Image Compression

• US 20200134835A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Wind River Systems Incorporated (Aptiv PLC)
• Original Assignee: Wind River Systems Incorporated (Aptiv PLC)
• Inventors: Koning, Maarten, Dragusu, Mihai
• Granted Patent: US 11,222,427 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06T 3/18 Image warping, e.g. rearranging pixels individually
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 9/00 Image coding bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/267 by performing operations on regions, e.g. growing, shrinking or watersheds
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A device, system, and method performs an image compression. The method includes receiving raw image data of an image and identifying objects in the image as one of a foreground object or a background object. The method includes generating first foreground image data for a first foreground object. The method includes generating first metadata for a first background object. The first metadata indicates a first identity and a first descriptive parameter for the first background object. The first descriptive parameter relates to how the first background object is situated in the image. The method includes generating first background image data for the first background object. The first background image data is empty data. The method includes storing processed image data for the image comprising the first foreground image data, the first metadata, and the first background image data.

Claims

1. A method, comprising:

at a compression server;

receiving raw image data of an image;

identifying objects in the image as one of a foreground object or a background object;

generating first foreground image data for a first foreground object;

generating first metadata for a first background object, the first metadata indicating a first identity and a first descriptive parameter for the first background object, the first descriptive parameter relating to how the first background object is situated in the image;

generating first background image data for the first background object, the first background image data being empty data; and

storing processed image data for the image comprising the first foreground image data, the first metadata, and the first background image data.

2. The method of claim 1, wherein the first metadata further indicates image information associated with the image.

3. The method of claim 2, wherein the image information includes a time and a location at which the image was captured.

4. The method of claim 1, wherein the first descriptive parameter indicates one of a perspective of the background object, a coloring of the background object, a shading of the background object, a brightness of the background object, a size of the background object, or a combination thereof.

5. The method of claim 1, wherein the first foreground image data and the first metadata indicate a relative position of the first foreground object and the first background object, respectively, in the image.

6. The method of claim 1, wherein the identifying of the objects as one of the foreground object or the background object comprises:

determining a significance score for each of the objects;

labeling the objects having the significance score greater than a significance threshold as the foreground object; and

labeling the objects having the significance score less than the significance threshold as the background object.

7. The method of claim 6, wherein the significance score is based on one of an individual capacity, a holistic capacity, or a combination thereof.

8. The method of claim 1, further comprising:

receiving a request to recreate the image based on the processed image data;

recreating the first foreground object using the first foreground image data;

approximating the first background object using the first metadata; and

recreating the image to include the first foreground object and the first background object.

9. The method of claim 8, wherein the approximating the first background object using the first metadata comprises:

retrieving an approximation image based on the first identity of the first background object; and

modifying the approximation image based on the first descriptive parameter.

10. The method of claim 1, wherein the empty data converts the background object to a monotone.

11. A compression server, comprising:

a transceiver configured to receive a raw image data of an image; and

a processor configured to identify objects in the image as one of a foreground object or a background object, the processor configured to generate first foreground image data for a first foreground object, the processor configured to generate first metadata for a first background object, the first metadata indicating a first identity and a first descriptive parameter for the first background object, the first descriptive parameter relating to how the first background object is situated in the image, the processor configured to generate first background image data for the first background object, the first background image data being empty data,

wherein processed image data for the image is configured to be stored by comprising the first foreground image data, the first metadata, and the first background image data.

12. The compression server of claim 11, wherein the first metadata further indicates image information associated with the image.

13. The compression server of claim 12, wherein the image information includes a time and a location at which the image was captured.

14. The compression server of claim 11, wherein the first descriptive parameter indicates one of a perspective of the background object, a coloring of the background object, a shading of the background object, a brightness of the background object, a size of the background object, or a combination thereof.

15. The compression server of claim 11, wherein the first foreground image data and the first metadata indicate a relative position of the first foreground object and the first background object, respectively, in the image.

16. The compression server of claim 11, wherein the processor identifies the objects as one of the foreground object or the background object by:

determining a significance score for each of the objects;

labeling the objects having the significance score greater than a significance threshold as the foreground object; and

labeling the objects having the significance score less than the significance threshold as the background object.

17. The compression server of claim 16, wherein the significance score is based on one of an individual capacity, a holistic capacity, or a combination thereof.

18. The compression server of claim 12, wherein the transceiver is configured to receive a request to recreate the image based on the processed image data, and wherein the processor recreates the first foreground object using the first foreground image data, the processor approximates the first background object using the first metadata, and the processor recreates the image to include the first foreground object and the first background object.

19. The compression server of claim 18, wherein the processor approximates the first background object using the first metadata by:

retrieving an approximation image based on the first identity of the first background object; and

modifying the approximation image based on the first descriptive parameter.

20. A method, comprising:

at a compression server;

receiving a request to recreate an image based on processed image data, the processed image data including foreground image data, metadata, and background image data, the foreground image data corresponding to at least one identified foreground object, the metadata indicating a respective identity for at least one identified background object, the metadata further indicating a descriptive parameter for each of the at least one identified background object, the descriptive parameter relating to how each of the at least one background object is situated in the image, the background image data being empty data;

recreating each foreground object using the foreground object data;

approximating each background object using the metadata; and

recreating the image.