Method and apparatus for identifying object of interest of user

1 . A method for identifying an object of interest of a user, comprising:

obtaining information about a line-of-sight-gazed region of the user and an environment image corresponding to the user, wherein the environment image includes a plurality of regions;

obtaining information about a first gaze region of the user in the environment image based on the environment image, wherein the first gaze region is obtained based on a plurality of interest values corresponding to the plurality of regions, each interest value is obtained based on at least color change richness of the corresponding region, and the first gaze region is used to indicate a sensitive region determined by using a physical feature of a human body;

obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region, wherein the target gaze region is used to indicate a region in which a target object gazed by the user in the environment image is located;

obtaining identity information of the user; and

displaying information about the target gaze region based on the identity information of the user.

2 . The method according to claim 1 , wherein the obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region comprises:

determining the target gaze region based on an overlapping region between the line-of-sight-gazed region and the first gaze region.

3 . The method according to claim 1 , wherein the user is a user in a vehicle, and the obtaining information about a line-of-sight-gazed region of the user and an environment image corresponding to the user comprises:

obtaining information about a line-of-sight-gazed region of the user in the vehicle and an image of a driving video record in the vehicle, wherein the line-of-sight-gazed region of the user in the vehicle is used to indicate information about a gaze region that is of the user in the vehicle and that is outside the vehicle; and

the obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region comprises:

determining the target gaze region of a driver based on the information about the line-of-sight-gazed region of the user in the vehicle and the information about the first gaze region in the image of the driving video record.

4 . The method according to claim 3 , wherein the obtaining information about a line-of-sight-gazed region of the user in the vehicle and an image of a driving video record in the vehicle comprises:

obtaining information about line-of-sight-gazed regions of the user in the vehicle in N frames of images and M frames of images of the driving video record, wherein the N frames of images and the M frames of images of the driving video record are images obtained from a same start moment to a same end moment, and both N and M are positive integers; and

the determining the target gaze region of a driver based on the information about the line-of-sight-gazed region of the user in the vehicle and the information about the first gaze region in the image of the driving video record comprises:

determining that a difference between the line-of-sight-gazed regions of the user in the vehicle in the N frames of images meets a first preset range;

determining that a difference between the first gaze regions in the M frames of images of the driving video record meets a second preset range;

determining an overlapping region based on the line-of-sight-gazed regions of the user in the vehicle in the N frames of images and the first gaze regions in the M frames of images of the driving video record; and

determining the target gaze region of the user in the vehicle based on the overlapping region.

5 . The method according to claim 4 , wherein the difference between the line-of-sight-gazed regions is a location difference between the line-of-sight-gazed regions, and the difference between the first gaze regions is a location difference between the first gaze regions.

6 . The method according to claim 3 , further comprising:

mapping the line-of-sight-gazed region of the user in the vehicle to an imaging plane on which the image of the driving video record is located; or

mapping the image of the driving video record to an imaging plane on which the line-of-sight-gazed region of the user in the vehicle is located.

7 . The method according to claim 3 , further comprising:

displaying information about the target gaze region on a display of the vehicle.

8 . The method according to claim 7 , wherein the vehicle comprises a plurality of displays, and the displaying information about the target gaze region on a display of the vehicle comprises:

determining a target display in the plurality of displays based on location information that is of the user in the vehicle; and

displaying the information about the target gaze region on the target display.

9 . The method according to claim 3 , further comprising:

displaying information about the target gaze region in the vehicle by using a head-up display (HUD) system.

10 . The method according to claim 3 , wherein the user in the vehicle is a driver of the vehicle, or a passenger in the vehicle.

11 . An apparatus for identifying an object of interest of a user, comprising at least one processor and a memory, wherein the memory stores program instructions for execution by the at least one processor to perform operations comprising:

obtaining information about a line-of-sight-gazed region of the user and an environment image corresponding to the user, wherein the environment image includes a plurality of regions;

obtaining information about a first gaze region of the user in the environment image based on the environment image, wherein the first gaze region is obtained based on a plurality of interest values corresponding to the plurality of regions, each interest value is obtained based on at least color change richness of the corresponding region, and the first gaze region is used to indicate a sensitive region determined by using a physical feature of a human body;

obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region, wherein the target gaze region is used to indicate a region in which a target object gazed by the user in the environment image is located;

obtaining identity information of the user; and

displaying information about the target gaze region based on the identity information of the user.

