Photographing method and electronic device
A photographing method and an electronic device are provided, so that a to-be-photographed target can continue to be tracked after the to-be-photographed target returns to a shooting image, to improve accuracy of focusing performed during photographing of a moving object. The method includes: displaying a first image including a first object and a tracking indicator that is associated with the first object, the tracking indicator indicating that the first object is a tracked target; displaying a second image that does not include the first object or the tracking indicator; displaying a third image including the first object; automatically setting the first object as the tracked target and displaying the tracking indicator associated with the first object; and automatically focusing on the first object when displaying the third image.
1. A photographing method, comprising:
generating a feature model comprising a plurality of to-be-photographed targets based on to-be-photographed objects comprised in a plurality of shooting images, wherein the to-be-photographed targets associate with a plurality of image features and the plurality of shooting images are obtained before a first shooting image;
obtaining the first shooting image comprising one or more to-be-photographed objects;
determining a to-be-photographed object in the first shooting image as a to-be-tracked target in response to the to-be-photographed object matching a to-be-photographed target in the feature model; and
tracking the to-be-tracked target in a number of shooting images following the first shooting image;
wherein for each of shooting images following the first shooting image, the tracking of the to-be-tracked target is active when the shooting image comprises a to-be-photographed object matching the to-be-tracked target, and the tracking of the to-be tracked target is inactive when the shooting image does not comprise a to-be-photographed object matching the to-be-tracked target;
wherein tracking the to-be-tracked target in the number of shooting images following the first shooting image further comprises:
initiating a timer in response to the tracking of the to-be-tracked target being active in a previous shooting image and the tracking of the to-be-tracked target being inactive in a current shooting image;
obtaining a next shooting image;
in response to the timer indicating a time interval less than a preset time length, determining one or more to-be-photographed objects in the next shooting image, and terminating the timer when a to-be-photographed object in the next shooting image matches the to-be-tracked target, and
in response to the timer indicating a time interval greater than or equal to the preset time length, determining a next to-be-tracked target in the next shooting image and terminating the timer.
2. The method of claim 1 , wherein generating the feature model further comprises:
obtaining a shooting image;
extracting a to-be-photographed object in the shooting image;
determining the to-be-photographed object being a to-be-photographed target according to a recognition algorithm;
determining an image feature associated with the to-be-photographed target;
adding the to-be-photographed target with the associated image feature to the feature model;
obtaining a next shooting image; and
adding a next to-be-photographed target with an associated image feature to the feature model.
3. The method of claim 2 , wherein the feature model is generated based on a preset number of shooting images before the first shooting image, and the plurality of to-be-photographed targets are determined based on the preset number of shooting images before the first shooting image.
4. The method of claim 2 , wherein the number of to-be-photographed targets in the feature model is less than or equal to a preset threshold.
5. The method of claim 4 , wherein generating the feature model further comprises:
determining a to-be-photographed target with an associated image feature to be added to the feature model;
deleting an earliest added to-be-photographed target with an associated image feature in response to the number of to-be-photographed targets stored in the feature model equal to the preset threshold; and
adding the new to-be-photographed target with the associated image feature to the feature model.
6. The method of claim 1 ,
wherein generating the feature model further comprising:
deleting the to-be-photographed targets with the associated image features stored in the feature model in response to a user selection of a to-be-photographed object in a shooting image;
determining an image feature associated with the to-be-photographed object selected by the user; and
adding the to-be-photographed object selected by the user to the feature model as a to-be-photographed target, the to-be-photographed target associated with the image feature determined for the to-be-photographed object selected by the user; and
wherein the one or more to-be-photographed objects comprised in the first shooting image are compared with the to-be-photographed target in the feature model.
7. The method of claim 1 , further comprising:
updating, in the feature model, an image feature of the to-be-photographed target matching the to-be-tracked target based on an image feature of the to-be-tracked target in the first shooting image;
wherein the tracking of the to-be-tracked target in the number of shooting images following the first shooting image is based on the updated image feature of the to-be-photographed target in the feature model.
8. The method of claim 1 , wherein determining the to-be-tracked target further comprises:
determining a matching degree for each to-be-photographed object comprised in the first shooting image and each of the to-be-photographed targets in the feature model;
determining a to-be-photographed object having a highest matching degree with a to-be-photographed target in the feature model and the matching degree being greater or equal to a threshold; and
determining the to-be-photographed object having the highest matching degree that is greater than a threshold as the to-be-tracked target.
9. The method of claim 1 , wherein the number of the shooting images following the first shooting image for tracking the to-be-tracked target is determined based on a preset tracking period, and the method further comprises:
after completion of the preset tracking period for the to-be-tracked target, obtaining a second shooting image comprising one or more to-be-photographed objects;
determining a to-be-photographed object in the second shooting image as a next to-be-tracked target in response to the to-be-photographed object matching a to-be-photographed target in the feature model; and
tracking the next to-be-tracked target in a number of shooting images following the second shooting image.
10. The method of claim 1 , wherein determining the to-be-tracked target further comprises:
generating a placeholder frame for the to-be-tracked target in the first shooting image, the placeholder frame accommodating the to-be-tracked target in the first shooting image; and
determining a plurality of feature points for the to-be-tracked target in the placeholder frame.
