Back to results
US 10,949,675 B2Granted
Image summarization system and method
AssigneeKt Corporation
InventorsTae Heon Park, Kwang Jung Kim, Jae Cheol Kwon, Bong-Ki Kim, Mi-Sook Lee
Life of this patent
Estimating the term…
Abstract
To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and selects objects which match a selection condition among extracted objects as a queue object. The image summarization system generates a summarized video based on the queue object and a background frame.
Claims27
A method comprising receiving an image stream of a control image collected by a camera;
- detecting, in the image stream, a background frame and all objects appearing in the image stream;
- assigning identification information to each newly detected object and identifying frame identification information for each frame in which the newly detected object is detected;
- selecting objects, from among the detected objects, which match a user input selection condition as a queue object;
- tracking, from among the selected objects, a valid object which is an object of which a number of detection times in a frame is greater than a predetermined threshold value in a plurality of frames;
- generating object metadata for the valid object;
- and
- generating a summarized video based on the object metadata of the queue object and the background frame.
4 more elements
A system comprising:
- a memory storing an image summarization program;
- and
- a processor that executed the image summarization program stored in the memory, which causes the processor to:
- receive an image stream of a control image collected by a camera;
- detect, in the image stream, a background frame and all objects appearing in the image stream;
- assign identification information to each newly detected object and identifying frame identification information for each frame in which the newly detected object is detected;
- select objects, from among the detected objects, which match a user input selection condition as a queue object;
- track, from among the selected objects, a valid object which is an object of which a number of detection times in a frame is greater than a predetermined threshold value in a plurality of frames;
- generate object metadata for the valid object;
- and
- generate a summarized video based on the object metadata of the queue object and the background frame.
8 more elements
Dependencies are inferred from the claim text.