초록 ▼

Systems and methods are provided for using imagery depicting a timekeeping device to determine a clock offset for a particular image capture device. The clock offset can be used to correct timestamps associated with one or more images captured by such image capture device. One example method include

Systems and methods are provided for using imagery depicting a timekeeping device to determine a clock offset for a particular image capture device. The clock offset can be used to correct timestamps associated with one or more images captured by such image capture device. One example method includes analyzing imagery depicting at least in part a timekeeping device to determine a first time displayed by the timekeeping device in the imagery. The method includes determining whether the first time comprises a 12-hour value or a 24-hour value. The method includes, when it is determined that the first time comprises a 12-hour value, determining a corresponding 24-hour value for the 12-hour value based at least in part on information contained within a plurality of images. The method includes determining a clock offset between the 24-hour value and the first timestamp. One example system includes a timestamp correction engine for correcting timestamps.

대표청구항 ▼

1. A computer-implemented method for correcting image timestamps, the method comprising: obtaining, by one or more computing devices, a first image from among a plurality of images, wherein the first image includes imagery depicting at least in part a timekeeping device, and wherein a first timestam

1. A computer-implemented method for correcting image timestamps, the method comprising: obtaining, by one or more computing devices, a first image from among a plurality of images, wherein the first image includes imagery depicting at least in part a timekeeping device, and wherein a first timestamp is associated with the first image, the first timestamp indicating an internal time of an image capture device when the image capture device captured the first image;analyzing, by the one or more computing devices, the imagery depicting at least in part the timekeeping device to determine a first time displayed by the timekeeping device in the imagery;determining, by the one or more computing devices, whether the first time comprises a 12-hour value or a 24-hour value;when it is determined that the first time comprises a 12-hour value, determining, by the one or more computing devices, a corresponding 24-hour value for the 12-hour value based at least in part on information contained within the plurality of images;determining, by the one or more computing devices, a clock offset between the 24-hour value and the first timestamp; andadjusting, by the one or more computing devices, a plurality of timestamps by the clock offset, wherein the plurality timestamps are respectively associated with the plurality of images captured by the image capture device. 2. The computer-implemented method of claim 1, wherein determining, by the one or more computing devices, the corresponding 24-hour value for the 12-hour value based at least in part on information contained within the plurality of images comprises: determining, by the one or more computing devices, an inclination of the sun depicted in the first image;identifying, by the one or more computing devices, one or more landmarks depicted by the first image; anddetermining an expected AM sun inclination and an expected PM sun inclination for a location associated with the one or more landmarks;comparing, by the one or more computing devices, the inclination of the sun to the expected AM sun inclination and the expected PM sun inclination; andselecting, by the one or more computing devices, an AM value or a PM value for the 12-hour value based at least in part on the comparison of the inclination of the sun to the expected AM sun inclination and the expected PM sun inclination. 3. The computer-implemented method of claim 1, wherein determining, by the one or more computing devices, a corresponding 24-hour value for the 12-hour value based at least in part on information contained within the first image comprises determining, by the one or more computing devices, an inclination of the sun depicted in the first image; anddetermining, by the one or more computing devices, the corresponding 24-hour value for the 12-hour value based at least in part on the inclination of the sun depicted in the first image. 4. The computer-implemented method of claim 3, wherein determining, by the one or more computing devices, the corresponding 24-hour value for the 12-hour value based at least in part on the inclination of the sun depicted in the first image comprises selecting, by the one or more computing devices, an AM value or a PM value for the 12-hour value based at least in part on the inclination of the sun depicted in the first image. 5. The computer-implemented method of claim 3, wherein determining, by the one or more computing devices, the corresponding 24-hour value for the 12-hour value based at least in part on the inclination of the sun depicted in the first image comprises: determining, by the one or more computing devices, a location at which the first image was captured;comparing, by the one or more computing devices, the inclination of the sun to an expected AM sun inclination and an expected PM sun inclination for the location; andselecting, by the one or more computing devices, an AM value or a PM value for the 12-hour value based at least in part on the comparison of the inclination of the sun to the expected AM sun inclination and the expected PM sun inclination. 6. The computer-implemented method of claim 5, wherein determining, by the one or more computing devices, the location at which the first image was captured comprises: obtaining, by the one or more computing devices, time-indexed location data associated with a user of the image capture device;determining, by the one or more computing devices, one or more locations specified by the time-indexed location data at one or more instances of the 12-hour value; andusing, by the one or more computing devices, the one or more locations specified by the time-indexed location data as the location at which the first image was captured. 7. The computer-implemented method of claim 6, wherein the time-indexed location data associated with the user of the image capture device comprises GPS data associated with the image capture device. 8. The computer-implemented method of claim 1, wherein adjusting, by the one or more computing devices, the plurality of timestamps by the clock offset comprises: obtaining, by the one or more computing devices, the plurality of images captured by the image capture device;determining, by the one or more computing devices, a subset of the plurality of images that have timestamps within a threshold time from the first timestamp; andadjusting, by the one or more computing devices for only the images included in the subset, the timestamp for each of the subset of images by the clock offset. 