Automatic Initialization for the Registration of GIS and Video Data

Colleu, Thomas; Sourimant, Gaël; Morin, Luce

doi:10.1109/3dtv.2008.4547805

Cited by 8 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is illustrated in Fig. 5, where we set p to 0.99 (a standard value) and n to 4 [1]. Back to Fig.…”

Section: Robust Matching Criterionmentioning

confidence: 96%

“…This work has already been described with more details in [1]. The major limitation of this approach is that it requires to choose a keyframe within the video to compute the first approximation of the camera pose in the SfM framework.…”

Section: Pose Ref Inementmentioning

confidence: 98%

“…This method is based on the following assumption: Given a keyframe, which criteria allow to determine whether the estimated pose is a viable one? The registration procedure becomes sequential, meaning that we test each image of the video as a keyframe, one after the other, using the algorithm described in [1]. Several criteria are used to determine whether a keyframe is a valid one for initial pose computation.…”

Section: Automatic Initial Registrationmentioning

confidence: 99%

“…The major limitation of this approach is that it requires to choose a keyframe within the video to compute the first approximation of the camera pose in the SfM framework. In [1], the keyframe is selected manually.…”

Section: Pose Ref Inementmentioning

confidence: 99%

See 3 more Smart Citations

Toward automatic GIS–video initial registration

et al. 2011

View full text Add to dashboard Cite

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,

show abstract

“…This is illustrated in Fig. 5, where we set p to 0.99 (a standard value) and n to 4 [1]. Back to Fig.…”

Section: Robust Matching Criterionmentioning

confidence: 96%

Section: Pose Ref Inementmentioning

confidence: 98%

Section: Automatic Initial Registrationmentioning

confidence: 99%

Section: Pose Ref Inementmentioning

confidence: 99%

See 2 more Smart Citations

Toward automatic GIS–video initial registration

et al. 2011

View full text Add to dashboard Cite

show abstract

“…According to [3], Video/GIS registration is a fusion between videos and geo-referenced building models which are extracted from GIS. The camera pose estimation problem is really the essential challenge of Video/GIS registration issue.…”

Section: Introductionmentioning

confidence: 99%

Skyline matching: A robust registration method between Video and GIS

Zhu

Pressigout²,

Servières³

et al. 2012

Usage, Usability, and Utility of 3D City Models – European COST Action TU0801

Self Cite

View full text Add to dashboard Cite

Abstract. Camera pose estimation from an image has long been a very active research for Video/GIS registration. Different from traditional methods which are based on direct building feature matching, this paper presents an alternative method which uses an overall Skyline feature to determine the camera's orientation. Through our skyline matching method we find out a way to transform an image/model matching problem into a curve matching problem which significantly reduced the computation complexity and make it a possible solution for real-time applications.

show abstract

Video/GIS registration system based on skyline matching method

Zhu

Morin

Pressigout

et al. 2013

2013 IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

International audienceVideo/GIS registration in urban environments is necessary for establishing correspondences between real objects and geometric information in Geographic Information System (GIS) applications such as outdoor Augmented Reality (AR) and building texture acquisition. In this work, we present a registration system using a GPS prior and a skyline matching method to estimate the camera pose from images. A skyline rectification method through vertical vanishing point detection is also developed to enable arbitrary camera orientation, with non nul tilt. The proposed approach is robust, fully automatic and computationally inexpensive which makes it a possible solution for mobile device applications. The performance of our approach is demonstrated in several experimental evaluations. The possible refinement of camera location through a systematic method is also investigated

show abstract

Automatic Initialization for the Registration of GIS and Video Data

Cited by 8 publications

References 9 publications

Toward automatic GIS–video initial registration

Toward automatic GIS–video initial registration

Skyline matching: A robust registration method between Video and GIS

Video/GIS registration system based on skyline matching method

Contact Info

Product

Resources

About