Object Tracking and Elimination Using Level-of-Detail Canny Edge Maps

  • Jihun Park
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4069)


We propose a method for tracking a nonparameterized subject contour in a single video stream with a moving camera. Then we eliminate the tracked contour object by replacing the background scene we get from other frame that is not occluded by the tracked object. Our method consists of two parts: first we track the object using LOD (Level-of-Detail) canny edge maps, then we generate background of each image frame and replace the tracked object in a scene by a background image from other frame. In order to track a contour object, LOD Canny edge maps are generated by changing scale parameters for a given image. A simple (strong) Canny edge map has the smallest number of edge pixels while the most detailed Canny edge map, WcannyN, has the largest number of edge pixels. To reduce side-effects because of irrelevant edges, we start our basic tracking by using simple (strong) Canny edges generated from large image intensity gradients of an input image, called Scanny edges. Starting from Scanny edges, we get more edge pixels ranging from simple Canny edge maps until the most detailed (weaker) Canny edge maps, called Wcanny maps along LOD hierarchy. LOD Canny edge pixels become nodes in routing, and LOD values of adjacent edge pixels determine routing costs between the nodes. We find the best route to follow Canny edge pixels favoring stronger Canny edge pixels. In order to remove the tracked object, we generate approximated background for the first frame. Background images for subsequent frames are based on the first frame background or previous frame images. This approach is based on computing camera motion, camera movement between two image frames. Our method works nice for moderate camera movement with small object shape changes.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Park, J.: Contour tracking using modified canny edge maps with level-of-detail. In: Gagalowicz, A., Philips, W. (eds.) CAIP 2005. LNCS, vol. 3691, pp. 1–8. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  2. 2.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 1, 321–331 (1987)CrossRefGoogle Scholar
  3. 3.
    Peterfreund, N.: Robust tracking of position and velocity with kalman snakes. IEEE Trans. on Pattern Analysis and Machine Intelligence 21, 564–569 (1999)CrossRefGoogle Scholar
  4. 4.
    Fu, Y., Erdem, A.T., Tekalp, A.M.: Tracking visible boundary of objects using occlusion adaptive motion snake. IEEE Trans. on Image Processing 9, 2051–2060 (2000)CrossRefGoogle Scholar
  5. 5.
    Paragios, N., Deriche, R.: Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans. on Pattern Analysis and Machine Intelligence 22, 266–280 (2000)CrossRefGoogle Scholar
  6. 6.
    Nguyen, H.T., Worring, M., van den Boomgaard, R., Smeulders, A.W.M.: Tracking nonparameterized object contours in video. IEEE Trans. on Image Processing 11, 1081–1091 (2002)CrossRefGoogle Scholar
  7. 7.
    Roerdink, J.B.T.M., Meijster, A.: The watershed transform: Definition, algorithms and parallelization strategies. Fundamenta Informaticae 41, 187–228 (2000)zbMATHMathSciNetGoogle Scholar
  8. 8.
    Nguyen, H.T., Worring, M., van den Boomgaard, R.: Watersnakes: energy-driven watershed segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 25, 330–342 (2003)CrossRefGoogle Scholar
  9. 9.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603–619 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jihun Park
    • 1
  1. 1.Department of Computer EngineeringHongik UniversitySeoulKorea

Personalised recommendations