Browse > Article

Parallelizing Feature Point Extraction in the Multi-Core Environment for Reducing Panorama Image Generation Time  

Kim, Geon-Ho (삼성전자 소프트웨어연구소)
Choi, Tai-Ho (삼성전자 소프트웨어연구소)
Chung, Hee-Jin (삼성전자 소프트웨어연구소)
Kwon, Bom-Jun (삼성전자 소프트웨어연구소)
Abstract
In this paper, we parallelized a feature point extraction algorithm to reduce panorama image generation time in multi-core environment. While we compose a panorama image with several images, the step to extract feature points of each picture is needed to find overlapped region of pictures. To perform rapidly feature extraction stage which requires much calculation, we developed a parallel algorithm to extract feature points and examined the performance using CBE(Cell Broadband Engine) which is asymmetric multi-core architecture. As a result of the exam, the algorithm we proposed has a property of linear scalability-the performance is increased in proportion the number of processors utilized. In this paper, we will suggest how Image processing operation can make high performance result in multi-core environment.
Keywords
Multi-core; Feature extraction; Panorama Image;
Citations & Related Records
연도 인용수 순위
  • Reference
1 P. J. Burt and E.H. Adelson. A Multiresolution Spline with Application to Image Mosaics. ACM transactions on Graphics, 2(4), 217-236, 1983   DOI
2 D. G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, Volume 60, Number 2, pp. 91-110, Springer, 2004   DOI
3 S. Nowozin. autopano-sift: making panoramas fun. http://user.cs.tu-berlin.de/~nowozin/autopano-sift/
4 D. G. Lowe. Object Recognition from Local Scale- Invariant Features. In Seventh International Conference on Computer Vision, Greece, pp. 1150- 1157, 1999
5 S. Richard. Image Alignment and Stitching : A Tutorial, Microsoft Research, September 27, 2004
6 IBM. Cell Broadband Engine Programming Handbook, Version 1.0. April 19, 2006