Methods and Apparatus for Providing a Scalable Identification of Digital Video Sequences
First Claim
1. A method for content based video sequence identification comprising:
- determining active regions in frames of a video sequence;
selecting a set of video frames in response to temporal statistical characteristics of the determined active regions;
extracting video features of the selected video frames; and
generating multi-dimensional content based signatures based on the extracted video features that identify the video sequence.
14 Assignments
0 Petitions
Accused Products
Abstract
Scaleable video sequence processing with various filtering rules is applied to extract dominant features, and generate unique set of signatures based on video content. Video sequence structuring and subsequent video sequence characterization is performed by tracking statistical changes in the content of a succession of video frames and selecting suitable frames for further treatment by region based intra-frame segmentation and contour tracing and description. Compact representative signatures are generated on the video sequence structural level as well as on the selected video frame level, resulting in an efficient video database formation and search.
178 Citations
25 Claims
-
1. A method for content based video sequence identification comprising:
-
determining active regions in frames of a video sequence; selecting a set of video frames in response to temporal statistical characteristics of the determined active regions; extracting video features of the selected video frames; and generating multi-dimensional content based signatures based on the extracted video features that identify the video sequence. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A method for content based video database formation, the method comprising:
-
processing a video sequence by video frame filtering, temporal statistic collection, and frame selection to produce analysis results; selecting active video frame areas based on the analysis results; segmenting video frames utilizing the selected active frame areas into regions delineated by computed contours; tracing the computed contours to produce a vector of contiguous spatial coordinates for each video frame; processing each vector of contiguous spatial coordinates to provide a contour pixel gradient vector orientation and magnitude for selected contours; generating for each of the selected contour a signature based on the contour pixel gradient vector orientation and magnitude; and forming a content based video database to hold the signatures. - View Dependent Claims (16, 17, 18, 19)
-
-
20. A method for video sequence structuring, the method comprising:
-
computing mean absolute value of difference (MAD) values for video frame active regions in a succession of video frames in a video sequence of video frames; generating a temporal statistical function f0(n) in response to the MAD values, the f0(n) function is a time series with its samples having identical values as the MAD values; partitioning the video sequence with a programmable size sliding window into multiple spatial partitions; attaching a starting point of the programmable size sliding windows to local extrema f0(n) values of the previous programmable size sliding window; selecting frames within each programmable size sliding window at the position of the local extrema f0(n) values; segmenting the selected frames into areas of similar light intensity and color having image contours; and processing the contours to extract features of the selected frame to identify the video sequence to be held in a signature database. - View Dependent Claims (21, 22, 23, 24, 25)
-
Specification