AnySURF: Flexible Local Features Computation
Many vision-based tasks for autonomous robotics are based on feature matching algorithms, finding point correspondences between two images. Unfortunately, existing algorithms for such tasks require significant computational resources and are designed under the assumption that they will run to completion and only then return a complete result.
Since partial results—a subset of all features in the image—are often sufficient, we propose in this paper a computationally-flexible algorithm, where results monotonically increase in quality, given additional computation time. The proposed algorithm, coined AnySURF (Anytime SURF), is based on the SURF scale- and rotation-invariant interest point detector and descriptor. We achieve flexibility by re-designing several major steps, mainly the feature search process, allowing results with increasing quality to be accumulated.
We contrast different design choices for AnySURF and evaluate the use of AnySURF in a series of experiments. Results are promising, and show the potential for dynamic anytime performance, robust to the available computation time.
KeywordsInterest Point Humanoid Robot Design Choice Scale Invariant Feature Transform Integral Image
- 1.DARPA grand challenge (2007), http://www.darpa.mil/grandchallenge/index.asp
- 3.Chekhlov, D., Pupilli, M., Mayol-Cuevas, W., Calway, A.: Real-Time and Robust Monocular SLAM Using Predictive Multi-resolution Descriptors. In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Remagnino, P., Nefian, A., Meenakshisundaram, G., Pascucci, V., Zara, J., Molineros, J., Theisel, H., Malzbender, T. (eds.) ISVC 2006. LNCS, vol. 4292, pp. 276–285. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 5.Evans, C.: Notes on the OpenSURF library. Tech. rep., University of Bristol (January 2009)Google Scholar
- 7.Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press (2004)Google Scholar
- 8.Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. Null 2, 506–513 (2004)Google Scholar
- 9.Kovesi, P.D.: MATLAB and Octave functions for computer vision and image processing (2000), http://www.csse.uwa.edu.au/~pk/Research/MatlabFns
- 10.Lowe, D.G.: Object recognition from local Scale-Invariant features. In: Proceedings of the International Conference on Computer Vision, vol. 2, p. 1150. IEEE (1999)Google Scholar
- 14.Moravec, H.P.: Visual Mapping by a Robot Rover (1979)Google Scholar
- 15.Orlinski, A.: Pan-o-matic - automatic control point creator for huginGoogle Scholar
- 17.Zilberstein, S.: Using anytime algorithms in intelligent systems. AI Magazine 17(3), 73–83 (1996)Google Scholar