Metrics and Optimization Techniques for Registration of Color to Laser Range Scans

Hantak, Chad; Lastra, Anselmo

doi:10.1109/3dpvt.2006.93

Cited by 12 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The image is re-rendered based on that calibration, and two or more passes of that process are applied, but this time with an affine 2D transform followed by a deformable transform. Image comparison is done using an expectation maximization variation [12] that combines good adaptability for comparison of images of different modalities and a relatively linear search space to avoid falling into local minima, an issue for this kind of application when using this metric [13]. By rendering after each step, we ensure that the rendered part of the 3D model really corresponds to the part visible in the image, but also compensates for limitations in the deformation model used by the registration algorithm.…”

Section: B Supervised Approachmentioning

confidence: 99%

Issues in acquiring, processing and visualizing large and detailed 3D models

Godin

Borgeat

Beraldin

et al. 2010

2010 44th Annual Conference on Information Sciences and Systems (CISS)

View full text Add to dashboard Cite

/npsi/ctrl?action=rtdoc&an=15261152&lang=en http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/ctrl?action=rtdoc&an=15261152&lang=fr READ THESE TERMS AND CONDITIONS CAREFULLY BEFORE USING THIS WEBSITE.http://nparc.cisti-icist.nrc-cnrc.gc.ca/npsi/jsp/nparc_cp.jsp?lang=en Vous avez des questions? Nous pouvons vous aider. Pour communiquer directement avec un auteur, consultez la première page de la revue dans laquelle son article a été publié afin de trouver ses coordonnées. Si vous n'arrivez pas à les repérer, communiquez avec nous à PublicationsArchive-ArchivesPublications@nrc-cnrc.gc.ca. Questions? Contact the NRC Publications Archive team atPublicationsArchive-ArchivesPublications@nrc-cnrc.gc.ca. If you wish to email the authors directly, please see the first page of the publication for their contact information. NRC Publications Archive Archives des publications du CNRCFor the publisher's version, please access the DOI link below./ Pour consulter la version de l'éditeur, utilisez le lien DOI ci-dessous.http://doi.org/10.1109/CISS.2010.5464966 IEEE, pp. 1-6, 2010-03-19 Issues in Acquiring, Processing and Visualizing Large and Detailed 3D Models Abstract-Modelling from reality using active optical geometric sensing has been a very active research area in computer graphics and vision for the last twenty years. While most elements of the modelling pipeline have reached maturity and have been adopted in several application sectors, several issues remain, particularly in the modelling of large structures and environments, as well as in the management of large, complex and detailed 3D models. This paper describes some of these issues, and outlines some of the solutions that we have proposed. These methods and approaches, as well as their current limitations, are described using different example applications: a monument (the Erechtheion), a painting (Mona Lisa), and a terrain model.

show abstract

Section: B Supervised Approachmentioning

confidence: 99%

Issues in acquiring, processing and visualizing large and detailed 3D models

Godin

Borgeat

Beraldin

et al. 2010

2010 44th Annual Conference on Information Sciences and Systems (CISS)

View full text Add to dashboard Cite

show abstract

“…Some range sensors are capable of recording the intensity of the reflected sensing light at each range sample, and to reduce noise, the sensing light is often not in the visible light spectrum. Williams et al [Williams et al 2004] and Hantak and Lastra [Hantak and Lastra 2006] use the dependence between color and the infra-red intensity at each range sample, and several similarity measures, such as mutual information and chi-square statistics, are used to search for the best match. For this approach, good camera pose initialization is crucial to derive the correct camera pose.…”

Section: Automatic Image-to-geometry Registrationmentioning

confidence: 99%

“…For this approach, good camera pose initialization is crucial to derive the correct camera pose. The registration results of different information-theoretic metrics are compared in [Hantak and Lastra 2006]. Also, Pong and Cham [Pong and Cham 2006] have explored mutual information between image intensity and object surface normals for the alignment of 3D objects to their 2D images.…”

Section: Automatic Image-to-geometry Registrationmentioning

confidence: 99%

Automatic registration of color images to 3D geometry

Yun-zhen

Low

2009

Proceedings of the 2009 Computer Graphics International Conference

View full text Add to dashboard Cite

We present an approach to automatically register a large set of color images to a 3D geometric model. The problem arises from the modeling of real-world environments, where surface geometry is acquired using range scanners whereas the color information is separately acquired using untracked and uncalibrated cameras. Our approach constructs a sparse 3D model from the color images using a multiview geometry technique. We project special light patterns onto the scene surfaces to increase the robustness of the multiview geometry reconstruction. The sparse model is then approximately aligned with the detailed model. Planes found in the detailed model are exploited to refine the registration. Finally, the registered color images are mapped to the detailed model using weighted blending, with careful consideration of occlusion and the preservation of image details.

show abstract

“…The image is re-rendered based on that calibration, and two or or more passes of that process are applied, but this time with an affine 2D transform followed by a deformable transform. Image comparison is done using an expectation maximization variation [8] that combines good adaptability for comparison of images of different modalities and a relatively linear search space to avoid falling into local minima, an issue for this kind of application when using this metric [2]. By re-rendering after each step, we insure that the rendered part of the 3D model really corresponds to the part visible in the image,but also compensates for limitations in the deformation model used by the registration algorithm.…”

Section: Image Registrationmentioning

confidence: 99%

“…Hantak [2] provides a good litterature review and classification of automatic registration techniques and compares different image-based similarity metrics for 3D/2D Special thanks to Prof. V. Valzano and A. Bandiera, Coordinamento SIBA, Universit del Salento, Lecce, Italia. intensity registration.…”

Section: Introductionmentioning

confidence: 99%

A framework for the registration of color images with 3D models

Borgeat

Poirier

Beraldin

et al. 2009

2009 16th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper describes an environment to automatically or semi-automatically compute the precise mapping between a set of 2D images and a triangulated 3D model built from highresolution 3D range data. This environment is part of our Atelier3D framework for the modeling, visualization and analysis of large sensor-based datasets. This work was done to initially support three cultural heritage application projects: the modeling of the Grotta dei Cervi in Italy, of the Erechtheion in Athens, Greece, and of Leonardo's Mona Lisa. The proposed method combines image-based registration, feature matching, robust estimation techniques and advanced multi-resolution rendering with a powerful user interface.

show abstract

Metrics and Optimization Techniques for Registration of Color to Laser Range Scans

Cited by 12 publications

References 21 publications

Issues in acquiring, processing and visualizing large and detailed 3D models

Issues in acquiring, processing and visualizing large and detailed 3D models

Automatic registration of color images to 3D geometry

A framework for the registration of color images with 3D models

Contact Info

Product

Resources

About