An Edge-Based Approach to Motion Detection

  • Angel D. Sappa
  • Fadi Dornaika
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3991)


This paper presents a simple technique for motion detection in steady-camera video sequences. It consists of three stages. Firstly, a coarse moving edge representation is computed by a set of arithmetic operations between a given frame and two equidistant ones (initially the nearest ones). Secondly, non-desired edges are removed by means of a filtering technique. The previous two stages are enough for detecting edges corresponding to objects moving in the image plane with a dynamics higher than the camera’s capture rate. However, in order to extract moving edges with a lower dynamics, a scheme that repeats the previous two stages at different time scales is performed. This temporal scheme is applied over couples of equidistant frames and stops when no new information about moving edges is obtained or a maximum number of iterations is reached. Although the proposed approach has been tested on human body motion detection it can be used for detecting moving objects in general. Experimental results with scenes containing movements at different speeds are presented.


Motion Detection Current Frame Original Frame Canny Edge Detector Edge Removal 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Kim, J., Kim, H.: Efficient Region-Based Motion Segmentation for a Video Monitoring System. Pattern Recognition Letters 24, 113–128 (2003)CrossRefGoogle Scholar
  2. Sheikh, Y., Shah, M.: Bayesian Object Detection in Dynamic Scenes. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition, San Diego, CA, USA (June 2005)Google Scholar
  3. Kellner, M., Hanning, T.: Motion Detection Based on Contour Strings. In: IEEE Int. Conf. on Image Processing, Singapore (October 2004)Google Scholar
  4. Radke, R., Andra, S., Al-Kofahi, O., Roysam, B.: Image Change Detection Algorithms: A Systematic Survey. IEEE Trans. On Image Processing 14, 294–307 (2005)CrossRefMathSciNetGoogle Scholar
  5. Bichsel, M.: Segmenting Simply Connected Moving Objects in a Static Scene. IEEE Trans. on Pattern Analysis and Machine Intelligence 16, 1138–1142 (1994)CrossRefGoogle Scholar
  6. Francois, A., Medioni, G.: Adaptive Color Background Modeling for Real-Time Segmen-tation of Video Streams. In: Int. Conf. on Imaging Science, Systems and Technology, Las Vegas, NA (June 1999)Google Scholar
  7. Jabri, S., Duric, Z., Wechsler, H., Rosenfeld, A.: Detection and Location of People in Video Images Using Adaptive Fusion of Color and Edge Information. In: 15th. Int. Conf. on Pattern Recognition, Barcelona, Spain (September 2000)Google Scholar
  8. Lee, D.: Effective Gaussian mixture learning for video background subtraction. IEEE Trans. on Pattern Analysis and Machine Intelligence 27, 827–832 (2005)CrossRefGoogle Scholar
  9. Farin, D., de With, P., Effelsberg, W.: Robust Background Estimation for Complex Video Sequences. In: IEEE Int. Conf. on Image Processing, Barcelona, Spain (September 2003)Google Scholar
  10. Kim, C., Hwang, J.: Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications. IEEE Trans. on Circuits and Systems for Video Technology 12, 122–129 (2002)CrossRefGoogle Scholar
  11. Marqués, F., Molina, C.: Object Tracking for Content-Based Functionalities. In: SPIE Vis. Commun. Image Processing, San Jose, CA, February 1997, vol. 3024 (1997)Google Scholar
  12. Canny, J.F.: A Computational Approach to Edge Detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 6, 679–698 (1986)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Angel D. Sappa
    • 1
  • Fadi Dornaika
    • 1
  1. 1.Computer Vison CenterEdifici O Campus UABBarcelonaSpain

Personalised recommendations