Toward automatic GIS–video initial registration

Abstract

In the context of registration between videos and geographic information system (GIS)-based 3D building models-for instance in augmented reality applications-we propose a solution to one of the most critical problems, namely the registration initialization. Successful automatic 2D/3D matching is achieved by combining two context-dependent improvements. On one hand, we associate semantic information to the low-level primitives we used to reduce the problem complexity. On the other hand, we avoid false initial registration solutions by analyzing the convergence of the iterative pose computation in a RANSAC framework. We require that videos are acquired together with global positioning system measures. We also present how such a registration can be exploited, once it has been performed for the whole video. Textures of visible buildings are extracted from the images. A new algorithm for façade texture fusion based on statistical analysis of the texels color is presented. It allows us to remove from the final textures all occluding objects in front of the viewed building façades. G. Sourimant (B) · T. Colleu · V. Jantet INRIA Rennes Bretagne Atlantique,

Skyline matching: A robust registration method between Video and GIS

“…Such a method, proposed by Reitmayr & Drummond [7], uses a rough textured GIS model as matching database and applies an edge-tracking system to calculate the camera pose. An improved work was done by Sourimant et al [2] where a RANSAC algorithm is applied to find out the best correspondence of line features between GIS model and image. Both their works are heavily dependant on a robust initial rough pose which is provided either through differential GPS or other additional sensors such as gyroscope.…”

“…So for any point P(x, y, z) in the Cartesian coordinate system the transformation is as follows. First, we can get the distance between P and C where P is the projection of point P in the horizontal plane which goes through the camera center C(x 0 , y 0 , z 0 ): = (x − x 0 ) 2 + (z − z 0 ) 2 Then we can got the Azimuth angle:…”

“…At the same time 3D models are replacing traditional 2D data. Under this context, Video/GIS registration technique is proposed as a solution for both Augmented Reality Application [1] and 3D texture update problem [2].…”

A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information

“…Subsequently, the research on the combination of video and GIS gradually deepened. Milosavljević [15] and Sourimant [16] used augmented reality technology to register surveillance video data with geospatial data and realized the superposition of video and 3D GIS data. Kim [17] and others extracted the dynamic information from a video to enhance the visual expression of dynamic scenes in Google Earth but lacked the combination of video and 3D GIS.…”