摘要 |
Mining a video stream for repeating video sequences includes receiving a video stream and generating hash values for the frames. Frames with matching hash values are identified and are used to identify candidate sub-sequences of frames. The sub-sequences are compared and when a threshold level of frames with hash values matched to frames of another sub-sequence are detected, a match is identified. Longer sequences are identified from the matched sub-sequences and examined to determine if they are similar. If they are, start and end frames are detected. A fingerprint of the repeating sequence is created by the system (4) and added to a database (5), with updates being sent to a reference database (9) of an automated detection and replacement apparatus (6). The output (8, 10) of the apparatus is switched according to whether a match is detected in a broadcast. Commercials or adverts are thereby detected and replaced on a live video broadcast. |