“…Of the 21 papers reviewed in this review, 14 (66.67%) ( [10], [11], [12], [15], [18], [19], [20], [21], [23], [26], [27], [28], [29], [30]) were studies related to dynamic gestures. Eight studies (33.3%) ( [13], [14], [16], [17]) were conducted to recognize static gestures based on precise position estimation technology for various still motions by attaching many markers to specific body parts ( [24], [25], [27], [28]). For performance evaluation, various performance indices such as accuracy, F1 score, and error rate were used, as the degree of improvement in accuracy compared to previous studies, comparison of accuracy using various algorithms, and normalization using independent data other than the data used to create the learning model.…”