Enhanced image capture
Disclosed are techniques that provide a “best” picture taken within a few seconds of the moment when a capture command is received (e.g., when the “shutter” button is pressed). In some situations, several still images are automatically (that is, without the user's input) captured. These images are compared to find a “best” image that is presented to the photographer for consideration. Video is also captured automatically and analyzed to see if there is an action scene or other motion content around the time of the capture command. If the analysis reveals anything interesting, then the video clip is presented to the photographer. The video clip may be cropped to match the still-capture scene and to remove transitory parts. Higher-precision horizon detection may be provided based on motion analysis and on pixel-data analysis.
1. A method comprising:
capturing, by an image-capture device, a video segment and a sequence of still images;
comparing one or more characteristics of a first still image from the sequence of still images to one or more characteristics of a second still image from the sequence of still images; and
adjusting the video segment based on the comparison of the one or more characteristics of the first still image and the second still image.
2. The method of claim 1 , wherein capturing the video segment and the sequence of still images is in temporal proximity to a capture command received by the image-capture device, and wherein the video segment and the sequence of still images are captured simultaneously.
3. The method of claim 1 , further comprising presenting, by the image-capture device, the adjusted video segment and the first still image, and wherein presenting the adjusted video segment and the first still image includes presenting the first still image using a gallery mode.
4. The method of claim 1 , wherein the video segment is a first portion of the video segment and the sequence of still images is a first portion of the sequence of still images,
the method further comprising:
adjusting one or more image-capture settings of the image-capture device to enable a second portion of the video segment and a second portion of the sequence of still images to be captured with the adjusted one or more image-capture settings.
5. The method of claim 4 , wherein the adjusted one or more image capture settings comprises at least one of:
exposure parameters of the image-capture device; or
flash lighting of the image-capture device.
6. The method of claim 1 , wherein the one or more characteristics of the first still image includes a detected horizon.
7. The method of claim 6 , wherein adjusting the video segment comprises:
determining a maximal line of one or more frames of the video segment;
determining a difference in angle between the maximal line of the one or more frames of the video segment and the detected horizon; and
rotating the one or more frames of the video segment based on the difference in angle between the maximal line of the one or more frames of the video segment and the detected horizon.
8. The method of claim 7 , wherein adjusting the video segment further comprises determining that the maximal line of the one or more frames is indicative of the detected horizon.
9. The method of claim 7 , wherein adjusting the video segment further comprises cropping and upscaling the one or more frames of the video segment.
10. The method of claim 1 , wherein the sequence of still images corresponds to frames of the video segment.
11. The method of claim 1 , wherein comparing the one or more characteristics of the first still image from the sequence of still images to the one or more characteristics of the second still image from the sequence of still images is based on a machine-learned model, the machine-learned model configured to utilize one or more user preferences, past behaviors, or privacy settings to determine that the one or more characteristics of the first still image are indicative of a better quality when compared to the one or more characteristics of the second still image from the sequence of still images.
12. The method of claim 1 , wherein the first still image from the sequence of still images and the second still image from the sequence of still images are not consecutive still images in the sequence of still images.
13. The method of claim 1 , wherein the one or more characteristics of the first still image do not include a quality characteristic.
14. An image-capture device comprising:
a display;
at least one processor; and
one or more non-transitory computer-readable storage media that, when executed by the at least one processor, cause the image-capture device to:
capture a video segment and a sequence of still images;
compare one or more characteristics of a first still image from the sequence of still images to one or more characteristics of a second still image from the sequence of still images; and
adjust the video segment based on the comparison of the one or more characteristics of the first still image and the second still image.
15. The image-capture device of claim 14 , wherein the image capture device is a cellphone, a camera, or a tablet.
16. The image-capture device of claim 14 , wherein the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image-capture device to present the adjusted video segment and the first still image.
17. The image-capture device of claim 16 , wherein the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image-capture device to present the adjusted video segment and the first still image using a gallery mode.
18. The image-capture device of claim 14 , wherein:
the video segment is a first portion of the video segment and the sequence of still images is a first portion of the sequence of still images; and
the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image-capture device to adjust one or more image-capture settings of the image-capture device to enable a second portion of the video segment and a second portion of the sequence of still images to be captured with the one or more image-capture settings.
19. The image-capture device of claim 14 , wherein the one or more characteristics of the first still image includes a detected horizon.
20. The image-capture device of claim 19 , wherein the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image capture device to adjust the video segment by:
determining a maximal line of one or more frames of the video segment;
determining a difference in angle between the maximal line of the one or more frames of the video segment and the detected horizon; and
rotating the one or more frames of the video segment based on the difference in angle between the maximal line of the one or more frames of the video segment and the detected horizon.
21. The image-capture device of claim 20 , the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image-capture device to adjust the video segment by determining that the maximal line of the one or more frames are indicative of the detected horizon.
22. The image-capture device of claim 20 , wherein the one or more non-transitory computer-readable storage media, when executed by the at least one processor, further cause the image-capture device to adjust the video segment by cropping and upscaling the one or more frames of the video segment.