Method and apparatus for comparing videos
In a method of comparing a query video and a target video, frames of the query video and frames of the target video are partitioned into blocks. The mean intensity value is calculated for each block. Minima and maxima values are extracted from temporal changes of the mean intensity values for each block. Inclines and declines are obtained from the minima and maxima values. The inclines and declines are used in determining if alignment exists between the query video and the target video.
1. A method for comparing a query video and a target video including:
partitioning frames of the query video and frames of the target video into blocks;
calculating the mean intensity value for the blocks;
extracting minima and maxima values from temporal changes of the mean intensity values for the blocks, wherein the extracted minima and maxima values are major minima and major maxima values;
obtaining major inclines and major declines from the major minima and major maxima values; and
determining if alignment exists between the query video and the target video using the major inclines and major declines.
2. The method as claimed in claim 1 and including calculating the similarity distance between the query video and the target video.
3. The method as claimed in claim 2 wherein calculation of the similarity distance between the query video and the target video is carried out when alignment is found to exist.
4. The method as claimed in claim 2 and including calculating the best similarity distance and comparing the best similarity distance with a given threshold value to determine if the query video and the target video are duplicates.
5. The method as claimed in claim 1 wherein non-major minima and non-major maxima values are excluded.
6. The method as claimed in claim 1 , further comprising: representing the mean pixel intensity values in the corresponding blocks over video frame sequences as time series.
7. The method as claimed in claim 1 and including sorting major inclines and major declines according to their gradients and using those with greater gradients in determining alignment.
8. The method as claimed in claim 2 and including using sequence matching to determine the similarity distance.
9. The method as claimed in claim 2 and including using keyframe pair wise matching to determine the similarity distance.
10. The method as claimed in claim 1 and including segmenting the query video and the target video into a list of intervals and selecting major inclines/declines within the intervals, the interval size being adapted based on the length of the videos.
11. The method as claimed in claim 4 and including storing the query video in a video database holding the target video when the query video is determined not to be a duplicate of the target video.
12. A device programmed or configured to perform a method comprising:
partitioning frames of the query video and frames of the target video into blocks;
calculating the mean intensity value for the blocks;
extracting minima and maxima values from temporal changes of the mean intensity values for the blocks, wherein the extracted minima and maxima values are major minima and major maxima values;
obtaining major inclines and major declines from the major minima and major maxima values; and
determining if alignment exists between the query video and the target video using the major inclines and major declines.
13. The device as claimed in claim 12 and programmed or configured to calculate the similarity distance between the query video and the target video.
14. The device as claimed in claim 12 and programmed or configured such that calculation of the similarity distance between the query video and the target video is carried out when alignment is found to exist.
15. The device as claimed in claim 12 and programmed or configured to calculate the best similarity distance and to compare the best similarity distance with a given threshold value to determine if the query video and the target video are duplicates.
16. The device as claimed in claim 12 wherein non-major minima and non-major maxima values are excluded.
17. The device as claimed in claim 12 and programmed or configured represent the mean pixel intensity values in the corresponding blocks over video frame sequences as time series.
18. The device as claimed in claim 12 and programmed or configured to sort major inclines and major declines according to their gradients and to use those with greater gradients in determining alignment.
19. The device as claimed in claim 13 and programmed or configured to use sequence matching to determine the similarity distance.
20. The device as claimed in claim 13 and programmed or configured to use keyframe pair wise matching to determine the similarity distance.
21. The device as claimed in claim 12 and programmed or configured to segment the query video and the target video into a list of intervals and to select major inclines/declines within each interval, the interval size being adapted based on the length of the videos.
22. The device as claimed in claim 15 and programmed or configured to store the query video in a video database holding the target video when the query video is determined not to be a duplicate of the target video.
23. A non-transitory computer-readable medium storing a machine-executable program for performing a method of managing video content comprising:
partitioning frames of the query video and frames of the target video into blocks;
calculating the mean intensity value for the blocks;
extracting minima and maxima values from temporal changes of the mean intensity values for the blocks, wherein the extracted minima and maxima values are major minima and major maxima values;
obtaining major inclines and major declines from the major minima and major maxima values; and
determining if alignment exists between the query video and the target video using the major inclines and major declines.