Research‎ > ‎

Image registration

Robust Image Registration with Global Intensity Transformation

In this work, we present a registration method for images that also takes into account a global intensity transformation between the images, as modeled by a camera response function, i,e., transformation between intensity distributions. The method is based on a joint iterative optimization (geometric and photometric) of the L1 norm of the intensity error. Two strategies are compared to directly find the appropriate intensity transformation within each iteration: histogram specification and the solution obtained by analyzing the necessary optimality conditions. Such strategies reduce the search space of the joint optimization to that of the geometric transformation between the images.

References:
S. Ruano, G. Gallego, A. Yezzi, C. Cuevas, N. García
Robust Image Registration with Global Intensity Transformation
19th IEEE International Symposium on Consumer Electronics (ISCE), Madrid, Spain, June 24-26, 2015.
doiPDF (OA-UPM)


Aerial video georegistration using terrain models from dense and coherent stereo matching

Dense 3D reconstruction of terrain models


In the context of aerial imagery, one of the first steps toward a coherent processing of the information contained in multiple images is geo-registration, which consists in assigning geographic 3D coordinates to the pixels of the image. This enables accurate alignment and geo-positioning of multiple images, detection of moving objects and fusion of data acquired from multiple sensors. To solve this problem there are different approaches that require, in addition to a precise characterization of the camera sensor, high resolution referenced images or terrain elevation models, which are usually not publicly available or out of date. Building upon the idea of developing technology that does not need a reference terrain elevation model, we propose a geo-registration technique that applies variational methods to obtain a dense and coherent surface elevation model that is used to replace the reference model. The surface elevation model is built by interpolation of scattered 3D points, which are obtained in a two-step process following a classical stereo pipeline: first, coherent disparity maps between image pairs of a video sequence are estimated and then image point correspondences are back-projected. The proposed variational method enforces continuity of the disparity map not only along epipolar lines (as done by previous geo-registration techniques) but also across them, in the full 2D image domain.

References:
S. Ruano, G. Gallego, C. Cuevas, N. García
Aerial video georegistration using terrain models from dense and coherent stereo matching
Proc. SPIE 9089, Geospatial InfoFusion and Video Analytics IV; and Motion Imagery for ISR (Intelligence, Surveillance, and Reconnaissance) and Situational Awareness II, 90890V (June 19, 2014). ISSN: 0277-786X; ISBN: 9781628410266. 
From SPIE DSS Sensing Technology and Applications Conference, Baltimore (MD), USA. May 5-9, 2014.
doiPDF (OA-UPM),  YouTube