Automatic Procedure for the Registration of Thermographic Images With Point Clouds

Lagüela, S.; Armesto, Julia; Arias, Pablo; Zakhor, Avideh

doi:10.5194/isprsarchives-xxxix-b5-211-2012

Cited by 10 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…26 Unfortunately, it becomes much more involved in the case RGB and IR data that need to be integrated. Some authors 38,39 have published procedures for automatic coregistration of RGB and IR images, which look promising but still work on a limited number of applications.…”

Section: Discussionmentioning

confidence: 99%

Rigorous procedure for mapping thermal infrared images on three-dimensional models of building façades

Previtali

Barazzetti

Redaelli

et al. 2013

J. Appl. Remote Sens

View full text Add to dashboard Cite

Abstract. A rigorous methodology for mapping thermal and RGB images on three-dimensional (3-D) models of building façades is presented. The developed method differs from most existing approaches because it relies on the use of thermal images coupled with 3-D models derived from terrestrial laser scanning surveying. The primary issue for an accurate texturing is the coregistration of the geometric model of the façade and the thermal images in the same reference system. This task is done by using a procedure standing out from other approaches adopted in current practice, which are mainly based on the independent registration of each image on the basis of homography or space resection techniques. A rigorous photogrammetric orientation of both thermal and RGB images is computed together in a combined bundle adjustment. This solution allows one to have a better control of the quality of the results, especially to reduce errors and artifacts in areas where more images are mosaicked onto the 3-D model. Several products can be obtained: 3-D triangulated textured models or raster products like orthophotos, having the temperature as radiometric value. The proposed approach is tested on different buildings of Politecnico di Milano University. Applications demonstrated the performance of the procedure and its technical applicability in routine thermal surveys. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Section: Discussionmentioning

confidence: 99%

Rigorous procedure for mapping thermal infrared images on three-dimensional models of building façades

Previtali

Barazzetti

Redaelli

et al. 2013

J. Appl. Remote Sens

View full text Add to dashboard Cite

show abstract

“…Fusing data taken from two different sources requires the data to be correctly registered or relatively aligned, for example by automatically extracting matching corner features in outdoor (street and façade) laser scanner point clouds and 2D images 11 . Some researchers have also used line features and Harris corners for the registration process 12,13 .…”

Section: Introductionmentioning

confidence: 99%

Damage and deterioration monitoring of artwork by data fusion of 3D surface and hyperspectral measurements

et al. 2014

View full text Add to dashboard Cite

This paper describes the processing algorithm methodology and preliminary results from a novel optical-based system for the assessment of chemical and mechanical deterioration of artworks. The FP7 Syddarta Project prototype is composed of two optical channels: 1) a 3D imaging channel which acquires 3D surface data and multiband information in the visible spectral range; 2) an infrared hyperspectral imaging channel in the spectral range 900 to 2500 nm. The processing algorithms developed perform the system calibration, damage detection and chemical deterioration analysis. Both photometric and geometric calibrations have been implemented. The photometric calibration is based on a white reference and intensity map and compensates for variation in light intensities. The geometric calibration is based on planar homographies to determine the interior and exterior orientation of the projector and the two cameras. This is used to map the acquired data of the different sensors into a single reference frame. To acquire 3D data, a set of phase-shifted fringe patterns is projected on the object which are processed by Fourier transform. To identify mechanical deterioration, the acquired 3D cloud of points is meshed and differences in surface normals for a given radius are computed. To analyse the chemical deterioration of the pigments a supervised classification method has been implemented. First of all, spectral data is normalized with the Extended Multiplicative Scatter Correction algorithm. Then, data dimensionality is reduced by applying Principal Component Analysis and classification is done with Support Vector Machine. Results are presented showing the performance of the described algorithms.

show abstract

“…(Weinmann et al, 2014) proposed the keypoint-based co-registration via the robust matching techniques method to find the corresponding keypoints in intensity image and IR image, and co-register the IR image to range image applying RANSAC-based projection. (Lagüela, Armesto, 2012) extract the line segments from IR images and point cloud separately. With the corresponding lines, the camera position can be estimated by the RANSAC process.…”

Section: Introductionmentioning

confidence: 99%

Direct Co-Registration of Tir Images and MLS Point Clouds by Corresponding Keypoints

Zhu

Hoegner

et al. 2019

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> In this work, we discussed how to directly combine thermal infrared image (TIR) and the point cloud without additional assistance from GCPs or 3D models. Specifically, we propose a point-based co-registration process for combining the TIR image and the point cloud for the buildings. The keypoints are extracted from images and point clouds via primitive segmentation and corner detection, then pairs of corresponding points are identified manually. After that, the estimated camera pose can be computed with EPnP algorithm. Finally, the point cloud with thermal information provided by IR images can be generated as a result, which is helpful in the tasks such as energy inspection, leakage detection, and abnormal condition monitoring. This paper provides us more insight about the probability and ideas about the combining TIR image and point cloud.</p>

show abstract

Automatic Procedure for the Registration of Thermographic Images With Point Clouds

Cited by 10 publications

References 17 publications

Rigorous procedure for mapping thermal infrared images on three-dimensional models of building façades

Rigorous procedure for mapping thermal infrared images on three-dimensional models of building façades

Damage and deterioration monitoring of artwork by data fusion of 3D surface and hyperspectral measurements

Direct Co-Registration of Tir Images and MLS Point Clouds by Corresponding Keypoints

Contact Info

Product

Resources

About