Fusion of thermal imagery with point clouds for building façade thermal attribute mapping

Lin, Defu; Jarząbek-Rychard, Małgorzata; Tong, Xiaochong; Maas, Hans‐Gerd

doi:10.1016/j.isprsjprs.2019.03.010

Cited by 55 publications

(41 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, in most cases of thermographic building inspections, absolute temperatures depend on material type, which is not known a prior; however, the differences in the raw measurements are useful as a discriminator in classification. A quantitative temperature evaluation regarding three types of material specific to façades-concrete, glass, and plastic-is presented in our other research, as described in [24]. Since the influence of emissivity on the temperature value is very small, the emissivity correction can be neglected for the presented application case.…”

Section: Data Acquisitionmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

Self Cite

View full text Add to dashboard Cite

Targeted energy management and control is becoming an increasing concern in the building sector. Automatic analyses of thermal data, which minimize the subjectivity of the assessment and allow for large-scale inspections, are therefore of high interest. In this study, we propose an approach for a supervised extraction of façade openings (windows and doors) from photogrammetric 3D point clouds attributed to RGB and thermal infrared (TIR) information. The novelty of the proposed approach is in the combination of thermal information with other available characteristics of data for a classification performed directly in 3D space. Images acquired in visible and thermal infrared spectra serve as input data for the camera pose estimation and the reconstruction of 3D scene geometry. To investigate the relevance of different information types to the classification performance, a Random Forest algorithm is applied to various sets of computed features. The best feature combination is then used as an input for a Conditional Random Field that enables us to incorporate contextual information and consider the interaction between the points. The evaluation executed on a per-point level shows that the fusion of all available information types together with context consideration allows us to extract objects with 90% completeness and 95% correctness. A respective assessment executed on a per-object level shows 97% completeness and 88% accuracy.

show abstract

Section: Data Acquisitionmentioning

confidence: 99%

“…(2019) [24]. Since the influence of emissivity on the temperature value is very small, the emissivity correction can be neglected for the presented application case.…”

Section: Data Acquisitionmentioning

confidence: 99%

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, Lin et al, [23] merged terrestrial thermal imagery and point clouds obtained from RGB imagery for the inspection of building insulation. Without the requirements of georeferencing data and prior relative pose knowledge, registration is implemented by coarse point cloud registration, fine matching of image pairs, and global image pose refinement.…”

Section: Vidas and Moghadammentioning

confidence: 99%

“…Multiple thermal cameras (four in this study) from different perspectives with a fixed relative pose are able to significantly increase the vertical and horizontal overlap, which is helpful in improving the number of tie points in the SfM procedure [1,23]. In addition, similar to the existing publications [23,33,34], a Wallis filter was applied to enhance the image contrast before point cloud generation. These filtered images were used to improve the quality of the generated thermal point clouds, while temperature images used for thermal attribute mapping were acquired after the radiometric calibration procedure (Section 3.1).…”

Section: Point Cloud Generationmentioning

confidence: 99%

“…Firstly, the registration between thermal imagery and RGB photogrammetric point clouds is conducted by a coarse point cloud registration supported by global positioning system (GPS) data and a fine point cloud registration based on iterative closest point (ICP). Then, in order to achieve great photogrammetric consistency of thermal attribute mapping results, three different strategies including texture selection based on thermal radiant characteristics [29], mean temperature computation of overlapping images [18], and global image pose refinement [23] are compared and tested on three different areas (built-up area, water area, bare soil). Relative registration accuracy between sensors rather than absolute geometric accuracy is used to evaluate the texture mapping results.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Thermal Attribute Mapping Strategies for Oblique Airborne Photogrammetric System AOS-Tx8

et al. 2019

Self Cite

View full text Add to dashboard Cite

Thermal imagery is widely used in various fields of remote sensing. In this study, a novel processing scheme is developed to process the data acquired by the oblique airborne photogrammetric system AOS-Tx8 consisting of four thermal cameras and four RGB cameras with the goal of large-scale area thermal attribute mapping. In order to merge 3D RGB data and 3D thermal data, registration is conducted in four steps: First, thermal and RGB point clouds are generated independently by applying structure from motion (SfM) photogrammetry to both the thermal and RGB imagery. Next, a coarse point cloud registration is performed by the support of georeferencing data (global positioning system, GPS). Subsequently, a fine point cloud registration is conducted by octree-based iterative closest point (ICP). Finally, three different texture mapping strategies are compared. Experimental results showed that the global image pose refinement outperforms the other two strategies at registration accuracy between thermal imagery and RGB point cloud. Potential building thermal leakages in large areas can be fast detected in the generated texture mapping results. Furthermore, a combination of the proposed workflow and the oblique airborne system allows for a detailed thermal analysis of building roofs and facades.

show abstract

3D Thermal Mapping of Architectural Heritage

Adamopoulos

Patrucco

Volinia

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The combination of thermographic and geometric recording has always been an issue for architectural heritage diagnostic investigations. Multidisciplinary projects often require integrating multi-sensor informationincluding metric and temperature data-to extract valid conclusions regarding the state-of-preservation of historical buildings. Towards this direction, recent technological advancements in thermographic cameras and three-dimensional (3D) documentation instrumentation and software have contributed significantly, assisting the rapid creation of detailed 3D thermal-textured results, which can be exploited for non-destructive diagnostical surveys. This paper aims to briefly review and evaluate the current workflows for thermographic architectural 3D modeling, which implement state-of-the-art sensing procedures and processing techniques, while also presenting some applications on case studies of significant heritage value to help discuss current problems and identify topics for relevant future research.

show abstract

Fusion of thermal imagery with point clouds for building façade thermal attribute mapping

Cited by 55 publications

References 17 publications

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Supervised Detection of Façade Openings in 3D Point Clouds with Thermal Attributes

Evaluating Thermal Attribute Mapping Strategies for Oblique Airborne Photogrammetric System AOS-Tx8

3D Thermal Mapping of Architectural Heritage

Contact Info

Product

Resources

About