Mvtec Software Gmbh

Universitat Leipzig

Markus Ulrich

Carsten Steger

Bertram Heinrich Drost

Tobias Böttger

Christian Wiedemann

Bertram Drost

The invention describes a generic framework for hand-eye calibration of camera-guided apparatuses, wherein the rigid 3D transformation between the apparatus and the camera must be determined. An example of such an apparatus is a camera-guided robot.

Hand-eye calibration of camera-guided apparatuses

In this invention, systems and methods are described that allow performing stereo reconstruction with line-scan cameras in general configurations. Consequently, the cumbersome exact alignment of the sensor lines becomes superfluous. The proposed method requires that telecentric lenses instead of perspective lenses are mounted on the line-scan cameras. In this case, the images can be accurately rectified with stereo rectification. The rectified images can be used to perform an efficient stereo matching. The method comprises a camera model and a calibration procedure that allow to precisely model the imaging process, also including the modelling of lens distortions even if the sensor lines are not exactly mounted behind the principal points. This ensures a high accuracy of the resulting 3D reconstruction.

System and method for efficient 3D reconstruction of objects with telecentric line-scan cameras

A method for adapting a matching model of an object comprising the step of providing an electronic image of the object; providing a matching model of the object, the matching model consisting of a plurality of points; determining a pose of the object in said electronic image by using a matching approach that uses said matching model; transforming the matching model according to said pose, yielding a transformed model; determining for at least one point of said transformed model a corresponding point in said electronic image; and adapting the matching model according to the at least one determined corresponding point.

System and method for model adaptation

The invention provides a method for recognizing instances of a 3D object in 3D scene data and scene intensity data and for determining the 3D poses of said instances comprising the following steps: (a) providing 3D object data and obtaining object intensity data; (b) providing 3D scene data and scene intensity data; (c) extracting scene feature points from the intensity data; (d) selecting at least one reference point from the 3D scene data; (e) computing, for each selected reference point, pose candidates for the 3D object under the assumption that said reference point is part of the 3D object by maximizing the number of extracted scene feature points that are consistent with the 3D object under the given pose candidate; (f) computing a set of filtered poses from the pose candidates.

Recognition and pose determination of 3D objects in multimodal scenes

The invention provides a method for recognizing instances of a 3D object in 3D scene data and for determining the 3D poses of said instances comprising the following steps: (a) providing 3D scene data; (b) selecting at least one reference point from the 3D scene data; (c) computing, for each selected reference point, pose candidates for the 3D object under the assumption that said reference point is part of the 3D object; and (d) computing a set of filtered poses from the pose candidates.

Recognition and pose determination of 3D objects in 3D scenes

The present invention provides a system and method for recognizing a 3D object in a single camera image and for determining the 3D pose of the object with respect to the camera coordinate system. In one typical application, the 3D pose is used to make a robot pick up the object. A view-based approach is presented that does not show the drawbacks of previous methods because it is robust to image noise, object occlusions, clutter, and contrast changes. Furthermore, the 3D pose is determined with a high accuracy. Finally, the presented method allows the recognition of the 3D object as well as the determination of its 3D pose in a very short computation time, making it also suitable for real-time applications. These improvements are achieved by the methods disclosed herein.

System and method for 3D object recognition

The present invention provides a system and methods for automatic parameter determination in machine vision in general, and in object recognition in particular. Many machine vision systems use algorithms that demand the user to specify one or more parameters in order to adapt the behavior of the algorithm in dependence of the current application. This is not desirable because the complexity of the algorithm should be hidden from the user and a manual parameter determination is contrary to a desirable high degree of automation. The present invention provides a method to automatically determine the most frequently used parameters in machine vision solely based on the input image itself. The method is explained in detail using an object recognition system as an example. In particular, the model generation process based on a model image of the object is explained. However, also other systems that use edge extraction algorithms, for example, can benefit from the present invention.

System and methods for automatic parameter determination in machine vision

The present invention provides a method for the recognition of objects in an image, where the objects may consist of an arbitrary number of parts that are allowed to move with respect to each other. In the offline phase the invention automatically learns the relative movements of the single object parts from a sequence of example images and builds a hierarchical model that incorporates a description of the single object parts, the relations between the parts, and an efficient search strategy. This is done by analyzing the pose variations (e.g., variations in position, orientation, and scale) of the single object parts in the example images. The poses can be obtained by an arbitrary similarity measure for object recognition, e.g., normalized cross correlation, Hausdorff distance, generalized Hough transform, the modification of the generalized Hough transform, or the similarity measure. In the online phase the invention uses the hierarchical model to efficiently find the entire object in the search image. During the online phase only valid instances of the object are found, i.e., the object parts are not searched for in the entire image but only in a restricted portion of parameter space that is defined by the relations between the object parts within the hierarchical model, what facilitates an efficient search and makes a subsequent validation step unnecessary.

Growing community of inventors

Munich, Germany

Markus Ulrich