Panorama Image based on Combination of Feature Points 


Vol. 35,  No. 8, pp. 179-184, Aug.  2010


PDF
  Abstract

Creating a panorama image by combining two separate images which have partial common area has been widely utilized in many fields such as producing digital map, film, aerial image and satellite image. The core technology of creating panorama image is to combine two images from generating transformation matrix by extracting exact corresponding points. The common way is applying Ransac algorithm to generate transformation matrix and combine images from extracted corresponding points which are converged over definite probability. In this paper, we present TMC (Transformation Matrix by Combination) algorithm that can replace Ransac algorithm. The proposed method, TMC algorithm uses SIFT to extract feature points which have robust properties on scale, rotation and translation. Then it gets transformation matrix from combination of fixed number of corresponding points which are proved as the most similar ones. Compare to Rnasac, TMC produces transformation matrix more effectively by having faster processing time and constant operation, and it has similar accuracy at the same time.

  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]

S. Yang, H. Jeon, C. Hwang, "Panorama Image based on Combination of Feature Points," The Journal of Korean Institute of Communications and Information Sciences, vol. 35, no. 8, pp. 179-184, 2010. DOI: .

[ACM Style]

Seung-beom Yang, Huyk-jun Jeon, and Chi-jung Hwang. 2010. Panorama Image based on Combination of Feature Points. The Journal of Korean Institute of Communications and Information Sciences, 35, 8, (2010), 179-184. DOI: .

[KICS Style]

Seung-beom Yang, Huyk-jun Jeon, Chi-jung Hwang, "Panorama Image based on Combination of Feature Points," The Journal of Korean Institute of Communications and Information Sciences, vol. 35, no. 8, pp. 179-184, 8. 2010.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880