![]() ![]() When adopted to thermographic building diagnostics, AR can provide a valuable and intuitive tool for integrating images from a thermal infrared (TIR) survey into the real architectural context. In recent years the applications of AR in the architecture, engineering, construction and facility management (AEC/FM) industry have been constantly explored ( Behzadan et al. 2014).Īugmented reality (AR) technology enables users to view the real world enhanced with computer-generated information. 2014) and surveillance systems for human detection and tracking ( Gade and Moeslund 2014 Kong et al. The respective pros and cons of thermal and visible images make them complement each other very well so both modalities are widely employed in building diagnostics ( Balaras and Argiriou 2002 Gade and Moeslund 2014 Kylili et al. Among the drawbacks inherent to thermal images are low spatial resolution, poor quality and lack of visual detail ( Choi et al. On the other hand, thermal cameras work with the heat radiation emitted by objects so they do not require visible illumination to function instead daylight is often avoided when thermal imaging is used for diagnostic purposes. However, their quality is greatly degraded when there is no sufficient lighting. Visible images captured by standard digital cameras have high spatial resolution and are rich in visual details. 2011) and medicine ( Oliveira and Tavares 2014). Such a benefit has made multimodality image registration a vital process in fields like remote sensing ( Dawn et al. ![]() Through image registration, these properties are integrated to provide us with a thorough understanding of the scene represented. Quantitative evaluation of our method shows that registration errors are lower than errors reported in similar studies and registration performance is usable for most tasks in thermographic inspection of building façades.ĭue to diverse mechanisms of different kinds of imaging sensors, multimodal images are capable of characterizing various distinct properties of a scene. During the formation of the feature correspondence set, the correctness of selected feature correspondences at each step is verified by the quality of the resulting registration, which is based on the ratio of areas between the transformed features and the reference features. Our method adopts a forward selection algorithm to determine feature correspondences needed for estimating the transformation model. ![]() The features result from grouping edge line segments with the help of image perspective information, namely, vanishing points. MethodsĪ novel quadrilateral feature is devised for this task, which models the shapes of commonly present façade elements, such as windows. This paper addresses the problem of registering thermal infrared and visible façade images, which is essential towards developing an AR-based building diagnostics application. Augmented reality (AR) technology, which supplements the real world with virtual objects, offers an ideal tool for presenting the combined results of thermal infrared and visible images. Therefore, it is often useful to register images of these two modalities for further inspection of architectures. However, the lack of visual details in thermal infrared images makes the complement of visible images a necessity. In virtue of their capability to measure temperature, thermal infrared cameras have been widely used in building diagnostics for detecting heat loss, air leakage, water damage etc. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |