US 12,003,744 B2 · Hierarchical surveilance video compression repository

Abstract

Apparatus and methods for processing video surveillance data includes training a data repository, using a first plurality of surveillance video files including a first plurality of video frames, to identify macroblocks of the video frames representing average content of the first plurality of surveillance video files. An ordered data structure is generated by sorting the plurality of macroblocks of video frames based on image differences within the plurality of macroblocks. The ordered data structure includes a root node. A second plurality of surveillance video files including a second plurality of video frames is received. The second plurality of video frames is inserted into the generated ordered data structure. References to the generated ordered data structure are stored in the data store for each frame of the second plurality of video frames along with a difference between corresponding video frames and references.

Claims14

Dependent claims

A method for processing video surveillance data comprising:

calculating average pixel values of corresponding macroblocks in intraframes in each of a first plurality of surveillance video files comprising a first plurality of video frames over a period of time;
generating an ordered data structure of a plurality of macroblocks of video frames contained in each of the first plurality of surveillance video files by sorting the plurality of macroblocks of video frames based on image differences within the plurality of macroblocks, wherein the ordered data structure includes a root node, wherein the root node comprises a frame that comprises one or more macroblocks having the average pixel values;
receiving a second plurality of surveillance video files comprising a second plurality of video frames;
inserting the second plurality of video frames into the ordered data structure;
and
storing, in a data repository, references to the ordered data structure for each frame of the second plurality of video frames and a difference between corresponding video frames and the references.

3 more elements

A system for processing video surveillance data comprising:

a hardware processor configured to:
calculate average pixel values of corresponding macroblocks in intraframes in each of a first plurality of surveillance video files comprising a first plurality of video frames over a period of time;
generate an ordered data structure of a plurality of macroblocks of video frames contained in each of the first plurality of surveillance video files by sorting the plurality of macroblocks of video frames based on image differences within the plurality of macroblocks, wherein the ordered data structure includes a root node, wherein the root node comprises a frame that comprises one or more macroblocks having the average pixel values;
receive a second plurality of surveillance video files comprising a second plurality of video frames;
insert the second plurality of video frames into the ordered data structure;
and
store, in a data repository, references to the ordered data structure for each frame of the second plurality of video frames and a difference between corresponding video frames and references.

4 more elements

Dependencies are inferred from the claim text.

Hierarchical surveilance video compression repository

Life of this patent

Hierarchical surveilance video compression repository

Life of this patent

Abstract

Claims14