Automatic Data Collection using In-vehicle Camera Images for Training Machine Learning-based Local Image Feature Matchers

Haruya Kyutoku, Tokihiko Akita, Seiichi Mita

Abstract: Local image features matching is a useful technique for 3D reconstruction and localization in ITS field. In recent years, machine learning-based local feature matching methods have been proposed. However, it is impractical to manually generate the ground truth of corresponding points used as training data on these methods. Therefore, for in-vehicle camera images we propose an automatic training data collection method using geometric constraints and continuity with the movement of the vehicle. The experimental results show that the proposed method can provide effective corresponding points for training a machine learning-based matcher.