Sequence Matching for Content-Based Video Retrieval
Sergii Mashtalir, Olena Mikhnova, Mykhailo I. Stolbovyi · 2018
In this paper the authors propose a novel technique for comparing video frame sequence presented in an arbitrary metric space. By reviewing existing best practices in spatio-temporal video segmentation and frame matching, the authors suggest mathematical grounding for efficient video content analysis. Variants of relationships are observed between the frame sequences under comparison (perfect match, inclusion, equality of cardinality of sets). Examples of application as well as estimation metrics are also provided.