The objective of the study was to create a printable 3D model of the sellar region of the sphenoid bone for demonstrating anatomical variant of the osseous bridging between anterior and posterior clinoid processes. Three-dimensional reconstruction of the middle cranial fossa along with 3D printed model, allow for accurate depicting position of the interclinoid bridge with reference to other basicranial structures.
The techniques of photogrammetric reconstruction were compared to the laser scanning in the article. The different conditions and constraints were introduced for reconstructed images, e.g. different materials, lighting condition, camera resolution, number of images in the sequence or using a-pripori calibration. The authors compare the results of surface reconstruction using software tools avaliable for photogrammetric reconstruction. The analysis is preformed for the selected objects with regard to laserscanned models or mathematical models.
The task of generating fast and accurate three-dimensional (3D) models of objects or scenes through a sequence of non-calibrated images is an active field of research. The recent development in algorithm optimization has resulted in many automatic solutions that can provide an accurate 3D model from texture-full objects. Structure-from-motion (SfM) is an image-based method that uses discriminative point-based feature identifier, such as SIFT, to locate feature points in the images. This method faces difficulties when presented with the objects made of homogenous or texture-less surfaces. To reconstruct such surfaces a well-known technique is to apply an artificial variety by covering the surface with a random texture pattern prior to the image capturing process. In this work, we designed three series of image patterns which are tested based on the contrast and density ratio which increases from the first to the last pattern within the same series. The performance of the patterns is evaluated by reconstructing the surface of a texture-less object and comparing it with the true data. Using the best-found patterns from the experiments, a 3D model of a Moai statue is reconstructed. The experimental results demonstrate that the density and structure of a pattern highly affects the quality of the reconstruction.
Despite the progress in digitization of civil engineering, the process of bridge inspection is still outdated. In most cases, its documentation consists of notes, sketches and photos. This results in significant data loss during structure maintenance and can even lead to critical failures. As a solution to this problem, many researchers see the use of modern technologies that are gaining popularity in civil engineering. Namely Building Information Modelling (BIM), 3D reconstruction and Artificial Intelligence (AI). However, despite their work, no particular solution was implemented. In this article, we evaluated the applicability of state-of-the-art methods based on a case study. We have considered each step starting from data acquisition and ending on BIM model enrichment. Additionally, the comparison of deep learning crack semantic segmentation algorithm with human inspector was performed. Authors believe that this kind of work is crucial for further advancements in the field of bridge maintenance.