Image based detection of geometric changes in
large scale urban evironments

Aparna Taneja Luca Ballan Marc Pollefeys
ETH Zurich ETH Zurich ETH Zurich


We present an algorithm to detect changes in the geometry of an urban environment using some images observing its current state. The proposed method can be used to significantly optimize the process of updating the 3D model of a city changing over time, by restricting this process to only those areas where changes are detected.

With this application in mind, we designed our algorithm to specifically detect only structural changes in the environment, ignoring any changes in its appearance, and ignoring also all the changes which are not relevant for update purposes, such as cars, people etc. The method also accounts for all the challenges involved in a large scale application of change detection, such as, inaccuracies in the input geometry, errors in the geo-location data of the images, as well as, the limited amount of information due to sparse imagery.


    Small-scale datasets [Readme]


    Large-scale dataset

The images for this dataset were downloaded from Google Streetview and the 3D model of Zurich can be obtained here.

Related works

City-Scale Change Detection in Cadastral 3D Models using Images
Aparna Taneja, Luca Ballan, Marc Pollefeys
CVPR 2013
Registration of Spherical Panoramic Images with Cadastral 3D Models
Aparna Taneja, Luca Ballan, Marc Pollefeys
3DIMPVT 2012
Image based detection of geometric changes in urban evironments
Aparna Taneja, Luca Ballan, Marc Pollefeys
ICCV 2011 (oral)
[PDF] [BibTex][Video][Talk]


The research leading to these results has received funding from the ERC under the EC’s Seventh Framework Programme (FP7/2007-2013) / ERC grant #210806, Swiss National Science Foundation, Honda and Google.

Computer Vision and Geometry Group CVG
ETH, Zurich