Systems and Methods for Semantically Classifying and Normalizing Shots in Video
First Claim
1. A method for classifying a video file according to one or more scene classes, the video file including a plurality of frames, where each frame includes a plurality of pixels, and where each pixel is associated with a vector of material classification scores describing the material content in its respective frame, comprising the steps of:
- (a) dividing each frame into a plurality of grid cells;
(b) for each frame, retrieving the vector of material classification scores for each pixel in each grid cell;
(c) for each grid cell, averaging the material classification scores across each pixel in the grid cell to form a material occurrence vector for the grid cell;
(d) concatenating the material occurrence vectors for the plurality of grid cells in each frame to generate a material arrangement vector for each frame;
(e) generating a scene classification score associated with each of the one or more scene classes for each frame in the video file via one or more scene classifiers based on the material arrangement vectors generated for each frame;
(f) generating a representative scene classification score for the video file for each of the one or more scene classes based on the scene classification scores generated for each frame; and
(g) if one of more of the representative scene classification scores is above a predetermined threshold value, labeling the video file according to the respective scene classes associated with the one or more scene classification scores that are above the predetermined threshold value.
10 Assignments
0 Petitions
Accused Products
Abstract
The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
-
Citations
15 Claims
-
1. A method for classifying a video file according to one or more scene classes, the video file including a plurality of frames, where each frame includes a plurality of pixels, and where each pixel is associated with a vector of material classification scores describing the material content in its respective frame, comprising the steps of:
-
(a) dividing each frame into a plurality of grid cells; (b) for each frame, retrieving the vector of material classification scores for each pixel in each grid cell; (c) for each grid cell, averaging the material classification scores across each pixel in the grid cell to form a material occurrence vector for the grid cell; (d) concatenating the material occurrence vectors for the plurality of grid cells in each frame to generate a material arrangement vector for each frame; (e) generating a scene classification score associated with each of the one or more scene classes for each frame in the video file via one or more scene classifiers based on the material arrangement vectors generated for each frame; (f) generating a representative scene classification score for the video file for each of the one or more scene classes based on the scene classification scores generated for each frame; and (g) if one of more of the representative scene classification scores is above a predetermined threshold value, labeling the video file according to the respective scene classes associated with the one or more scene classification scores that are above the predetermined threshold value. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15)
-
Specification