Movement Detection Using LabVIEW by Analysis of Real-Time Video

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 379)

Abstract

Movement detection is the key to solving many simple and complex problems in the real world. In its simplistic form, movement detection involves capturing the subject in question and comparing it with previous knowledge of shape, size, and displacement of subject from the captured snapshot/reference. This paper explores different noise filtering techniques Averaging/Mean filter, Median filter, Gaussian smoothing and object detection methods such as Background subtraction, Optical flow method, Temporal differencing, Sum of Absolute difference along with its advantages and disadvantages. The paper describes the Gaussian smoothing and absolute difference method that was used to detect movement in real-time video using LabVIEW. The approach involved processing set of consecutive video frames, extracting absolute difference of each other to detect foreground and background objects and its relative displacement from previous position. Subsequent to movement detection, the method also aims to highlight the region of object movement along with a Boolean indicator to visually inform the end user about movement detection.

Keywords

LabVIEW Absolute difference Object movement detect 

References

  1. 1.
    National Instruments Corporation.: IMAQ vision for LabVIEW user manual. Part Number 322917B-01, June 2003Google Scholar
  2. 2.
    Qidwai, U., Chen, C.J.: Digital Image Processing: An Algorithmic Approach with MATLAB®, pp. 104–109. Chapman and Hall/CRC, Boca Raton (2009)Google Scholar
  3. 3.
    Wikipedia® Outline of object recognition. [Online] (2015) Google Scholar
  4. 4.
    Liua, C., Yuena, P.C., Qiua, G.: Object Motion Detection Using Information Theoretic Spatio-Temporal Saliency. Elsevier Ltd., New York (2009)Google Scholar
  5. 5.
    Swati, C., Vishal, J.: Human activity tracking and analysis for surveillance. Int. J. Comput. Sci. Inf. Technol 5(5) 6707–6711 (2014)Google Scholar
  6. 6.
    Moore, D.: A Real-World System for Human Motion Detection and Tracking. California Institute of Technology, California (2003)Google Scholar
  7. 7.
    Lu, N., Wang, J., Wu, Q.H., Yang, L.: An improved motion detection method for real-time surveillance. IAENG Int. J. Comput. Sci. 35, 119 (2008)Google Scholar
  8. 8.
    Sreedevi, M., Yaswanth Kumar, A., Anjan Babu, G., Sendhil Kumar, R.: Real time movement detection for human recognition. In: Proceedings of the World Congress on Engineering and Computer Science vol. I (2012)Google Scholar
  9. 9.
    Wikipedia® Sum of absolute differences. [Online] (2015)Google Scholar
  10. 10.
    Bhat, M., Kapoor, P., Raina, B.L.: Application of SAD algorithm in image processing for motion detection and Simulink block sets for object tracking. Int. J. Eng. Sci. Adv. Technol. 2(3), 731–736 (2012)Google Scholar
  11. 11.
    Bradley, D., Roth, G.: Adaptive thresholding using integral image. J. Graph. Tools 12(2), 13–21 (2007)CrossRefGoogle Scholar
  12. 12.
    Tripty, S., Sanju, S., Bichu, V.: A new algorithm designing for detection of moving objects in video. Int. J. Comput. Appl. 96(2), 4–11 (2014)Google Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  1. 1.Electronics Communication Engineering DepartmentV.T.U, Sri Jagadguru Balagangadharanatha Swamiji Institute of TechnologyBangaloreIndia

Personalised recommendations