Extended Design Science Research Methodology For Parallel Vision System

  • Authors

    • Deshinta Arrova Dewi
    • Elankovan Sundararajan
    2018-11-26
    https://doi.org/10.14419/ijet.v7i4.29.21962
  • Design science research, image processing, research methodology, the parallel vision system
  • Vision system implements image processing in its design and development. The process involves a series of static and dynamic images that are received from a real-time environment. The vision system produces an important outcome in term of object features that are meant for observation, for example, object location, identity, orientation, and others. The previous research in image processing has incorporated a test-driven agile simulation as a research methodology. However, the research methodology for the vision system remains lack of attention. This paper investigates the possibility of the Design Science Research Methodology (DSRM) for vision system application. First, the vision system framework that involves image processing is presented. Second, qualitative content analysis to find a match between vision and DSRM components is demonstrated. Third, investigation on the parallelization of the vision system is reviewed and finally, the extension of DRSM to accommodate parallelization is exposed.  The selected case study in this paper involves a vision system for an autonomous robot whereby a parallelization is employed to accelerate computation. The analysis shows that the customized DSRM match with the parallel vision system development stages. The customized DRSM will assist the vision engineers to design the vision system efficiently.

  • References

    1. [1] E. N. Malamas, E. G. M. Petrakis, M. Zervakis, L. Petit, and J. D. Legat, (2003), A survey on industrial vision systems, applications and tools, Image Vis. Comput., vol. 21, no. 2, pp. 171–188.

      [2] S. Hosseinpour, S. Rafiee, S. S. Mohtasebi, and M. Aghbashlo, (2013), Application of computer vision technique for on-line monitoring of shrimp color changes during drying, J. Food Eng., vol. 115, no. 1, pp. 99–114.

      [3] H. Zhang and D. Li, (2014), Applications of computer vision techniques to cotton foreign matter inspection: A review, Comput. Electron. Agric., vol. 109, pp. 59–70.

      [4] T. Mörwald, J. Prankl, M. Zillich, and M. Vincze, (2013), “Advances in real-time object tracking,†J. Real-Time Image Process., vol. 10, no. 4, pp. 683–697.

      [5] M. Danelljan, F. S. Khan, M. Felsberg, and J. Van De Weijer, (2014), Adaptive color attributes for real-time visual tracking, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 1090–1097.

      [6] V. P. Bhuvana, M. Schranz, C. S. Regazzoni, B. Rinner, A. M. Tonello, and M. Huemer, (2016), Multi-camera object tracking using surprisal observations in visual sensor networks,†EURASIP J. Adv. Signal Process., vol. 2016, no. 1, p. 50.

      [7] A. DAWADEE, J. CHAHL, D. NANDAGOPAL, and Z. NEDIC, (2013), Illumination, Scale and Rotation Invariant Algorithm for Vision-Based Uav Navigation, Int. J. Pattern Recognit. Artif. Intell., vol. 27, no. 5, p. 1359003.

      [8] Y. Zhao and H. Pei, (2012), An Improved Vision-based Algorithm for Unmanned Aerial Vehicles Autonomous Landing, Phys. Procedia, vol. 33, no. 2, pp. 935–941.

      [9] F. Beuth, A. Jamalian, and F. H. Hamker, (20140), How Visual Attention and Suppression Facilitate Object Recognition?, Icann2014, no. September, pp. 1–8.

      [10] A. Yupatova, V. Schneider, W. Dulz, and R. German, (2014), Test-Driven Agile Simulation for Design of Image Processing Systems, 16th Int. Conference Adv. Syst. Test. Valid. Lifecycle, no. c, pp. 7–8.

      [11] N. Akiya, Scott Bury, and J. M. Wassick, (2011), VERITAS - A VERSATILE MODELING ENVIRONMENT FOR TEST-DRIVEN AGILE SIMULATION, Proc. 2011 Winter Simul. Conf. 11-14 Dec, pp. 2194–2205.

      [12] R. Hevner, S. T. March, and J. Park, (2004), Design Science in Information Systems Research, MIS Q., vol. 28, no. 1, pp. 75–105,

      [13] M. P. Uysal, (2016), Towards a Software Engineering Research Framework : Extending Design Science Research, Int. Res. J. Eng. Technol., vol. 3, no. February, pp. 2–6.

      [14] M. Carcary, (2011), Design science research: The case of the IT capability maturity framework (IT CMF), Electron. J. Bus. Res. Methods, vol. 9, no. 2, pp. 109–118.

      [15] J. Venable, J. Pries-heje, and R. Baskerville, (2014), FEDS: a Framework for Evaluation in Design Science Research, Eur. J. Inf. Syst., vol. 25, no. October 2012, pp. 1–13.

      [16] M. E. Ragab and G. F. Elkabbany, (2014), A Parallel Implementation of Multiple Non-overlapping Cameras for Robot Pose Estimation, KSII Trans. INTERNET Inf. Syst., vol. 8, no. 11, pp. 3253–3256.

      [17] P. S. Pacheco, (2011), Introduction to Parallel Programming.

      [18] D. B. Kirk and W. W. Hwu, (2013), Programming Massively Parallel Processors. Elsevier Inc.

      [19] S. Wrede, C. Bauckhage, G. Sagerer, W. Ponweiser, and M. Vincze, (2004), Integration frameworks for large scale cognitive vision systems - An evaluative study, Proc. - Int. Conf. Pattern Recognit., vol. 1, no. C, pp. 761–764.

  • Downloads

  • How to Cite

    Dewi, D. A., & Sundararajan, E. (2018). Extended Design Science Research Methodology For Parallel Vision System. International Journal of Engineering & Technology, 7(4.29), 157-161. https://doi.org/10.14419/ijet.v7i4.29.21962