Faster than real-time detection of shot boundaries, sampling structure and dynamic keyframes in video
This addresses fundamental video analysis tasks for applications requiring efficient preprocessing, though it appears incremental in improving speed and robustness.
The paper tackles the problem of detecting shot boundaries, sampling structure, and dynamic keyframes in video, presenting a novel algorithm that achieves four times faster than real-time performance with high robustness in challenging conditions.
The detection of shot boundaries (hardcuts and short dissolves), sampling structure (progressive / interlaced / pulldown) and dynamic keyframes in a video are fundamental video analysis tasks which have to be done before any further high-level analysis tasks. We present a novel algorithm which does all these analysis tasks in an unified way, by utilizing a combination of inter-frame and intra-frame measures derived from the motion field and normalized cross correlation. The algorithm runs four times faster than real-time due to sparse and selective calculation of these measures. An initial evaluation furthermore shows that the proposed algorithm is extremely robust even for challenging content showing large camera or object motion, flashlights, flicker or low contrast / noise.