||Scene Mapping-based Video Registration Using Frame Similarity Measurement and Feature Tracking
||Vidya Sawant;Jinbeum Jang;Joonki Paik
||Video registration; Frame similarity; Feature tracking; Feature matching
||Video registration is a technique that obtains pairs of frames showing the same scene to synchronize two videos. This paper presents a video registration algorithm based on scene mapping using frame similarity measurement and feature point tracking. The proposed algorithm consists of four steps: i) frame-to-frame matching based on similarity measurement to set the start frame, ii) feature tracking using feature points of the start frame to obtain a candidate matching scene, iii) end-frame matching for scene mapping, and iv) synchronization of two videos using a linear equation. In the proposed algorithm, frame-to-frame matching is performed using traditional feature detection and matching. Additionally, the proposed algorithm measures the similarity between frames to register videos with the most similar structural information. Feature point tracking is performed to track and collect similar structures in a candidate scene. We demonstrate that the proposed algorithm can synchronize frames from registered videos for some experiments.
Therefore, the proposed algorithm can be applied to various areas.