The computer vision applications in intelligent tutoring systems (ITS) have enabled its use in various domains such as dance and sports. The adaptation in the tutoring system is based on the analysis of hand gestures, body postures, and movement. All these are termed as gross body movements (GBM). The use of these in the intelligent tutoring systems is termed as GBM-ITS in this article. There is no survey paper that considers the use of GBM-ITS in different domains. A systematic process is followed to address six review questions (RQs) by considering the 33 articles published between 2010 to 2022. A brief discussion regarding the methods adopted for analysis and the performance metrics used for evaluation has been made. The use of devices for the purpose of the study is analyzed with the need for its use. The feedback mechanisms adopted by the studies are reviewed. The information derived from the survey by addressing the RQs has been summarised as observations. This review results indicate the impact of GBM-ITSs in various domains and its potential to reduce human interventions significantly in the near future. Some of the future directions the review results indicated are: 1. the state-of-the-art computer vision methods for detection and tracking along with the temporal aspects are not much explored in GBM-ITS. 2. the current GBM-ITS are designed for beginners, and there is a vast scope to extend it for intermediate and experts. 3. the test users are considerably less, and there is a need for large-scale implementations and testing for generalizability or to check robustness. 4. more importance can be given to privacy and ethics as the GBM-ITS is performing better 5. since most methods use machine/deep learning methods, dataset dissemination will increase the design and development of GBM-ITS. 6. mechanism used in providing feedback needs to be evaluated and optimized.
- Inicie sesión para enviar comentarios