System And Method For Representing Long Video Sequences
AssigneeVisible World, Inc.
InventorErik Van de Pol
Life of this patent
Estimating the term…
Abstract
Systems and procedures for transforming video into a condensed visual representation. An example procedure may include receiving video comprised of a plurality of frames. For each frame, the example procedure may create a first representation, reduced in one dimension, wherein a visual property of each pixel of the first representation is assigned by aggregating a visual property of the pixels of the frame having the same position in the unreduced dimension. The example procedure may further form a condensed visual representation including the first representations aligned along the reduced dimension according to an order of the frames in the video.
Claims20
A method comprising:
- receiving content comprising a plurality of frames;
- condensing the content to determine a condensed visual representation and metadata for each frame of the plurality of frames;
- determining, based on the condensed visual representation, a transition or an insertion point in the content;
- and
- causing display of the condensed visual representation and an identifier of the transition or the insertion point relative to the condensed visual representation.
A device comprising:
- one or more processors;
- and
- memory storing instructions that, when executed by the one or more processors, cause the device to:
- receive content comprising a plurality of frames;
- condense the content to determine a condensed visual representation and metadata for each frame of the plurality of frames;
- determine, based on the condensed visual representation, a transition or an insertion point in the content;
- and
- cause display of the condensed visual representation and an identifier of the transition or the insertion point relative to the condensed visual representation.
A computer-readable medium storing instructions that, when executed, cause:
- receiving content comprising a plurality of frames;
- condensing the content to determine a condensed visual representation and metadata for each frame of the plurality of frames;
- determining, based on the condensed visual representation, a transition or an insertion point in the content;
- and
- causing display of the condensed visual representation and an identifier of the transition or the insertion point relative to the condensed visual representation.
Dependencies are inferred from the claim text.