Augmented reality guiding method, apparatus, electronic device and computer-readable storage medium

1. An augmented reality (AR) guiding method applied to an AR device, comprising:

obtaining a real-time surrounding image and a focus of a user's line of sight in the real-time surrounding image;

performing an image recognition process on the real-time surrounding image to obtain a first set of surrounding feature points;

obtaining a marked sample image corresponding to the real-time surrounding image;

screening the surrounding feature points in the first set of surrounding feature points based on the marked sample image to obtain a second set of surrounding feature points;

determining a first surrounding image based on the second set of surrounding feature points, the first surrounding image including at least one image area, and a density of the surrounding feature points in each image area being greater than a density threshold;

determining a guide sign sequence based on the at least one image area; and

displaying at least one guide animation based on the guide sign sequence, each guide animation being used to guide the focus of the user's line of sight from a current guide sign to a subsequent guide sign.

2. The AR guiding method according to claim 1 , wherein screening the surrounding feature points in the first set of surrounding feature points to obtain the second set of surrounding feature points based on the marked sample image comprises:

determining a feature descriptor of each surrounding feature point in the marked sample image to obtain a first set of feature descriptors;

determining the feature descriptor of each surrounding feature point in the first set of surrounding feature points to obtain a second set of feature descriptors;

determining a similarity between each feature descriptor in the first set of feature descriptors and each feature descriptor in the second set of feature descripts; and

determining the surrounding feature point whose similarity satisfies a similarity threshold as an element in the second set of surrounding feature points.

3. The AR guiding method according to claim 1 , wherein determining the first surrounding image based on the second set of surrounding feature points comprises:

reconstructing a second surrounding image based on the second set of surrounding feature points;

dividing the second surrounding image into at least one image area;

determining the densities of the surrounding feature points in the at least one image area; and

determining each image area where the density of the surrounding feature points is greater than the density threshold as the image area in the first surrounding image.

4. The AR guiding method according to claim 1 , each image area corresponding to one guide sign, wherein determining the guide sign sequence based on the at least one image area comprises:

sorting the at least one image area based on the density of the surrounding feature points in each image area to obtain an observation order of the at least one image area; and

determining an order of guide signs to obtain the guide sign sequence based on the observation order.

5. The AR guiding method according to claim 1 , further comprising:

in response to the focus of the user's line of sight not moving from the current guide sign to the subsequent guide sign, repeatedly displaying the at least one guide animation.

6. The AR guiding method according to claim 1 , further comprising:

obtaining a target position of the focus of the user's line of sight;

obtaining a surrounding image at the target position; and

in response to no surrounding feature point appearing at the target position in the surrounding image, outputting a prompt message of moving a position.

7. An augmented reality (AR) guiding device, comprising:

a memory storing program instructions; and

a processor couple to the memory;

wherein when being executed by the processor, the program instructions cause the processor to:

obtain a real-time surrounding image and a focus of a user's line of sight in the real-time surrounding image;

perform an image recognition process on the real-time surrounding image to obtain a first set of surrounding feature points;

obtain a marked sample image corresponding to the real-time surrounding image;

screen the surrounding feature points in the first set of surrounding feature points based on the marked sample image to obtain a second set of surrounding feature points;

determine a first surrounding image based on the second set of surrounding feature points, the first surrounding image including at least one image area, and a density of the surrounding feature points in each image area being greater than a density threshold;

determine a guide sign sequence based on the at least one image area; and

display at least one guide animation based on the guide sign sequence, each guide animation being used to guide the focus of the user's line of sight from a current guide sign to a subsequent guide sign.

8. The AR guiding device according to claim 7 , wherein when screening the surrounding feature points in the first set of surrounding feature points to obtain the second set of surrounding feature points based on the marked sample image, the processor is further configured to:

determine a feature descriptor of each surrounding feature point in the marked sample image to obtain a first set of feature descriptors;

determine the feature descriptor of each surrounding feature point in the first set of surrounding feature points to obtain a second set of feature descriptors;

determine a similarity between each feature descriptor in the first set of feature descriptors and each feature descriptor in the second set of feature descripts; and

determine the surrounding feature point whose similarity satisfies a similarity threshold as an element in the second set of surrounding feature points.

9. The AR guiding device according to claim 7 , wherein when determining the first surrounding image based on the second set of surrounding feature points, the processor is further configured to:

reconstruct a second surrounding image based on the second set of surrounding feature points;

divide the second surrounding image into at least one image area;

determine the densities of the surrounding feature points in the at least one image area; and

determine each image area where the density of the surrounding feature points is greater than the density threshold as the image area in the first surrounding image.

