Abstract
This paper describes the setup and realization of a distributed camera system designed to survey a laboratory area where humans and mobile manipulator robots collaborate jointly. The system consists of 40 industrial grade cameras surveying a 10 m by 10 m area from a top-down perspective, connected via Gigabit Ethernet (GigE) to a cluster of 40 computers for distributed image processing. The cameras were fully calibrated, achieving an average reprojection error of 0.13 pixels for the complete system, which exceeds state-of-the art accuracy. Current long-term testing has the system running with at least 99.994% availability for up to two weeks. Successful application tests of the system were conducted, where it was used to track the movements of robots and humans across the surveyed area.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
E. Carey and V. Rowley, “GigE Vision: video streaming and device control over Ethernet standard,” Tech. Rep. (Automated Imaging Association (AIA), Ann Harbor, MI, 2011).
R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, 2nd ed. (Cambridge University Press, Cambridge, 2004). doi:10.1016/S0143-8166(01)00145-2
J. Heikkilach. Intellig. 22(10), 1066–1077 (2000). doi: 10.1109/34.879788.
G. Kurillo, Z. Li, and R. Bajcsy, “Framework for hierarchical calibration of multi-camera systems for teleimmersion,” in Proc. 2nd Int. Conf. on Immersive Telecommunications IMMERSCOM’09, Ed. by D. Mukherjee, A. Smolic, G. Alregib, and K. Nahrstedt (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (ICST), Berkeley, CA, 2009), pp. 1–6.
S. Lanser, C. Zierl, and R. Beutlhauser, “Multibildkalibrierung einer CCD-Kamera,” in Proc. 17th DAGM Symp. Verstehen akustischer und visueller Informationen. Bielefeld, Sept. 13–15, 1995, Ed. by G. Sagerer, S. Posch, and F. Kummert (Springer, Berlin, Heidelberg, 1995), pp. 481–491. doi: 10.1007/978-3-642-79980-8-57.
C. L. Ogden, C. D. Fryar, M. D. Carroll, and K. M. Flegal, “Mean body weight, height, and body mass index, United States 1960–2002,” Adv. Data 347, 1–17 (2004).
M. Pollefeys, S. N. Sinha, L. Guan, and J.-S. Franco, “Multi-view calibration, synchronization, and dynamic scene reconstruction,” in Multi-Camera Networks: Principles and Applications, Ed. by H. Aghajan and A. Cavallaro (Elsevier, 2008), Chapter 2, pp. 29–75. doi: 10.1016/B978-0-12-374633-7.00004-5.
C. Steger, M. Ulrich, and C. Wiedemann, Machine Vision Algorithms and Applications, 1st ed. (Wiley-VCH, Weinheim, 2008).
T. Svoboda, D. Martinec, and T. Pajdla, “A convenient multicamera self-calibration for virtual environments,” Presence Teleoperators Virtual Environ. 14(4) 407–422 (2005). doi: 10.1162/105474605774785325.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Martin Eggers received a diploma (Dipl.-Inf Univ.) in computer science from Technische Universität München (TUM) in 2009. He is currently working as a doctoral candidate in the German Cluster of Excellence for Cognition in Technical Systems (CoTeSys) at TUM, where his research interests are tracking and surveillance architectures and applications of large scale multi-camera systems. In 2009, he received a best paper award for the paper “Facial Expression Recognition with 3D Deformable Models” at the conference for Advances in Computer-Human Interaction.
Veselin Dikov is a Software Engineer at MVTec Software GmbH, where his expertise is focused on single and multi-camera calibration, 3D computer vision, image-based bar code identification, and object recognition. In 2006, he received his M.Sc. with Honors from Technische Universität München (TUM) in Computational Science and Engineering and he graduated from the Bavarian Graduate School of Computational Science and Engineering (BGCE), part of the Elitenetzwerk Bayern.
Christoph Mayer studied Computer Science at the Technische Universität München from 2000 to 2007. He started to work on his PhD in 2008 at the Chair for Image Understanding and Knowledge-based Systems at the Technische Universität München. Currently, he is working in the German Cluster of Excellence “Cognition for Technical Systems” in the Intelligent Autonomous Systems Group. His research interests are in the field of face model fitting, facial expression recognition and emotion recognition. He has been first author of the paper “Adjusted Pixel Features for Facial Component Classification” that appeared in the Vision and Image Computing Journal in 2009 and has been awarded with the best paper award in 2009 for the paper “Facial Expression Recognition with 3D Deformable Models” that has been presented at the conference “Advances in Computer-Human Interaction”. He received his doctoral degree in Computer Science in 2012.
Carsten Steger studied computer science at the Technische Universität München (TUM) and received his PhD from TUM in 1998. In 1996, he co-founded the company MVTec Software GmbH, where he heads the Research and Development department. He has authored and coauthored more than 70 scientific publications in the fields of computer and machine vision, including several textbooks on machine vision. In 2011, Carsten Steger was appointed TUM Adjunct Professor for the field of computer vision.
Bernd Radig received a degree in Physics from the University of Bonn in 1973 and a doctoral degree in Computer Science from the University of Hamburg in 1978. He continued his scientific work in Hamburg and received his habilitation in 1982. Until 1986 he was an Associate Professor at the Department of Computer Science at the University of Hamburg, leading the Research Group Cognitive Systems. Since 1986 he is a full professor at the Department of Computer Science of the Technische Universität München. He has been founding member and chairman of the Bavarian research association for Knowledge Based Systems (since 1988) and the initiator and chairman of the Association of Bavarian Research Co-operarions (1993–2006). He is an editor of the journal “International Journal on Pattern Recognition and Image Analysis”. He was a board member of the German Excellence Cluster “Cognition for Technical Systems” (2008–2012). His main research interests are in Computer Vision, with a focus on human computer interaction, multi-camera systems and object and person tracking. He has been author of the paper “Adjusted Pixel Features for Facial Component Classification” that appeared in the Vision and Image Computing Journal in 2009 and of the paper “Learning Local Objective Functions for Robust Face Model Fitting” that appeared in the Pattern Analysis and Machine Intelligent Journal in 2008. Furthermore, he has been awarded with the best paper award in 2009 for the paper “Facial Expression Recognition with 3D Deformable Models” that has been presented at the conference “Advances in Computer-Human Interaction”.
Rights and permissions
About this article
Cite this article
Eggers, M., Dikov, V., Mayer, C. et al. Setup and calibration of a distributed camera system for surveillance of laboratory space. Pattern Recognit. Image Anal. 23, 481–487 (2013). https://doi.org/10.1134/S1054661813040032
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661813040032