Where was that photo taken? Deriving geographical information from image collections based on temporal exposure attributes

Abstract

This paper demonstrates a novel strategy for inferring approximate geographical information from the exposure information and temporal patterns of outdoor images in image collections. Image exposure is reliant on light and most photographs are therefore taken in daylight which again depends on the position of the sun. Clearly, the sun results in different lighting conditions at different geographical location and at different times of the day, and hence the observed intensity patterns can be used to deduce the approximate location of the photographer at the time the photographs were taken. Images taken inside or at night are temporally connected to the daylight images and the geographical information can therefore be transferred to related ''dark'' photographs. The strategy is efficient as it only considers meta information and not image contents. Large databases can therefore be indexed efficiently. Experimental results demonstrate that the current approach yields a longitudinal error of 15.7°and a latitudinal error of 30.5°for authentic image collections comprising a mixture of outdoor and indoor images. The strategy determined the correct hemisphere in all the tests. Although not as accurate as GPS receiver, the geographical information is sufficiently detailed to be useful. Applications include improved image retrieval, image browsing and automatic image tagging. The strategy does not require a GPS receiver and can be applied to the existing digital image collections.

Communicating Panoramic 360 Degree Immersed Experiences: A Simple Technique for Sketching in 3D

“…Therefore, to represent all possible angles 360 degrees in the horizontal direction and 180 degrees in the vertical direction gives an aspect ratio of 360:180 or 2:1. This is analogous to latitude and longitude [9,10,11]. Equirectangular world maps therefore often have an aspect ratio of 2:1.…”

Drawing Abrasive Hologram Animations with Auto-Generated Scratch Patterns

“…This is achieved by making hand sketches in equirectangular panoramic space [11] where the world is viewed using a longitudinal and latitudinal angle [12,13]. This space is not straightforward; it has thus been proposed to use supporting gridlines making it easy to trace lines in the x, y and z dimensions [14].…”

A Configurable Photo Browser Framework for Large Image Collections

“…The background for this work was the author's previous research on techniques for extracting geographical information from image collections [13][14][15][16] where the geographical information is extracted from the image meta data stored in the image EXIF headers [10,17,18]. This has for instance been applied to automatic tagging of images and providing summaries of collections in the form of image browsers for the blind [19].…”

“…The exposure value gives an absolute measurement of the light intensity at the scene and such information cannot be extracted fully from the content of images as the image measurements are relative. Moreover, even more abstract information such as geographical location [16] and descriptive information relating to local time zones [19] can be extracted based on these quantities. One strength of meta-information is that it can be exploited without having to inspect the image contents and is thus not related to the image size.…”