Geographically locating and posing images in a large-scale image repository and processing framework

摘要

Aspects of the disclosure relate generally to systems and methods for geographically locating images. For example, images from different sources may be associated with different types of location information or simply none at all. In order to reduce inconsistency among images, location information may be gathered for an image using bitmap processing, metadata processing, and information retrieved from where the image was found. This location information can be filtered to remove less reliable or conflicting information. Images may be clustered based on their appearance on an interactive online resource that corresponds to a user-defined event, based on image similarity, and by their appearance in a user photo album. The location information of the images of a cluster is then copied to all of the other images of that cluster.

主权项

1. A method comprising:
receiving, by one or more computing devices, a first image associated with an identifier;using, by the one or more computing devices, the identifier, locating an interactive online resource that corresponds to a user-defined event, the interactive online resource allowing different users to upload images related to the user defined event;
identifying a second image that is from a uniform resource locator (URL) different from a first URL of the interactive online resource and that is identical to the first image;for the first image, generating, by the one or more computing devices, a first set of location data based on at least information found at the second URL;
generating, by the one or more computing devices, a cluster of images that are all associated with the identifier, the cluster including at least the first image and one other image, wherein the one other image is associated with a second set of location data; identifying, by the one or more computing devices, a source of each location data in the first set of location data and the second set of location data; determining, by the one or more computing devices, a reliability level of each source wherein the reliability level of each source comprises assigning a value to each source; ranking, by the one or more computing devices, each of the location data according to the reliability level; filtering, by the one or more computing devices, the first set of location data and the second set of location data based on the rankings to create a filtered first set of location data and a filtered second set of location data; combining, by the one or more computing devices, the filtered first set of location data and the filtered second set of location data into a third set of location data; and assigning, by the one or more computing devices, the third set of location data to each image of the cluster of images, such that the first image receives at least the filtered second set of location data associated with the one other image and the one other image receives at least the filtered first set of location data associated with the first image.