11. The method of claim 1 , wherein tracking the to-be-tracked target in the number of shooting images following the first shooting image further comprises:
in each shooting image of the number of shooting images following the first shooting image, determining a plurality of feature points for the to-be-tracked target in the shooting image in response to the tracking of the to-be-tracked target being active in the shooting image.
12. An electronic device, comprising:
one or more processors; and
a non-transitory computer-readable medium, having computer-executable instructions stored thereon, the computer-executable instructions, when executed by one or more processors, causing the one or more processors to facilitate:
generating a feature model comprising a plurality of to-be-photographed targets based on to-be-photographed objects comprised in a plurality of shooting images, wherein the to-be-photographed targets associate with a plurality of image features and the plurality of shooting images are obtained before a first shooting image;
obtaining the first shooting image comprising one or more to-be-photographed objects;
determining a to-be-photographed object in the first shooting image as a to-be-tracked target in response to the to-be-photographed object matching a to-be-photographed target in the feature model; and
tracking the to-be-tracked target in a number of shooting images following the first shooting image;
wherein for each of shooting images following the first shooting image, the tracking of the to-be-tracked target is active when the shooting image comprises a to-be-photographed object matching the to-be-tracked target, and the tracking of the to-be tracked target is inactive when the shooting image does not comprise a to-be-photographed object matching the to-be-tracked target; and
wherein tracking the to-be-tracked target in the number of shooting images following the first shooting image further comprises:
initiating a timer in response to the tracking of the to-be-tracked target being active in a previous shooting image and the tracking of the to-be-tracked target being inactive in a current shooting image;
obtaining a next shooting image;
in response to the timer indicating a time interval less than a preset time length, determining one or more to-be-photographed objects in the next shooting image, and terminating the timer when a to-be-photographed object in the next shooting image matches the to-be-tracked target, and
in response to the timer indicating a time interval greater than or equal to the preset time length, determining a next to-be-tracked target in the next shooting image and terminating the timer.
13. The device of claim 12 , wherein generating the feature model further comprises:
obtaining a shooting image;
extracting a to-be-photographed object in the shooting image;
determining the to-be-photographed object being a to-be-photographed target according to a recognition algorithm;
determining an image feature associated with the to-be-photographed target;
adding the to-be-photographed target with the associated image feature to the feature model;
obtaining a next shooting image; and
adding a next to-be-photographed target with an associated image feature to the feature model.
14. The device of claim 13 , wherein the feature model is generated based on a preset number of shooting images before the first shooting image, and the plurality of to-be-photographed targets are determined based on the preset number of shooting images before the first shooting image.
15. The device of claim 13 , wherein the number of to-be-photographed targets in the feature model is less than or equal to a preset threshold.
16. The device of claim 15 , wherein generating the feature model further comprises:
determining a to-be-photographed target with an associated image feature to be added to the feature model;
deleting an earliest added to-be-photographed target with an associated image feature in response to the number of to-be-photographed targets stored in the feature model equal to the preset threshold; and
adding the new to-be-photographed target with the associated image feature to the feature model.
17. The device of claim 12 ,
wherein generating the feature model further comprising:
deleting the to-be-photographed targets with the associated image features stored in the feature model in response to a user selection of a to-be-photographed object in a shooting image;
determining an image feature associated with the to-be-photographed object selected by the user; and
adding the to-be-photographed object selected by the user to the feature model as a to-be-photographed target, the to-be-photographed target associated with the image feature determined for the to-be-photographed object selected by the user; and
wherein the one or more to-be-photographed objects comprised in the first shooting image are compared with the to-be-photographed target in the feature model.
18. The device of claim 12 , wherein the computer-executable instructions, when executed by the one or more processors, causing the one or more processors to further facilitate:
updating, in the feature model, an image feature of the to-be-photographed target matching the to-be-tracked target based on an image feature of the to-be-tracked target in the first shooting image;
wherein the tracking of the to-be-tracked target in the number of shooting images following the first shooting image is based on the updated image feature of the to-be-photographed target in the feature model.
19. The method of claim 12 , wherein determining the to-be-tracked target further comprises:
determining a matching degree for each to-be-photographed object comprised in the first shooting image and each of the to-be-photographed targets in the feature model;
determining a to-be-photographed object having a highest matching degree with a to-be-photographed target in the feature model and the matching degree being greater or equal to a threshold; and
determining the to-be-photographed object having the highest matching degree that is greater than a threshold as the to-be-tracked target.
20. The method of claim 12 , wherein the number of the shooting images following the first shooting image for tracking the to-be-tracked target is determined based on a preset tracking period, and wherein the computer-executable instructions, when executed by one or more processors, causing the one or more processors to further facilitate:
after completion of the preset tracking period for the to-be-tracked target, obtaining a second shooting image comprising one or more to-be-photographed objects;
determining a to-be-photographed object in the second shooting image as a next to-be-tracked target in response to the to-be-photographed object matching a to-be-photographed target in the feature model; and
tracking the next to-be-tracked target in a number of shooting images following the second shooting image.