Spatially resolved stereoscopic surface profiling by using a feature-selective segmentation and merging technique

Abstract

We present a feature-selective segmentation and merging technique to achieve spatially resolved surface profiles of the parts by 3D stereoscopy and strobo-stereoscopy. A pair of vision cameras capture images of the parts at different angles, and 3D stereoscopic images can be reconstructed. Conventional filtering processes of the 3D images involve data loss and lower the spatial resolution of the image. In this study, the 3D reconstructed image was spatially resolved by automatically recognizing and segmenting the features on the raw images, locally and adaptively applying super-resolution algorithm to the segmented images based on the classified features, and then merging those filtered segments. Here, the features are transformed into masks that selectively separate the features and background images for segmentation. The experimental results were compared with those of conventional filtering methods by using Gaussian filters and bandpass filters in terms of spatial frequency and profile accuracy. As a result, the selective feature segmentation technique was capable of spatially resolved 3D stereoscopic imaging while preserving imaging features.

Applying Gaussian mixture models for enhanced characterization of featured surfaces and mixed lubrication analysis

“…However, the presence of distinct features on surfaces poses a challenge to accurately describing their topography. Therefore, effective segmentation methods are required to overcome this limitation [7]. Segmentation involves dividing the surface into distinct components, allowing researchers to identify and analyze specific features or regions of interest, thus enabling a deeper understanding of their contribution to the overall functionality of surface textures [8].…”

A Single Camera Unit-based Three-Dimensional Surface Imaging Technique

“…With the development of high-resolution and high-speed imaging systems along with highperformance computational algorithms [5,6], 3D imaging technology can be adapted to numerous applications in many ways, combining various 3D surface imaging schemes and high-performance software technology including artificial intelligence. Since a few decades, numerous 3D surface imaging techniques have been introduced: stereoscopy [7,8], strobe stereoscopy [9][10][11], structured light 3D scanning [12][13][14], time-of-flight scanning [15], interferometry [16], holographic imaging [17], and so on. The 3D surface imaging techniques mentioned above have their own peculiarities in terms of application.…”

“…Stereoscopy is the most widely used due to its low cost and compact configuration, but it is limited to non-textured (smooth) 3D surface feature measurements because no difference in pixel intensities between the left and right images results in failure of the 3D image reconstruction. Guo et al recently introduced strobe stereoscopy, which combines stereoscopy and stroboscopy for in-process 3D surface imaging of the rotating target, but it is also limited to non-textured part measurement [9][10][11]. The structured light scanning method uses time-varying and spatial frequency modulated fringe patterns incident on the target surface.…”