12 . The apparatus according to claim 11 , wherein the obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region comprises:

determining the target gaze region based on an overlapping region between the line-of-sight-gazed region and the first gaze region.

13 . The apparatus according to claim 11 , wherein the user is a user in a vehicle, and the obtaining information about a line-of-sight-gazed region of the user and an environment image corresponding to the user comprises:

obtaining information about a line-of-sight-gazed region of the user in the vehicle and an image of a driving video record in the vehicle, wherein the line-of-sight-gazed region of the user in the vehicle is used to indicate information about a gaze region that is of the user in the vehicle and that is outside the vehicle; and

the obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region comprises:

determining the target gaze region of a driver based on the information about the line-of-sight-gazed region of the user in the vehicle and the information about the first gaze region in the image of the driving video record.

14 . The apparatus according to claim 13 , wherein the obtaining information about a line-of-sight-gazed region of the user in the vehicle and an image of a driving video record in the vehicle comprises:

obtaining information about line-of-sight-gazed regions of the user in the vehicle in N frames of images and M frames of images of the driving video record, wherein the N frames of images and the M frames of images of the driving video record are images obtained from a same start moment to a same end moment, and both N and M are positive integers; and

the determining the target gaze region of a driver based on the information about the line-of-sight-gazed region of the user in the vehicle and the information about the first gaze region in the image of the driving video record comprises:

determining that a difference between the line-of-sight-gazed regions of the user in the vehicle in the N frames of images meets a first preset range;

determining that a difference between the first gaze regions in the M frames of images of the driving video record meets a second preset range;

determining an overlapping region based on the line-of-sight-gazed regions of the user in the vehicle in the N frames of images and the first gaze regions in the M frames of images of the driving video record; and

determining the target gaze region of the user in the vehicle based on the overlapping region.

15 . The apparatus according to claim 14 , wherein the difference between the line-of-sight-gazed regions is a location difference between the line-of-sight-gazed regions, and the difference between the first gaze regions is a location difference between the first gaze regions.

16 . The apparatus according to claim 13 , wherein the operations further comprise:

mapping the line-of-sight-gazed region of the user in the vehicle to an imaging plane on which the image of the driving video record is located; or

mapping the image of the driving video record to an imaging plane on which the line-of-sight-gazed region of the user in the vehicle is located.

17 . The apparatus according to claim 13 , wherein the operations further comprise:

displaying information about the target gaze region on a display of the vehicle.

18 . A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores program instructions for execution by at least one processor, and wherein the programming instructions instruct the at least one processor to perform operations comprising:

obtaining information about a line-of-sight-gazed region of a user and an environment image corresponding to the user, wherein the environment image includes a plurality of regions;

obtaining information about a first gaze region of the user in the environment image based on the environment image, wherein the first gaze region is obtained based on a plurality of interest values corresponding to the plurality of regions, each interest value is obtained based on at least color change richness of the corresponding region, and the first gaze region is used to indicate a sensitive region determined by using a physical feature of a human body;

obtaining a target gaze region of the user based on the information about the line-of-sight-gazed region and the information about the first gaze region, wherein the target gaze region is used to indicate a region in which a target object gazed by the user in the environment image is located;

obtaining identity information of the user; and

displaying information about the target gaze region based on the identity information of the user.

19 . The method according to claim 1 , wherein displaying the information about the target gaze region based on the identity information of the user comprises:

based on the identity information of the user indicating a driver of a vehicle, displaying the information about the target gaze region using a head-up display (HUD) of the vehicle.

20 . The method according to claim 1 , wherein displaying the information about the target gaze region based on the identity information of the user comprises:

based on the identity information of the user indicating a passenger of a vehicle, displaying the information about the target gaze region using a display of the vehicle corresponding to location information of the user in the vehicle.