Determining Spatial Motion Directly from Normal Flow Field: A Comprehensive Treatment
Determining motion from a video of the imaged scene relative to the camera is important for various robotics tasks including visual control and autonomous navigation. The difficulty of the problem lies mainly in that the flow pattern directly observable in the video is generally not the full flow field induced by the motion, but only partial information of it, which is known as the normal flow field. A few methods collectively referred to as the direct methods have been proposed to determine the spatial motion from merely the normal flow field without ever interpolating the full flows. However, such methods generally have difficulty addressing the case of general motion. This work proposes a new direct method that uses two constraints: one related to the direction component of the normal flow field, and the other to the magnitude component, to determine motion. The first constraint presents itself as a system of linear inequalities to bind the motion parameters; the second one uses the rotation magnitude’s globality to all image positions to constrain the motion parameters further. A two-stage iterative process in a coarse-to-fine framework is used to exploit the two constraints. Experimental results on benchmark data show that the new treatment can tackle even the case of general motion.
KeywordsMotion Vector Motion Parameter Linear Inequality General Motion Spatial Motion
Unable to display preview. Download preview PDF.
- 3.Bruss, A.R., Horn, B.K.P.: Passive navigation. In: Int’l Conf. on Computer Vision Graphic and Imagining, vol. 21, pp. 3–20 (1983)Google Scholar
- 4.Chung, R., Yuan, D.: Direct determination of camera motion from normal flows. In: Int’l Conf. on Visualization, Imaging, and Image Processing, pp. 153–157 (2009)Google Scholar
- 5.Cipolla, R., Okamoto, Y., Kuno, Y.: Robust structure from motion using motion parallax. In: Int’l Conf. Computer Vision, pp. 374–382 (1993)Google Scholar
- 6.Farnebäck, G.: Polynomial expansion for orientation and motion estimation. PhD thesis, Dept. of Electrical Engineering, Linköping University (2002)Google Scholar
- 7.Fejes, S., Davis, L.S.: What can projections of flow fields tell us about the visual motion. In: Int’l Conf. on Computer Vision, pp. 979–986 (1998)Google Scholar
- 10.Horn, B.K.P., Shunck, B.G.: Determining optical Flow. AI 17, 185–203 (1981)Google Scholar
- 12.Lourakis, M.I.A.: Using constraint lines for estimating egomotion. In: Asian Conf. on Computer Vision, pp. 971–976 (2000)Google Scholar
- 13.Lourakis, M.I.A.: Egomotion estimation using quadruples of collinear image points. In: European Conf. on Computer Vision, pp. 834–848 (2000)Google Scholar
- 14.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Int’l Conf. on Computer Vision, pp. 933–938 (1981)Google Scholar
- 16.Raudies, F., Neumann, H.: An efficient linear method for the estimation of ego-motion from optical flow. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM. LNCS, vol. 5748, pp. 11–20. Springer, Heidelberg (2009)Google Scholar
- 18.Silva, C., Santos-Victor, J.: Egomotion estimation on a topological space. In: Int’l Conf. on Pattern Recognition, pp. 64–66 (1998)Google Scholar