Optical methods for deformations diagnostic and surface shape measurement are widely used in scientific research and industry. Most of these methods are based on triangulating a set of two-dimensional points in the images appropriate to the same three-dimensional points of the object in space. Various algorithms to search such points are applied. The possibility of using cross-correlation processing of digital images to search these points is considered in the work. Algorithms based on the correlation function calculation are widely employed in such a popular flow diagnostic method as PIV. The cameras of a stereo system for surface shape measurement can be widely spaced, and the tilt angles relative to the surface can differ significantly. This leads to the fact that the images taken from the cameras cannot be directly processed by the correlation function because it is not invariant to rotation. To solve this problem, fiducial markers are used to find an initial estimate of displacement of the images relative to each other. This approach makes it possible to successfully apply correlation processing for stereo system images with a large stereo base.
Close-range photogrammetry is widely used to measure the surface shape of various objects and its deformations. The classic approach for this is to use a stereo pair of images, which are captured from different angles using two digital video cameras. The surface shape is measured by triangulating a set of corresponding two-dimensional points from these images using a predetermined location of cameras relative to each other. Various algorithms are used to find these points. Several photogrammetry methods use cross-correlation for this purpose. This paper discusses the possibility of replacing the correlation algorithm with neural networks to determine displacements of small areas in the images. They allow increasing the calculation speed and the spatial resolution of the measurement results. To verify the possibility of using convolutional networks for photogrammetry tasks, computer and physical modeling were carried out. For the first test, a set of synthetically generated images representing images of the Particle Image Velocimetry method was used. The displacements of particles in the images are known, it allows to estimate the accuracy of processing of such images. For the second test, a series of experimental images with surfaces with different deformation was obtained. Computational experiments were performed to process synthetic and experimental images using selected neural networks and a classical cross-correlation algorithm. The limitations on the use of the compared algorithms were determined and their error in reconstructing the three-dimensional shape of the surface was evaluated. Computer and physical modeling have shown the operability and efficiency of neural networks for processing photogrammetry images.
Close-range photogrammetry is widely used to measure the surface shape of various objects and its deformations. Usually, a stereo pair of images of the object under study, obtained from different angles by means of several digital video cameras, is used for this purpose. The surface shape is measured by triangulating a set of corresponding two-dimensional points from these images using a predetermined location of cameras relative to each other. Various algorithms are used to find these points. Several photogrammetric methods use cross-correlation for this purpose. This paper discusses the possibility of replacing the correlation algorithm with neural networks to determine offsets in the images. They allow to increase the calculation speed and the spatial resolution of the measurement results. To verify the possibility of their application, a series of experimental images of surfaces with different deformations were obtained. Computational experiments were performed to process these images using selected neural networks and a classical cross-correlation algorithm. The limitations on the use of the compared algorithms were determined and their error in restoring the three-dimensional shape of the surface was estimated. The physical simulation to verify the selected neural networks for image processing for the task of photogrammetry showed their performance and efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.