An Evaluation Method of Obstacle Avoidance Behavior on Bicycle Trip Using Rider's Gesture

摘要

This paper proposes a method for evaluation of obstacle avoidance behavior on bicycle trips in videos using rider's gesture based on OpenPose. Since a bicycle is a vehicle which is ridden by rotating a wheel with load transfer of a rider, there is a high correlation between bicycle behavior and rider's gesture. Therefore, we evaluate the obstacle avoidance behavior based on rider's gesture. In the proposed method, features about rider's gesture are obtained by utilizing OpenPose. In addition, support vector machines (SVMs) are constructed based on the features. Our method detects the obstacle avoidance behavior and classifies that to a degree of danger. Experimental results show the effectiveness of our method.