Scale Invariant Detection and Tracking of Elongated Structures
This paper describes a method for the detection of tracking of elongated structures that is robust under changes of scale and orientation. This method is based on extending the concept of scale invariant natural interest points to include elongated ridge structures. An operator is proposed that directly detects ridge points and provides an estimation of their elongation and orientation. A tracking process is used to follow elongated features over time and to robustly observe changes in scale and orientation. Changes in scale are used to directly estimate time to contact. Experimental results demonstrate that the method works well in cluttered scenes that are typical of urban environments.
KeywordsGraphic Processing Unit Interest Point Scale Invariant Feature Transform Ridge Line Laplacian Pyramid
Unable to display preview. Download preview PDF.
- 3.Crowley, J.L., Hall, D., Colin de Verdière, V.: View invariant object recognition using coloured receptive fields. Machine GRAPHICS and VISION 9(2), 341–352 (2000)Google Scholar
- 5.Harris, C., Stephens, M.: A combined corner and edge detector. pp. 189–192, Manchester (1988)Google Scholar
- 6.Lowe, D.G.: Object recognition from local scale-invariant feature. In: International Conference on Computer Vision, pp. 1150–1157 (1999)Google Scholar
- 7.Negre, A., Braillon, C., Crowley, J.L., Laugier, C.: Real-time time-to-collision from variation of intrinsic scale. In: Proc. of the Int. Symp. on Experimental Robotics, Rio de Janeiro, Brazil (2006)Google Scholar
- 8.Schmid, R.M., Bauckhage, C.: Comparing and evaluating interest points, pp. 230–235 (1998)Google Scholar
- 9.Tran, T.T.H., Lux, A.: A method for ridge extraction. In: Asian Conference on Computer Vision (2004)Google Scholar