Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지

Performance Analysis of Feature Detection Methods for Topology-Based Feature Description

토폴로지 기반 특징 기술을 위한 특징 검출 방법의 성능 분석

  • Received : 2015.03.31
  • Accepted : 2015.05.01
  • Published : 2015.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

When the scene has less texture or when camera pose largely changes, the existing texture-based feature tracking methods are not reliable. Topology-based feature description methods, which use the geometric relationship between features such as LLAH, is a good alternative. However, they require feature detection methods with high performance. As a basic study on developing an effective feature detection method for topology-based feature description, this paper aims at examining their applicability to topology-based feature description by analyzing the repeatability of several feature detection methods that are included in the OpenCV library. Experimental results show that FAST outperforms the others.

텍스처가 부족한 장면이나 카메라 포즈 변화가 클 경우, 기존의 텍스처 기반의 특징 추적 방법의 신뢰도는 크게 떨어진다. LLAH와 같은 특징 사이의 기하 정보를 활용하는 토폴로지 기반 특징 기술 방법이 좋은 대안이 될 수 있으나, 특징 검출방법의 성능에 크게 영향을 받는다. 본 논문에서는 토폴로지 기반 특징 기술을 위한 효과적인 특징 검출 방법을 마련하기 위한 기초 연구로, OpenCV 라이브러리에서 제공되는 특징 검출 방법들의 반복성(repeatability) 분석을 통해 토폴로지 기반 특징 기술에의 적용 가능성을 살펴본다. 실험을 통해, FAST의 성능이 가장 우수함을 확인하였다.

Keywords

References

  1. C. Harris and M. Stephens, "A combined corner and edge detector," Proc. of the 4th Alvey Vision Conf., pp. 147-151, 1988.
  2. E. Rosten and T. Drummond, "Fusing points and lines for high performance tracking," Proc. of ICCV, pp. 1508-1511, 2005.
  3. E. Rublee, V. Rabaud, K. Konolige, G. R. Bradski, "ORB: An efficient alternative to SIFT or SURF," Proc. of ICCV, pp. 2564-2571, 2011.
  4. S. Leutenegger, M. Chli, and R. Siegwart, "BRISK: Binary robust invariant scalable keypoints," Proc. of ICCV, pp. 2548-2555, 2011.
  5. D. G. Lowe, "Distinctive image features from scale-invariant keypoints", IJCV, vol. 60, no. 2, pp. 91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  6. H. Bay, T. Tuytelaars, L. V. Gool, "SURF: Speeded up robust features," Proc. of ECCV, pp. 404-417, 2006.
  7. OpenCV, http://opencv.org/
  8. H.-S. Ryu, H. Park, "A system for supporting paper-based augmented reality," MTAP, 2015. (online published)
  9. T. Nakai, K. Kise, and M. Iwamura, "Use of affine invariants in locally likely arrangement hashing for camera-based document image retrieval," Proc. DAS, pp. 541-552, 2006.
  10. H. Uchiyama and H. Saito, "Random dot markers," Proc. of VR, pp.35-38, 2011.
  11. B.-K. Seo, H. Uchiyama, and J.-I. Park, "stAR: Visualizing constellations with star retrieval," Proc. of SIGGRAPH ASIA, article no. 53, 2011.
  12. H. Uchiyama and E. Marchand, "Toward augmenting everything: Detecting and tracking geometrical features on planar objects," Proc. of ISMAR, pp. 17-25, 2011.
  13. M. Agrawal, K. Konolige, and M. R. Blas, "CenSurE: Center surround extremas for realtime feature detection and matching," Proc. of ECCV, pp. 102-115, 2008.
  14. Schmid, R. Mohr, and C. Bauckhage, "Evaluation of interest point detectors," IJCV, vol. 37, no. 2, pp. 151-172, 2000. https://doi.org/10.1023/A:1008199403446
  15. http://www.robots.ox.ac.uk/-vgg/research/affine/index.html