Pose Classification in Archery Sports Based on YoloV8 Using SVM and Random Forest Methods

This research creates a YOLOv8-based pose classification system that can analyze and classify the movements of
archery athletes. The system is combined with SVM and RF methods, and utilizes YoloV8 pose detection and machine
learning techniques to provide more accurate classification. Video data collection, system design and implementation, and
analysis of implementation results are some of the stages passed during system development. The process includes joint
feature extraction using YOLOv8 and classification for Recurve and Barebow categories using SVM and RF. The test results
show the difference in performance between the two classification methods. For the Recurve category, SVM had 90%
accuracy for testing, while RF had 87% accuracy for testing. For the Barebow category, SVM had 76% accuracy for testing,
while RF had 75% accuracy for testing. In terms of generalization, the two methods differed, with SVM showing better
stability between testing and training performance. The results show that SVM is superior when testing when compared to
RF which makes an anomaly with previous studies