Machine Learning for High-Speed Corner Detection
Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate.
Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations . Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.
Unable to display preview. Download preview PDF.
- 2.Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: 10th IEEE International Conference on Computer Vision, Beijing, China, vol. 2, pp. 1508–1515. Springer, Heidelberg (2005)Google Scholar
- 3.Rosten, E., Reitmayr, G., Drummond, T.: Real-time video annotations for augmented reality. In: International Symposium on Visual Computing (2005)Google Scholar
- 4.Moravec, H.: Obstacle avoidance and navigation in the real world by a seeing robot rover. In: Tech. report CMU-RI-TR-80-03, Robotics Institute, Carnegie Mellon University & doctoral dissertation, Stanford University. Carnegie Mellon University (1980); available as Stanford AIM-340, CS-80-813 and republished as a Carnegie Mellon University Robotics Institue Technical Report to increase availabilityGoogle Scholar
- 5.Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
- 7.Shi, J., Tomasi, C.: Good features to track. In: 9th IEEE Conference on Computer Vision and Pattern Recognition, Springer, Heidelberg (1994)Google Scholar
- 8.Noble, A.: Descriptions of image surfaces. PhD thesis, Department of Engineering Science, University of Oxford (1989)Google Scholar
- 10.Zuliani, M., Kenney, C., Manjunath, B.: A mathematical comparison of point detectors. In: Second IEEE Image and Video Registration Workshop (IVR), Washington DC, USA (2004)Google Scholar
- 13.James, L., Crowley, O.R.: Fast computation of characteristic scale using a half octave pyramid. In: Scale Space 2003: 4th International Conference on Scale-Space theories in Computer Vision, Isle of Skye, Scotland (2003)Google Scholar
- 15.Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: 8th IEEE International Conference on Computer Vision, Vancouver, Canada, Springer, pp. 525–531 (2001)Google Scholar
- 16.Brown, M., Lowe, D.G.: Invariant features from interest point groups. In: 13th British Machine Vision Conference, Cardiff, British Machine Vision Assosciation, pp. 656–665 (2002)Google Scholar
- 18.Rutkowski, W.S., Rosenfeld, A.: A comparison of corner detection techniques for chain coded curves. Technical Report 623, Maryland University (1978)Google Scholar
- 22.Haralick, R.M., Shapiro, L.G.: Computer and robot vision, vol. 1. Addison-Wesley, Reading (1993)Google Scholar
- 30.Dias, P., Kassim, A., Srinivasan, V.: A neural network based corner detection method. In: IEEE International Conference on Neural Networks, Perth, WA, Australia, vol. 4, pp. 2116–2120 (1995)Google Scholar
- 31.Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
- 32.Smith, S.M.: http://www.fmrib.ox.ac.uk/~steve/susan/susan2l.c (accessed 2005)
- 33.Performenace Evaluation of Corner Detection Algorithms under Affine and Similarity Transforms. In: Cootes, T.F., Taylor, C. (eds.) 12th British Machine Vision Conference, Manchester, British Machine Vision Assosciation (2001)Google Scholar
- 34.Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: 6th IEEE International Conference on Computer Vision, Bombay, India, pp. 230–235. Springer, Heidelberg (1998)Google Scholar
- 35.Lowe, D.G.: Demo software: Sift keypoint detector (accessed 2005), http://www.cs.ubc.ca/~lowe/keypoints/