Visual detection and tracking of moving objects

Ergezer H., Leblebicioglu K.

IEEE 15th Signal Processing and Communications Applications Conference, Eskişehir, Turkey, 11 - 13 June 2007, pp.632-633 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2007.4298624
  • City: Eskişehir
  • Country: Turkey
  • Page Numbers: pp.632-633
  • Middle East Technical University Affiliated: Yes


In this paper, primary steps of a visual surveillance system are presented: moving object detection and tracking of these moving objects. Running average method has been used to detect the moving objects in the video, which is taken from a static camera. Tracking of foreground objects has been realized by using a Kalman filter. After background subtraction, morphological operators are used to remove noises detected as foreground. Active contour models (snakes) are the segmentation tools for the extracted foregrounds. Snakes have been also used as an extra tool for object tracking.