. Lastly, we adopt the Adaptive Wing Loss as the loss function, making the model more stable and accurate in localization. We pre-train the model on the COCO2017 dataset and conduct experiments on basketball player detection tasks. The experimental data show that, compared to the baseline model, our full model has significant improvements in Average Precision (AP), AP50, and running speed (FPS) metrics. Specifically, the full model achieves an AP of 70.0%, AP50 of 88.0%, and FPS of 41. The research results of this study can provide more accurate pose estimation information for basketball game analysis, contributing to the improvement of game strategy formulation and player performance evaluation.