9. The computer-implemented method of claim 1, wherein adjusting, by the one or more computing devices, the plurality of timestamps by the clock offset comprises: obtaining, by the one or more computing devices, the plurality of images captured by the image capture device;clustering, by the one or more computing devices, the plurality of images into one or more clusters based on a frequency of capture exhibited by the plurality of images;adjusting, by the one or more computing devices for only the images included in the same cluster as the first image, the timestamp for each image included in the same cluster as the first image by the clock offset. 10. The computer-implemented method of claim 1, further comprising, after adjusting, by the one or more computing devices, the plurality of timestamps by the clock offset: determining, by the one or more computing devices, a plurality of locations respectively associated with the plurality of images by respectively comparing the plurality of adjusted timestamps to time-indexed location data associated with a user of the image capture device; andgenerating, by the one or more computing devices, metadata for each of the plurality of images, wherein the metadata for each image indicates the location associated with such image. 11. The computer-implemented method of claim 10, wherein the time-indexed location data associated with a user of the image capture device comprises time-indexed location data associated with a second device associated with the user, the second device being distinct from the image capture device. 12. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising: identifying an image that depicts a clock, wherein the image was captured by an image capture device;analyzing the image to determine a time displayed by the clock;when the time is a 12-hour value: determining an inclination of the sun depicted in the image or depicted in another image captured by the image capture device within a threshold period of time;determining a coarse location at which the image was captured; anddetermining a 24-hour value for the 12-hour value based at least in part on the inclination of the sun and the coarse location;determining a clock offset between the 24-hour value and a timestamp associated with the image; andadjusting a plurality of timestamps by the clock offset, wherein the plurality of timestamps are respectively associated with a plurality of images captured by the image capture device. 13. The one or more non-transitory computer-readable media of claim 12, wherein determining the coarse location at which the image was captured comprises identifying one or more locations specified by time-indexed location data associated with a user of the image capture device. 14. The one or more non-transitory computer-readable media of claim 13, wherein the time-indexed location data comprises GPS data associated with a second device associated with the user, wherein the second device is distinct from the image capture device. 15. The one or more non-transitory computer-readable media of claim 12, wherein determining the 24-hour value for the 12-hour value based at least in part on the inclination of the sun and the coarse location comprises: obtaining an expected AM sun inclination associated with the coarse location and an AM version of the 12-hour value;obtaining an expected PM sun inclination associated with the coarse location and a PM version of the 12-hour value; andselecting either the AM version of the 12-hour value or the PM version of the 12-hour value as the 24-hour value based at least in part on a comparison of the inclination of the sun to the expected AM sun inclination and the expected PM sun inclination. 16. A computing system for correcting image timestamps, the system comprising: one or more computing devices; andone or more non-transitory computer-readable media storing instructions that, when executed by the one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising: obtaining a plurality of images captured by an image capture device, wherein a plurality of timestamps are respectively associated with the plurality of images;identifying a first image of the plurality of images that includes imagery depicting at least in part a timekeeping device;determining a first time displayed by the timekeeping device in the first image;disambiguating between an AM version of the first time and a PM version of the first time based at least in part on location information associated with the first image;determining an offset between the first time and the timestamp of the first image; andadjusting the plurality of timestamps by the offset. 17. The computing system of claim 16, wherein disambiguating between the AM version of the first time and the PM version of the first time based at least in part on location information associated with the first image comprises: determining a location at which the first image was captured;matching the location against time-indexed location data associated with a user associated with the first image; andselecting the AM version or the PM version of the first time based at least in part on the matching. 18. The computing system of claim 17, wherein matching the location against time-indexed location data associated with the user associated with the first image comprises determining, based at least in part on the time-indexed location data, whether the user was located at the location at only the AM version of the first time or at only the PM version of the first time; andselecting the AM version or the PM version of the first time based at least in part on the matching comprises: selecting the AM version when it is determined, based at least in part on the time-indexed location data, that the user was located at the location at only the AM version of the first time; andselecting the PM version when it is determined, based at least in part on the time-indexed location data, that the user was located at the location at only the PM version of the first time. 19. The computing system of claim 16, wherein adjusting the plurality of timestamps by the offset comprises: clustering the plurality of images based at least in part on the plurality of timestamps; andadjusting the timestamps by the offset for only a first subset of the plurality of images that are included in a first cluster of which the first image is a member. 20. The computing system of claim 16, wherein adjusting the plurality of timestamps by the offset comprises: clustering the plurality of images based at least in part on one or more trends exhibited by a device photo capture history associated with the image capture device; andadjusting the timestamps by the offset for only a first subset of the plurality of images that are included in a first cluster of which the first image is a member.