Academic literature on the topic 'Image-to-BIM Registration'

Abstract. Construction progress documentation is currently of great interest for the AEC (Architecture, Engineering and Construction) branch and BIM (Building Information Modeling). Subject of this work is the geometric accuracy assessment of image-based change detection in indoor environments based on a BIM. Line features usually serve well as geodetic references in indoor scenes in order to solve for camera orientation. However, building edges are never perfectly built as planned and often geometrically generalized for BIM compliant representation. As a result, in this approach, line correspondences for image-to-model co-registration are considered as statistically uncertain entities as this is essential for dealing with metric confidences in the field of civil engineering and BIM. We present an estimation model for camera pose refinement which is based on the incidence condition between model edges and corresponding image lines. Geometric accuracies are assigned to the model edges according to the Level of Accuracy (LOA) specification for BIM. The approach is demonstrated in a series of tests using a synthetic image of an indoor BIM. The effects of varying edge detection accuracies on the estimation are investigated as well as the effects of using model edges with different geometric quality by adding Gaussian noise to the synthetic observations, each within 100 simulation runs. The results show that the camera orientation can be improved with the presented estimation model as long as the BIM compliant references meet the conditions of LOA 30 or higher (σ < 7.5 mm).

Abstract. The application of mixed reality visualisation in construction engineering requires accurate placement and retrieval of virtual models within the real world, which depends on the localisation accuracy. However, it is hard to understand what this means practically from localisation accuracy alone. For example, when we superimpose a Building Information Model (BIM) over the real building, it is unclear how well does a BIM element fit the real one and how small a BIM element are we able to retrieve. In this paper, we evaluate virtual element retrieval by designing an experiment where we attempt to retrieve a set of cubes of different sizes placed in both the real and the virtual world. Furthermore, inspired by existing camera localisation methods for indoor MR being almost exclusively image-based, we use a localisation approach based solely on 3D-3D model registration. The approach is based on the automated registration of a low-density mesh model of the surroundings created by the MR device to the existing point cloud of an indoor environment. We develop a prototype and perform experiments on real-world data which show high localisation accuracy, with average translation and rotation errors of 1.4 cm and 0.24°, respectively. Finally, we show that the success rate of virtual element retrieval is closely related to the localisation accuracy.

With the emergence of XR technologies, the demand for new time- and cost-saving applications in the AEC industry based on these new technologies is rapidly increasing. Their real-time feedback and digital interaction in the field makes these systems very well suited for construction site monitoring, maintenance, project planning, and so on. However, the continuously changing environments of construction sites and facilities requires extraordinary robust and dynamic data acquisition technologies to capture and update the built environment. New XR devices already have the hardware to accomplish these tasks, but the framework to document and geolocate multi-temporal mappings of a changing environment is still very much the subject of ongoing research. The goal of this research is, therefore, to study whether Lidar and photogrammetric technologies can be adapted to process XR sensory data and align multiple time series in the same coordinate system. Given the sometimes drastic changes on sites, we do not only use the sensory data but also any preexisting remote sensing data and as-is or as-designed BIM to aid the registration. In this work, we specifically study the low-resolution geometry and image matching of the Hololens 2 during consecutive stages of a construction. During the experiments, multiple time series of constructions are captured and registered. The experiments show that XR-captured data can be reliably registered to preexisting datasets with an accuracy that matches or exceeds the resolution of the sensory data. These results indicate that this method is an excellent way to align generic XR devices to a wide variety of existing reference data.

Abstract. The co-registration of photogrammetric products such as image blocks or point clouds is an essential step before they can be used for subsequent analysis. Usually this is done by using control points. This has some disadvantages such as the need for additional measuring devices and a laborious measuring of the coordinates. In prior works we developed a procedure that enables a marker-less co-registration of an image block with a digital building model. This extended abstract presents our current research as work-progress. For further facilitating and improving this process we identified two tasks. Using videogrammetry as data capturing technique and using an enhanced matching algorithm during the co-registration. This paper summarizes essential steps when making the switch from photogrammetry to videogrammetry and explains the basic principles of the improved matching process.

<p>With the improvement of the informatization and digitization of bridge structures, the importance of technologies such as Building Information Modeling(BIM) and computer vision is constantly increasing. This type of technology all relies on a scan of the structure's appearance. However, based on the principle of optical imaging, there is a contradiction between imaging field of view(FOV) and pixel resolution. Therefore, the existing apparent detection or scanning technology either uses lower pixel resolution to obtain the structured apparent image at the panoramic scale, or a series of scattered high-resolution images in a local area, which has caused two aspect of defects in the detection of apparent damage. On the one hand, low-resolution image data has an adverse effect on the accuracy of deep learning or machine vision models. On the other hand, due to the single surface texture of concrete materials, the number of feature points is scarce in image processing, which reduces the stability of the image stitching algorithm based on feature points. These problems make the apparent images collected in the current inspection work cannot be well applied to the long-term evolution analysis of apparent damage. In order to achieve high-resolution imaging within the panoramic range of the structure, we propose a panoramic image stitching method. Firstly, the traditional single-view imaging is extended to multi-view imaging, and the result images are used for panoramic stitching. Because the feature information in a single image is greatly increased, the stability of the image stitching algorithm based on feature point matching has also been greatly improved. Secondly, through experiments, we determine the number of cameras with the highest efficiency for this novel panoramic image stitching method. Lastly, based on real bridge image data, we evaluate and compare several image stitching algorithms in terms of accuracy, efficiency, and robustness. The experimental results show that this panoramic image stitching method can be well adapted to the apparent scanning task of large-scale components in concrete bridges, and is meaningful for the standardization and automatic acquisition of structural appearance images.</p>