ABSTRACT
The detection, extraction, and matching of image features is a popular method for generating point-to-point correspondences for the estimation of scene and camera geometries. In this work we evaluate the performance of a variety of feature detection algorithms over two reference data sets and a set of aerial images which includes large changes in scene illumination. The evaluated detectors showed expected performance against the reference data sets, and aerial images with constant lighting conditions, but were unsuccessful in aligning image pairs showing strong changes in image exposure and illumination.
- M. Agrawal, K. Konolige, and M. R. Blas. CenSurE: center surround extremas for realtime feature detection and matching. In D. Forsyth, P. Torr, and A. Zisserman, editors, Computer Vision -- ECCV 2008, volume 5305, pages 102--115. Springer Berlin Heidelberg, Berlin, Heidelberg, 2008.Google Scholar
- H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool. Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110(3): 346--359, 2008. Google ScholarDigital Library
- T. Botterill. Visual Navigation for Mobile Robots using the Bag-of-Words Algorithm. PhD thesis, University of Canterbury, Christchurch, New Zealand, 2010.Google Scholar
- T. Botterill, S. Mills, and R. Green. New conditional sampling strategies for speeded-up RANSAC. In Proceedings of the British Machine Vision Conference, 2009.Google ScholarCross Ref
- O. Chum and J. Matas. Matching with PROSAC -- progressive sample consensus. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 220--226, San Diego, CA, USA. Google ScholarDigital Library
- K. Cordes, B. Rosenhahn, and J. Ostermann. Increasing the accuracy of feature evaluation benchmarks using differential evolution. In Differential Evolution (SDE), 2011 IEEE Symposium on, pages 1--8. IEEE, Apr. 2011.Google ScholarCross Ref
- C. Engels, H. Stewénius, and D. Nistér. Bundle adjustment rules. Photogrammetric Computer Vision, 2, 2006.Google Scholar
- C. Evans. Notes on the OpenSURF library. Technical Report CSTR-09-001, University of Bristol, Jan. 2009.Google Scholar
- S. Gauglitz, T. Höllerer, and M. Turk. Evaluation of interest point detectors and feature descriptors for visual tracking. International Journal of Computer Vision, 94(3): 335--360, Mar. 2011. Google ScholarDigital Library
- J. Geusebroek, R. van den Boomgaard, A. Smeulders, and H. Geerts. Color invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(12): 1338--1350, Dec. 2001. Google ScholarDigital Library
- C. Harris and M. Stephens. A combined corner and edge detector. In Alvey vision conference, volume 15, page 50, 1988.Google Scholar
- R. I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521540518, second edition, 2004. Google ScholarDigital Library
- R. Hess. An open-source SIFT Library. In Proceedings of the international conference on Multimedia, pages 1493--1496, 2010. Google ScholarDigital Library
- D. G. Lowe. Distinctive image features from Scale-Invariant keypoints. International Journal of Computer Vision, 60(2): 91--110, Nov. 2004. Google ScholarDigital Library
- K. Mikolajczyk and C. Schmid. An affine invariant interest point detector. In A. Heyden, G. Sparr, M. Nielsen, and P. Johansen, editors, Computer Vision -- ECCV 2002, volume 2350, pages 128--142. Springer Berlin Heidelberg, Berlin, Heidelberg. Google ScholarDigital Library
- K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. V. Gool. A comparison of affine region detectors. International Journal of Computer Vision, 65(--2): 43--72, Oct. 2005. Google ScholarDigital Library
- OpenCV development team. OpenCV v2.3 documentation. Technical report, Aug. 2011.Google Scholar
- E. Rosten and T. Drummond. Machine learning for High-Speed corner detection. In A. Leonardis, H. Bischof, and A. Pinz, editors, Computer Vision -- ECCV 2006, volume 3951, pages 430--443. Springer Berlin Heidelberg, Berlin, Heidelberg, 2006. Google ScholarDigital Library
- E. Rosten, R. Porter, and T. Drummond. Faster and better: A machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(1): 105--119, Jan. 2010. Google ScholarDigital Library
- A. Schmidt, M. Kraft, and A. Kasiński. An evaluation of image feature detectors and descriptors for robot navigation. In L. Bolc, R. Tadeusiewicz, L. J. Chmielewski, and K. Wojciechowski, editors, Computer Vision and Graphics, volume 6375, pages 251--259. Springer Berlin Heidelberg, Berlin, Heidelberg, 2010. Google ScholarDigital Library
- J. Shi and C. Tomasi. Good features to track. In Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1994, pages 593--600. IEEE Comput. Soc. Press, 1994.Google Scholar
- C. Tomasi and T. Kanade. Detection and tracking of point features, 1991.Google Scholar
- P. Torr. MLESAC: a new robust estimator with application to estimating image geometry. Computer Vision and Image Understanding, 78(1): 138--156, Apr. 2000. Google ScholarDigital Library
- T. Tuytelaars and K. Mikolajczyk. Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision, 3(3): 177--280, 2007. Google ScholarDigital Library
Index Terms
- Evaluation of feature detectors for registering aerial images
Recommendations
Pose Guided Matching for Aerial Images
IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New ZealandThe estimation of the geometric relationship between pairs of images is a core task for many computer vision applications. Frequently, prior information on the inter-image or inter-camera geometry is available from e.g., a motion model or external ...
Feature Detection and Description in Remote Sensing Images using a Hybrid Feature Detector
AbstractFeature detection plays a crucial role in image registration. There exists quite a few feature detection algorithms in literature like BRISK, FAST, SURF etc [14]. Each of these algorithms has its own advantages and disadvantages. BRISK is rotation ...
Comments