A Study on Motion Detection of Object Using Active Block Matching Algorithm 


Vol. 31,  No. 4, pp. 407-416, Apr.  2006


PDF
  Abstract

It is difficult for the movement detection of an object through a camera to detect exact movement because of unnecessary noises and changes of the light. It can be recognized as a background, when there is no movement after the inflow of an object. Therefore, It is necessary to fast search algorithm for tracking and extract of object that is realtime image.
In this thesis, we evaluate the difference of the input vision based on initial image and replace some pixels in process of time. When there is a big difference between background image and input image, we decide it is the point of the time of the object input and then extract boundary point of it.
The extracted boundary point detects precise movement of the object by creating minimum block of it and searching block that maintaining distance. The designed and embodied system shows more than 95% accuracy in the performance test.

  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]

C. Lee, M. Park, K. Lee, "A Study on Motion Detection of Object Using Active Block Matching Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 31, no. 4, pp. 407-416, 2006. DOI: .

[ACM Style]

Chang-soo Lee, Mi-og Park, and Kyung-seok Lee. 2006. A Study on Motion Detection of Object Using Active Block Matching Algorithm. The Journal of Korean Institute of Communications and Information Sciences, 31, 4, (2006), 407-416. DOI: .

[KICS Style]

Chang-soo Lee, Mi-og Park, Kyung-seok Lee, "A Study on Motion Detection of Object Using Active Block Matching Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 31, no. 4, pp. 407-416, 4. 2006.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880