Abstract
Industrial quality inspection is an important application domain of three-dimensional computer vision methods. Traditional vision-based industrial quality inspection systems primarily rely on two-dimensional detection and pose estimation algorithms e.g. relying on the detection of point and line features, the extraction of blob features from binarised images, or two-dimensional grey value correlation techniques. More advanced vision-based quality inspection systems employ three-dimensional methods in order to detect production faults more reliably and robustly. In this section we regard applications in the automobile industry of the methods for three-dimensional pose estimation of rigid and articulated objects described in previous chapters. A typical area of interest is checking for completeness of a set of small parts attached to a large workpiece, such as plugs, cables, screws, and covers mounted on a car engine. A different task is the inspection of the position and orientation of parts, e.g. for checking if they are correctly mounted but also for grasping and transporting them with an industrial robot. For each scenario we compare our evaluation results to results reported in the literature for systems performing similar inspection tasks. Furthermore, we describe applications of the developed integrated approaches to the three-dimensional reconstruction of rough metallic surfaces of automotive parts.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In all experiments, the same blockmatching threshold was used. Slightly decreasing this threshold for the star pattern example would have resulted in more than one initial three-dimensional point. However, this somewhat extreme configuration was used intentionally in order to illustrate that this information is sufficient to obtain convergence of the specular stereo scheme.
References
Atkinson, G. A., Hancock, E. R., 2005b. Multi-view surface reconstruction using polarization. Proc. Int. Conf. on Computer Vision, Beijing, pp. 309–316.
Bachler, G., Berger, M., Röhrer, R., Scherer, S., Pinz, A., 1999. A vision driven automatic assembly unit. Proc. International Conference on Computer Analysis of Images and Patterns, Ljubljana, Slovenia, pp. 375–382.
Barrois, B., Wöhler, C., 2007. 3D pose estimation based on multiple monocular cues. ISPRS Workshop Towards Benchmarking Automated Calibration, Orientation and Surface Reconstruction from Images (BenCOS), held in conjunction with CVPR 2007, Minneapolis, USA.
Batlle, J., Mouaddib, E., Salvi, J., 1998. Recent progress in coded structured light as a technique to solve the correspondence problem: a survey. Pattern Recognit. 31(7), pp. 963–982.
Beraldin, J.-A., 2004. Integration of laser scanning and close-range photogrammetry—the last decade and beyond. Proc. 20th Int. Soc. for Photogrammetry and Remote Sensing Congress, Commission VII, pp. 972–983.
Chang, J. Y., Raskar, R., Agrawal, A., 2009. 3D pose estimation and segmentation using specular cues. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1706–1713.
Collet, A., Martinez, M., Srinivasa, S., 2011. The MOPED framework: object recognition and pose estimation for manipulation. Int. J. Robot. Res. 30(10), pp. 1284–1306.
d’Angelo, P., Wöhler, C., Krüger, L., 2004. Model based multi-view active contours for quality inspection. Proc. Int. Conf. on Computer Vision and Graphics, Warszaw, Poland.
d’Angelo, P., Wöhler, C., 2005a. 3D reconstruction of metallic surfaces by photopolarimetric analysis. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.), Proc. 14th Scand. Conf. on Image Analysis, Joensuu, Finland. Lecture Notes in Computer Science 3540, pp. 689–698, Springer, Berlin.
d’Angelo, P., Wöhler, C., 2005b. 3D surface reconstruction based on combined analysis of reflectance and polarisation properties: a local approach. ISPRS Workshop Towards Benchmarking Automated Calibration, Orientation and Surface Reconstruction from Images (BenCOS), Beijing, China.
d’Angelo, P., Wöhler, C., 2005c. 3D surface reconstruction by combination of photopolarimetry and depth from defocus. In: Kropatsch, W., Sablatnig, R., Hanbury, A. (eds.). Pattern Recognition, Proc. 27th DAGM Symposium, Vienna, Austria. Lecture Notes in Computer Science 3663, pp. 176–183, Springer, Berlin.
d’Angelo, P., Wöhler, C., 2006. Image-based 3D surface reconstruction by combination of sparse depth data with shape from shading and polarisation. ISPRS Conf. on Photogrammetric Computer Vision, Bonn, Germany.
d’Angelo, P., Wöhler, C., 2008. Image-based 3D surface reconstruction by combination of photometric, geometric, and real-aperture methods. ISPRS J. Photogramm. Remote Sens. 63(3), pp. 297–321.
