In this paper, we will derive a phenomenological model of the bidirectional
reflectance distribution function of non-Lambertian metallic
materials typically used in industrial inspection. We will show, how
the model can be fitted to measured reflectance values and how the
fitted model can be used to determine a suitable illumination position.
Together with a given sensor pose, this illumination position can
be used to calculate the necessary shutter time, aperture, focus setting
and expected gray value to successfully perform a given visual inspection
task. The paper concludes with several example inspection tasks.
In this paper we present a novel image-based 3D surface reconstruction technique that incorporates both reflectance and polarisation features into a variational framework. The proposed technique is suitable for single-image and multi-image (photopolarimetric stereo) analysis. It is especially suited for the difficult task of 3D reconstruction of rough metallic surfaces. An error functional consisting of several error terms related to the measured reflectance and polarisation properties is minimised in order to obtain a 3D reconstruction of the surface. We show that the combined approach strongly increases the accuracy of the surface reconstruction result, compared to techniques based on either reflectance or polarisation alone. We perform an evaluation of the algorithm with respect to single and multiple reflectance and polarisation images of the surface, relying on synthetic ground truth data. This evaluation also reveals which polarisation features should preferably be used in the context of 3D reconstruction of rough metallic surfaces. Furthermore, we report 3D reconstruction results for a raw forged iron surface, thus showing the applicability of our method in real-world scenarios, here in the domain of industrial quality inspection.
A complete framework for automatic calibration of camera systems with an arbitrary number of image sensors is presented. This new approach is superior to other methods in that it obtains both the internal
and external parameters of camera systems with arbitrary resolutions, focal lengths, pixel sizes, positions and orientations from calibration rigs printed on paper. The only requirement on the placement of the cameras is an overlapping field of view. Although the basic algorithms are suitable for a very wide range of camera models (including OmniView and fish eye lenses) we concentrate on the
camera model by Bouguet (http://www.vision.caltech.edu/bouguetj/). The most important part of the calibration process is the search for the calibration rig, a checkerboard. Our approach is based on the topological analysis of the corner candidates. It is suitable for a wide range of sensors, including OmniView cameras, which is demonstrated by finding the rig in images of such a camera. The internal calibration of each camera is performed as proposed by Bouguet, although this may be replaced with a different model. The
calibration of all cameras into a common coordinate system is an optimization process on the spatial coordinates of the calibration rig. This approach shows significant advantages compared to the method of Bouguet, esp. for cameras with a large field of view. A comparison of our automatic system with the camera calibration toolbox for MATLAB, which contains an implementation of the Bouguet calibration, shows its increased accuracy compared to the manual approach.
In this paper a novel framework for surface quality inspection of industrial parts based on three-dimensional surface reconstruction by self-consistent fusion of shading and shadow features is presented. Relying on the analysis of at least two pixel-synchronous greyscale images of the scene acquired under very different illumination conditions, this framework combines a shadow analysis of the first image of the scene, allowing for a determination of large-scale altitude differences on the surface at high accuracy, with a variational shape from shading scheme applied to the second image (and eventually to further images), estimating the surface gradients and altitude profile. In a first step, the result of shadow analysis is used for selecting a solution of the variational shape from shading scheme which is consistent with the average altitude difference derived by shadow analysis. In a second step, the detailed shadow structure is taken into account. An error term that aims at adjusting the altitude differences extracted from the reconstructed surface profile to those derived from shadow analysis is incorporated into the error function to be minimized by the variational shape from shading scheme. The second reconstruction step is initialized with the result of the first step. In contrast to existing shape from shading or photometric stereo approaches, our algorithm shows the advantage that it neither requires a very accurate knowledge of the reflectance function of the surface to be reconstructed, nor does it critically depend on the initialization. The described framework is applied to the three-dimensional reconstruction of metal sheet and raw cast iron surfaces in the context of industrial quality inspection.
In this paper, we will describe a real-time stereo vision algorithm that determines the disparity map of a given scene by an evaluation of the object contours, relying on a reference image displaying the scene without objects. Contours are extracted from the full-resolution absolute difference image between current and reference image by binarization with several locally adaptive thresholds. To estimate disparity values, contour segments extending over several epipolar lines are used. This approach leads to very accurate disparity values. The algorithm can be configured such that no image region that differs from the reference image by more than a given minimum statistical significance is overlooked, which makes it especially suitable for safety applications.
We successfully apply this contour based stereo vision (CBS)algorithm to the task of video surveillance of hazardous areas in the production environment, regarding several thousands of test images. Under the harsh conditions encountered in this setting, the CBS algorithm achieves to faithfully detect objects entering the scene and determine their three-dimensional structure. What is more, it turns out to cope with small objects and very difficult illumination and contrast settings.