Segmentation of Target Object using Block-based SSD Algorithm and Adaptive Tracking Window in Stereo Target Tracking System 


Vol. 27,  No. 11, pp. 1055-1064, Nov.  2002


PDF
  Abstract

In this paper, a new stereo object extraction algorithm using a block-based SSD(sum of squard difference) algorithm and the configuration parameters of a stereo camera is proposed. That is, by applying the SSD algorithm between the initial reference image and the next stereo inpu image, location coordinates of a target object in the right and left images are acquired and then with these values, the pan/tilt system is controlled. And using the moving angle of this pan/tilt system and the configulation parameters of the stereo camera system, the mask windows size of a target object is adaptively determined. The newly segmented target image is used as a reference image in the next stage and it is automatically updated in the course of target tracking basing on the same procedure. Meanwhile, a target object is under tracking through continuously controlling the convergence and FOV by using the sequentiall extracted location coordinates of a moving target.
From some experimental results using 30 frames of the sequential stereo input images, it is analyzed that the disparity between the segmented object images in the right and left images is kept to be very low to 1.3 pixels and 0.3 pixels on average in the horizontal and vertical directions, respectively. These good experiments finally suggest a possibility of implementation of a new practical stereo object tracking systetem by using the proposed algorithm.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Ko, c. Park, E. Kim, "Segmentation of Target Object using Block-based SSD Algorithm and Adaptive Tracking Window in Stereo Target Tracking System," The Journal of Korean Institute of Communications and Information Sciences, vol. 27, no. 11, pp. 1055-1064, 2002. DOI: .

[ACM Style]

Jung-Hwan Ko, chang-Ju Park, and Eun-Soo Kim. 2002. Segmentation of Target Object using Block-based SSD Algorithm and Adaptive Tracking Window in Stereo Target Tracking System. The Journal of Korean Institute of Communications and Information Sciences, 27, 11, (2002), 1055-1064. DOI: .

[KICS Style]

Jung-Hwan Ko, chang-Ju Park, Eun-Soo Kim, "Segmentation of Target Object using Block-based SSD Algorithm and Adaptive Tracking Window in Stereo Target Tracking System," The Journal of Korean Institute of Communications and Information Sciences, vol. 27, no. 11, pp. 1055-1064, 11. 2002.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880