Demant, C., 1999. Industrial Image Processing. Springer, Berlin.
Hahn, M., Barrois, B., Krüger, L., Wöhler, C., Sagerer, G., Kummert, F., 2010a. 3D pose estimation and motion analysis of the articulated human hand-forearm limb in an industrial production environment. 3D Research 03, 03.
Hahn, M., Krüger, L., Wöhler, C., Groß, H.-M., 2007. Tracking of human body parts using the multiocular contracting curve density algorithm. Proc. Int. Conf. on 3-D Digital Imaging and Modeling, Montréal, Canada.
Herbort, S., Grumpe, A. & Wöhler, C., 2011. Reconstruction of non-Lambertian surfaces by fusion of shape from shading and active range scanning. Proc. IEEE Int. Conf. Image Process.
Herbort, S., Wöhler, C., 2012. Self-consistent 3D surface reconstruction and reflectance model estimation of metallic surfaces. Proc. Int. Conf. on Computer Vision Theory and Applications, Rome, Italy.
Horn, B. K. P., 1989. Height and Gradient from Shading. MIT Technical Report, AI memo, no. 1105A.
Kölzow, T., Ellenrieder, M., 2003. A general approach for multi-feature, multi-sensor classification and localization of 3D objects in 2D image sequences. Proc. SPIE-IS&T Electronic Imaging, SPIE 5014, pp. 99–110.
Krüger, L., 2007. Model Based Object Classification and Localisation in Multiocular Images. Doctoral Dissertation, Technical Faculty, Bielefeld University, Germany.
Krüger, L., Ellenrieder, M. M., 2005. Pose estimation using the multiocular contracting curve density algorithm. Proc. 10th Int. Fall Workshop on Vision, Modeling, and Visualization, Erlangen, Germany.
Krüger, L., Wöhler, C., Würz-Wessel, A., Stein, F., 2004. In-factory calibration of multiocular camera systems. Proc. SPIE Photonics Europe (Optical Metrology in Production Engineering), Strasbourg, pp. 126–137.
McEwen, A. S., 1991. Photometric functions for photoclinometry and other applications. Icarus 92, pp. 298–311.
Mühlmann, K., 2002. Design und Implementierung eines Systems zur schnellen Rekonstruktion dreidimensionaler Modelle aus Stereobildern. Doctoral Dissertation, Faculty of Science, Mannheim University.
Nomura, Y., Zhang, D., Sakaida, Y., Fujii, S., 1996. 3-d object pose estimation based on iterative image matching: shading and edge data fusion. Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, pp. 866–871.
Stößel, D., 2007. Automated Visual Inspection of Assemblies from Monocular Images. Doctoral Dissertation, Technical Faculty, Bielefeld University, Germany.
von Bank, C., Gavrila, D. M., Wöhler, C., 2003. A visual quality inspection system based on a hierarchical 3D pose estimation algorithm. In: Michaelis, B., Krell, G. (eds.), Pattern Recognition, Proc. 25th DAGM Symposium, Magdeburg, Germany. Lecture Notes in Computer Science 2781, pp. 179–186, Springer, Berlin.
Westling, M., Davis, L., 1996. Object recognition by fast hypothesis generation and reasoning about object interactions. Proc. Int. Conf. on Pattern Recognition, IV, pp. 148–153.
Wöhler, C., d’Angelo, P., 2009. Stereo image analysis of non-Lambertian surfaces. Int. J. Comput. Vis. 81(2), pp. 172–190.
Wöhler, C., Hafezi, K., 2005. A general framework for three-dimensional surface reconstruction by self-consistent fusion of shading and shadow features. Pattern Recognit. 38(7), pp. 965–983.
Yoon, Y., DeSouza, G. N., Kak, A. C., 2003. Real-time tracking and pose estimation for industrial objects using geometric features. Proc. Int. Conf. on Robotics and Automation, pp. 3473–3478.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Wöhler, C. (2013). Applications to Industrial Quality Inspection. In: 3D Computer Vision. X.media.publishing. Springer, London. https://doi.org/10.1007/978-1-4471-4150-1_6
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4150-1_6
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4149-5
Online ISBN: 978-1-4471-4150-1
eBook Packages: Computer ScienceComputer Science (R0)