10. The AR guiding device according to claim 7 , each image area corresponding to one guide sign, wherein when determining the guide sign sequence based on the at least one image area, the processor is further configured to:

sort the at least one image area based on the density of the surrounding feature points in each image area to obtain an observation order of the at least one image area; and

determine an order of guide signs to obtain the guide sign sequence based on the observation order.

11. The AR guiding device according to claim 7 , wherein the processor is further configured to:

in response to the focus of the user's line of sight not moving from the current guide sign to the subsequent guide sign, repeatedly display the at least one guide animation.

12. The AR guiding device according to claim 7 , wherein the processor is further configured to:

obtain a target position of the focus of the user's line of sight;

obtain a surrounding image at the target position; and

in response to no surrounding feature point appearing at the target position in the surrounding image, output a prompt message of moving a position.

13. A non-transitory computer-readable storage medium storing computer instructions, when being executed by a processor, the computer instructions causing the processor to:

obtain a real-time surrounding image and a focus of a user's line of sight in the real-time surrounding image;

perform an image recognition process on the real-time surrounding image to obtain a first set of surrounding feature points;

obtain a marked sample image corresponding to the real-time surrounding image;

screen the surrounding feature points in the first set of surrounding feature points based on the marked sample image to obtain a second set of surrounding feature points;

determine a first surrounding image based on the second set of surrounding feature points, the first surrounding image including at least one image area, and a density of the surrounding feature points in each image area being greater than a density threshold;

determine a guide sign sequence based on the at least one image area; and

display at least one guide animation based on the guide sign sequence, each guide animation being used to guide the focus of the user's line of sight from a current guide sign to a subsequent guide sign.

14. The non-transitory computer-readable storage medium according to claim 13 , wherein when screening the surrounding feature points in the first set of surrounding feature points to obtain the second set of surrounding feature points based on the marked sample image, the processor is further configured to:

determine a feature descriptor of each surrounding feature point in the marked sample image to obtain a first set of feature descriptors;

determine the feature descriptor of each surrounding feature point in the first set of surrounding feature points to obtain a second set of feature descriptors;

determine a similarity between each feature descriptor in the first set of feature descriptors and each feature descriptor in the second set of feature descripts; and

determine the surrounding feature point whose similarity satisfies a similarity threshold as an element in the second set of surrounding feature points.

15. The non-transitory computer-readable storage medium according to claim 13 , wherein when screening the surrounding feature points in the first set of surrounding feature points to obtain the second set of surrounding feature points based on the marked sample image, the processor is further configured to:

determine a feature descriptor of each surrounding feature point in the marked sample image to obtain a first set of feature descriptors;

determine the feature descriptor of each surrounding feature point in the first set of surrounding feature points to obtain a second set of feature descriptors;

determine a similarity between each feature descriptor in the first set of feature descriptors and each feature descriptor in the second set of feature descripts; and

determine the surrounding feature point whose similarity satisfies a similarity threshold as an element in the second set of surrounding feature points.

16. The non-transitory computer-readable storage medium according to claim 13 , wherein when determining the first surrounding image based on the second set of surrounding feature points, the processor is further configured to:

reconstruct a second surrounding image based on the second set of surrounding feature points;

divide the second surrounding image into at least one image area;

determine the densities of the surrounding feature points in the at least one image area; and

determine each image area where the density of the surrounding feature points is greater than the density threshold as the image area in the first surrounding image.

17. The non-transitory computer-readable storage medium according to claim 13 , each image area corresponding to one guide sign, wherein when determining the guide sign sequence based on the at least one image area, the processor is further configured to:

sort the at least one image area based on the density of the surrounding feature points in each image area to obtain an observation order of the at least one image area; and

determine an order of guide signs to obtain the guide sign sequence based on the observation order.

18. The non-transitory computer-readable storage medium according to claim 13 , wherein the processor is further configured to:

in response to the focus of the user's line of sight not moving from the current guide sign to the subsequent guide sign, repeatedly display the at least one guide animation.

19. The non-transitory computer-readable storage medium according to claim 13 , wherein the processor is further configured to:

obtain a target position of the focus of the user's line of sight;

obtain a surrounding image at the target position; and

in response to no surrounding feature point appearing at the target position in the surrounding image, output a prompt message of moving a position.