Analysis to Feature-Based Video Stabilization/Registration Techniques within Application of Traffic Data Collection

Machine vision is rapidly gaining popularity in various applications, among others in the field of Intelligent Transportation Systems. In particular, potential advantages are foreseen by the exploitation of Aerial Vehicles (AV) in delivering a superior view on traffic phenomena. However, vibration on AVs makes it difficult to extract moving objects on the ground. To partly overcome this issue, image stabilization/registration procedures are adopted to correct and stitch multiple frames taken of the same scene but from different positions, angles, or sensors. In this study, we aim to examine the impact of multiple feature-based techniques for video stabilization using different scenarios. In the proposed framework, SURF detector outperformed the others in terms of time efficiency and output similarity.