Unlocking the urban photographic record through 4D scene modeling

Show simple item record

dc.contributor.author Schindler, Grant en_US
dc.date.accessioned 2010-09-15T18:48:23Z
dc.date.available 2010-09-15T18:48:23Z
dc.date.issued 2010-07-09 en_US
dc.identifier.uri http://hdl.handle.net/1853/34719
dc.description.abstract Vast collections of historical photographs are being digitally archived and placed online, providing an objective record of the last two centuries that remains largely untapped. We propose that time-varying 3D models can pull together and index large collections of images while also serving as a tool of historical discovery, revealing new information about the locations, dates, and contents of historical images. In particular, our goal is to use computer vision techniques to tie together a large set of historical photographs of a given city into a consistent 4D model of the city: a 3D model with time as an additional dimension. To extract 4D city models from historical images, we must perform inference about the position of cameras and scene structure in both space and time. Traditional structure from motion techniques can be used to deal with the spatial problem, while here we focus on the problem of inferring temporal information: a date for each image and a time interval for which each structural element in the scene persists. We first formulate this task as a constraint satisfaction problem based on the visibility of structural elements in each image, resulting in a temporal ordering of images. Next, we present methods to incorporate real date information into the temporal inference solution. Finally, we present a general probabilistic framework for estimating all temporal variables in structure from motion problems, including an unknown date for each camera and an unknown time interval for each structural element. Given a collection of images with mostly unknown or uncertain dates, we can use this framework to automatically recover the dates of all images by reasoning probabilistically about the visibility and existence of objects in the scene. We present results for image collections consisting of hundreds of historical images of cities taken over decades of time, including Manhattan and downtown Atlanta. en_US
dc.publisher Georgia Institute of Technology en_US
dc.subject Computer vision en_US
dc.subject 3D reconstruction en_US
dc.subject Structure from motion en_US
dc.subject Historical photographs en_US
dc.subject Temporal inference en_US
dc.subject.lcsh Digital images
dc.subject.lcsh Photographs Conservation and restoration
dc.subject.lcsh Three-dimensional imaging
dc.title Unlocking the urban photographic record through 4D scene modeling en_US
dc.type Dissertation en_US
dc.description.degree Ph.D. en_US
dc.contributor.department Computing en_US
dc.description.advisor Committee Chair: Dellaert, Frank; Committee Member: Essa, Irfan; Committee Member: Kang, Sing Bing; Committee Member: Seitz, Steven; Committee Member: Yezzi, Anthony en_US

Files in this item

Files Size Format View
schindler_grant_e_201008_phd.pdf 17.16Mb PDF View/ Open

This item appears in the following Collection(s)

Show simple item record