Image adjustment method, apparatus, device and computer readable storage medium

1. An image adjustment method, comprising:

determining a distance between a user and a display apparatus;

determining, according to a relationship between the distance and a foreground image or a background image displayed on the display apparatus, a target image to which action information of the user is directed, wherein the target image comprises at least one of the foreground image and the background image;

determining an adjustment manner corresponding to the action information of the user; and

adjusting the target image according to the adjustment manner,

wherein the determining of the target image comprises: when the distance is within a first distance range, determining the foreground image as the target image; and when the distance is within a second distance range different from the first distance range, determining the background image as the target image.

2. The method according to claim 1 , further comprising:

acquiring a second image in a case of displaying a first image, before determining the distance between the user and the display apparatus; and

displaying, on the display apparatus, the first image as the background image and the second image as the foreground image.

3. The method according to claim 2 , wherein acquiring a second image comprises:

capturing a third image; and

extracting a preset type of object from the third image as the second image.

4. The method according to claim 1 , further comprising:

if the target image comprises one of the foreground image and the background image, fusing the adjusted one of the foreground image and the background image with the other one of the foreground image and the background image; and

if the target image comprises both the foreground image and the background image, fusing the adjusted foreground image with the adjusted background image.

5. The method according to claim 1 , wherein a correspondence relationship between the action information and the adjustment manner is predetermined by:

constructing a training set composed of action information and adjustment manners; and

performing training through deep learning based on the training set to determine the correspondence relationship between the action information and the adjustment manner.

6. An image adjustment device, comprising:

a processor; and

a memory coupled to the processor and having instructions stored thereon and executable by the processor;

wherein the instructions, when executed by the processor, cause the processor to be configured to:

determine a distance between a user and a display apparatus;

determine, according to a relationship between the distance and a foreground image or a background image displayed on the display apparatus, a target image to which action information of the user is directed, wherein the target image comprises at least one of the foreground image and the background image;

determine an adjustment manner corresponding to the action information of the user; and

adjust the target image according to the adjustment manner, and

wherein the processor is further configured to: determine the foreground image as the target image, when the distance ii within a first distance range; and determine the background image as the target image, when the distance is within a second distance range different from the first distance range.

7. The device according to claim 6 , wherein the processor is further configured to:

acquire a second image in a case of displaying a first image; and

display, on the display apparatus, the first image as the background image and the second image as the foreground image.

8. The device according to claim 7 , wherein the processor is further configured to:

capture a third image; and

extract a preset type of object from the third image as the second image.

9. The device according to claim 6 , wherein the processor is further configured to:

if the target image comprises one of the foreground image and the background image, fuse the adjusted one of the foreground image and the background image with the other one of the foreground image and the background image; and if the target image comprises both the foreground image and the background image, fuse the adjusted foreground image with the adjusted background image.

10. The device according to claim 6 , wherein the processor is further configured to:

construct a training set composed of action information and adjustment manners; and

perform training through deep learning based on the training set to determine the correspondence relationship between the action information and the adjustment manner.

11. A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method according to claim 1 .