Robust corner detection using altitude to chord ratio accumulation
- 109 Downloads
As one of the most significant image local features, corner is widely utilized in many computer vision applications. A number of contour-based corner detection algorithms have been proposed over the last decades, among which the chord-to-point distance accumulation (CPDA) corner detector is reported to produce robust performance in corner detection, especially compared with curvature scale-space (CSS) based corner detectors, which are sensitive to local variation and noise on the contour. In this paper, we investigate the CPDA algorithm in terms of its limitations, and then propose the altitude-to-chord ratio accumulation (ACRA) corner detector based on CPDA approach. Altitude-to-chord ratio is insensitive to the selection of chord length compared with chord-to-point distance, which allows us utilize a single chord instead of the three chords used in CPDA algorithm. Besides, we replace the maximum normalization used in CPDA algorithm with the linear normalization to avoid the uneven data projection. Numerical experiments demonstrate that the proposed ACRA corner detection algorithm outperforms the CPDA approach and other seven state-of-the-art methods in terms of the repeatability and localization error evaluation metrics.
KeywordsAltitude-to-chord ratio accumulation Contour-based corner detection Low-level feature detection
This work was supported in part by the National Natural Science Foundation of China under Grant 61602091 and Grant 61571102, in part by the Fundamental Research Funds for the Central Universities under Grant ZYGX2016J199 and Grant ZYGX2014Z003.
- 2.Awrangjeb M, Lu G (2013) A performance review of recent corner detectors. In: International Conference on Digital Image Computing: Techniques and Applications. Hobart, AustraliaGoogle Scholar
- 3.Awrangjeb M, Lu G J, Murshed M (2007) An affine resilient curvature scale-space corner detector. In: IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, HI, AmericaGoogle Scholar
- 4.Awrangjeb M, Lu G J, Fraser C S, Ravanbakhsh M (2009) A fast corner detector based on the chord-to-point distance accumulation technique. In: International Conference on Digital Image Computing: Techniques and Applications, Melbourne, AustraliaGoogle Scholar
- 5.Awrangjeb M, Lu G, Fraser C S (2010) A comparative study on contour-based corner detectors. In: International Conference on Digital Image Computing: Techniques and Applications, Sydney, AustraliaGoogle Scholar
- 8.Harris C, Stephens M (1988) A combined corner and edge detector. In: Alvey Vision Conference, Manchester, BritainGoogle Scholar
- 12.Lin X, Zhu C, Zhang Q, Huang X, Liu Y (2017) Efficient and robust corner detectors based on second order difference of contour. IEEE Signal Process Lett PP(99):1–1Google Scholar
- 14.Mokhtarian F, Mohanna F (2001) Enhancing the curvature scale space corner detector. In: Proceedings of the Scandinavian Conference on Image Analysis, Bergen, NorwayGoogle Scholar
- 16.Moravec HP (1980) Obstacle avoidance and navigation in the real world by a seeing robot rover. PhD thesis, Stanford, p aAI8024717Google Scholar
- 20.Rosten E, Drummond T (2005) Fusing points and lines for high performance tracking. In: IEEE International Conference on Computer Vision, Beijing, ChinaGoogle Scholar
- 21.Shi J, Tomasi C (1994) Good features to track. In: IEEE International Conference on Computer Vision and Pattern Recognition, Seattle, WAGoogle Scholar
- 25.Topal C, Özkan K, Benligiray B, Akinlar C (2013) A robust css corner detector based on the turning angle curvature of image gradients. In: IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, CanadaGoogle Scholar