ONE SHOT OPTICAL 3D SURFACE RECONSTRUCTION OF WEAK TEXTURED OBJECTS FOR AN AGRICULTURAL APPLICATION

Optical 3D measurement is meaningful in numerous industrial applications. In various cases, the objects to be measured moreover contain only sparse or even no texture. Predestinated examples are agricultural products like peeled potato tubers as well as industrial repetition parts made of plastic or ceramic, such as housing parts or ceramic bottles. These parts are often conveyed in a wobbling way during the automated optical inspection. Thus, conventional 3D shape acquisition methods like laser scanning might fail. In this paper, a novel approach for acquiring 3D shape of weak textured and moving objects is presented. It is primarily intended for automated optical quality assurance in field of agricultural processing industry. To facilitate such measurements, an active stereo vision system with structured light is proposed. The system consists of multiple camera pairs and auxiliary laser pattern generators. The shape acquisition is performed within one shot and is therefore beneficial for rapid inspection tasks. An experimental setup, including hardware and software, has been developed and implemented.

[1]  Jing Luo,et al.  Two Cameras Vision Model for the 3D Shape Recovery , 2009, 2009 Fifth International Conference on Natural Computation.

[2]  Mohan M. Trivedi,et al.  3-D Computer Vision Using Structured Light: Design, Calibration, and Implementation Issues , 1996, Adv. Comput..

[3]  Helmut Hamfeld.  Aktive Stereoskopie: neue Verfahren zur dreidimensionalen Vermessung von Objekten , 2002 .

[4]  Klaus D. Tönnies.  Grundlagen der Bildverarbeitung , 2005 .

[5]  Yasushi Yagi,et al.  Dynamic scene shape reconstruction using a single structured light pattern , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Kristian Ambrosch,et al.  Accurate hardware-based stereo vision , 2010, Comput. Vis. Image Underst..

[7]  Lilong Cai,et al.  Accurate Dimensional Measurement of 3D Round Holes Based on Stereo Vision , 2009 .

[8]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Antonios Gasteratos,et al.  Review of Stereo Vision Algorithms: From Software to Hardware , 2008 .

[10]  Bernd Michaelis,et al.  A Stereo Vision System for Top View Book Scanners , 2009 .

[11]  Michael Weyrich,et al.  Vision based defect detection on 3D objects and path planning for processing , 2011 .

[12]  Gui Gao,et al.  A Fast Structured Light Matching Method in Robot Stereo Vision , 2010 .

[13]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[14]  S. Tosovic,et al.  On Combining Shape from Silhouette and Shape from Structured Light ∗ , 2002 .

[15]  Alberto Tellaeche,et al.  Automatic Inspection of Percussion Caps by Means of Combined 2D and 3D Machine Vision Techniques , 2010 .

[16]  Moulay A. Akhloufi.  Real-time 3D visual servoing of an industrial cutting robot manipulator , 2009 .

[17]  Sebastian Thrun,et al.  High-quality scanning using time-of-flight depth superresolution , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[18]  A. U.S.,et al.  Recovering Surface Shape and Orientation from Texture , 2002 .

[19]  Bin Liu,et al.  A mesh-candidate-based 3D reconstruction system for online depth recovery , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[20]  Michael Weyrich,et al.  Optical 3D-Surface Reconstruction of Weak Textured Objects Based on an Approach of Disparity Stereo Inspection , 2011 .

[21]  Ping-Sing Tsai,et al.  Shape from Shading: A Survey , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Alan C. Bovik,et al.  Shape from Texture Using Local Spectral Moments , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Boubakeur Boufama,et al.  Multibaseline stereo using a single-lens camera , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[24]  Jürgen Wahrburg,et al.  Entwicklung eines robotergeführten Lichtschnittsensors für die berührungslose Erfassung anatomischer Strukturen , 2010, CURAC.

[25]  Paul J. Besl,et al.  Active, optical range imaging sensors , 1988, Machine Vision and Applications.

[26]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[27]  Tae-Sun Choi,et al.  Recovering 3D Shape of Weak Textured Surfaces , 2009, 2009 International Conference on Computational Science and Its Applications.