Abstract
This work is dedicated to develop a safety measurement for human–machine cooperative system, in which the machine region and the human region cannot be separated due to the overlap and the movement both from human and from machines. Modern production processes become more and more flexible. Therefore, there is a need that devices used in workplace also support flexibility as much as possible. Such characteristics have vision-based protective devices. We present a neural system for the advanced recognition of danger situation for safety control. The sequence of the images from two cameras located above the robot is presented to the system of cellular neural networks (CNNs) realized in the PC computer. They detect a new object appearing in a safety field, define its position with respect to the robot arm and perform the feature extraction of its image. Experiments conducted using artificial images (virtual environment) and low-quality images (internet cameras) indicate that our system can work in a real time and detect successively dangerous situations. We have found that the CNN is unable to detect a new object properly in the presence of high level of noise as a result of percolation type phase transition. An example of possible application of the system is presented.
Similar content being viewed by others
References
Bomer, T.: Vision based protective devices (VBPD)—a vision becomes reality. In: 3rd International Conference. SIAS, Nancy, France, pp. 7–11 (2003)
Japanese Machinery Federation: In: Report of the Project “Development for the International Standards in the field of Safety of Machinery—a vision-based protective devices (VBPD)”. IEC 44/343/INF (2001–2010)
Kahlmann, T., Remondino F., Guillaume, S.: Range imaging technology: new developments and applications for people identification and tracking. In: Proceedings of SPIE 6491:64910C (2007)
Gardeux, F.: Detection of persons based on digital vision: advantages and limits, INRS, HST, ND, 2276-208-07 (2007)
Hamajima, K., Lu, J., Ishihara, K.: Object zone detection method with omni-directional vision sensors. In: Specific Research Reports of the National Institute of Industrial Safety, NIIS-SRR-NO.33 (2005)
Cervera, E., Garcia-Aracil, N., Martinez, E., Nomdedeu, L., Del Pobil, A.: Safety for a robot arm moving amidst humans by using panoramic vision. In: IEEE International Conference on Robotics and Automation, art. no. 4543530, pp. 2183–2188 (2008)
Lu J., Hamajima K., Jiang W.: Monitoring a wide manufacture field automatically by multiple sensors. Acta Autom. Sin. 32, 956–967 (2006)
Kruger, J., Nickolay, V., Schulz, O.: Image-based 3D-surveillance in man-robot cooperation. In: 2nd IEEE International Conference on Industrial Informatics, Berlin, pp. 411–420 (2004)
Hagele, M., Schaaf, W., Helms, E.: Robot assistants at manual workplaces: effective co-operation and safety aspects. In: Proceedings of the 33rd ISR (International Symposium on Robotics) (2002)
Costantini, G., Casali, D., Carota, M., Perfetti, R.: A CNN-based algorithm for moving object detection in stereovision applications. In: European Conference on Circuit Theory and Design ECCTD 2007, art. no. 4529642, pp. 500–503 (2007)
Bishop C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)
Morgan, G., Austin, J.: Safety critical neural network. In: Proceedings of the International Conference on Neural Network, Cambridge, pp. 212–218 (1995)
Gobron, S., Devillard, F., Heit, B.: Retina simulation using cellular automata and GPU programming. In: Machine Vision and Applications, vol. 18, pp. 331–342 (2007)
Chua L.O.: CNN—A Paradigm for Complexity. World Press, Singapore (1986)
Samson E., Laurendeau D., Parizeau M., Comtois S., Allan J., Gosselin C.: The agile stereo pair for active vision. Mach. Vis. Appl. 17, 32–50 (2006)
Nomura A., Ichikawa M., Miike H.: Reactiondiffusion algorithm for stereo disparity detection. Mach. Vis. Appl. 20, 175–187 (2009)
Yuan, D., Chung, R.: Correspondence-free stereo vision: extension from planar scene case to polyhedral scene case. Mach. Vis. Appl. (2008). doi:10.1007/s00138-008-0177-4
Sun, W., Spackman, S.: Multi-object segmentation by stereo mismatch. Mach. Vis. Appl. (2008). doi:10.1007/s00138-008-0127-1
Bradski, G., Kaehler, A.: Learning OpenCV: Computer Vision with the OpenCV Library. O’Reilly Media, Inc. (2008)
Kosinski R.A.: Intelligent neural system for safety control. WSEAS Trans. Syst. 2, 98–103 (2003)
Siemiatkowska B., Kosinski R.A.: Application of Neural Network for Safety Control. WSEAS Trans. Comput. 3, 575–580 (2004)
Gonzales R.C.: Digital image processing. Adison-Wesley, Reading (1992)
Sim, R., Dudek, G.: Mobile robot localization from learned landmark. In: IEEE Conference On Intelligent Robots and Systems, pp. 1060–1065 (1998)
Zetu D., Akgunduz A.: Tracking-based depth recovery for virtual reality applications. Mach. Vis. Appl. 16, 122–127 (2005)
Yamaguchi, T., Hashimoto, S.: Fast crack detection method for large-size concrete surface images using percolation-based image processing. Mach. Vis. Appl. (2009). doi:10.1007/s00138-009-0189-8
Stauffer D., Aharony A.: Introduction to percolation Theory, 2nd edn. Taylor and Francis, London (1994)
Feris, R., Raskar, R., Tan, L., Turk, M.: Discontinuity preserving stereo with small baseline multi-flash illumination. In: Tenth IEEE International Conference on Computer Vision, ICCV, pp. 412–419 (2005)
Hamajima K., Lu J., Ishihara K.: The basic analysis for object zone detection with volume intersection method using omni-directional vision sensors for man-machine co-existence systems. Trans. Jpn. Soc. Mech. Eng. Part C 74(2), 409–416 (2008)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Grabowski, A., Kosiński, R.A. & Dźwiarek, M. Vision safety system based on cellular neural networks. Machine Vision and Applications 22, 581–590 (2011). https://doi.org/10.1007/s00138-010-0269-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-010-0269-9