A Robust Recursive Factorization Method for Recovering Structure and Motion from Live Video Frames

Takeshi Kurata*, Jun Fujiki*, Masakatsu Kourogi+, Katsuhiko Sakaue*

*Electrotechnical Laboratory, 1-1-4 Umezono, Tsukuba, Ibaraki, 305-8568, JAPAN
+School of Sci. & Eng., Waseda University, 3-4-1 Ohkubo, Shinjuku, Tokyo, 169-8555, JAPAN

Email: t.kurata@aist.go.jp
URL: http://staff.aist.go.jp/t.kurata/

This paper describes a fast and robust approach for recovering structure and motion from video frames. It first describes a robust recursive factorization method for affine projection. Using the Least Median of Squares (LMedS) criterion, the method estimates the dominant 3D affine motion and discards feature points regarded as outliers. The computational cost of the overall procedure is reduced by combining this robust-statistics-based method with a recursive factorization method that can at each frame provide the updated 3D structure of an object at a fixed computational cost by using the principal component analysis. This paper then describes experiments with synthetic data and with real image sequences, the results of which demonstrate that the method can be used to estimate the dominant structure and the motion robustly and in real-time on an off-the-shelf PC.

  • The paper in PDF format
  • MPEG files linked in the above PDF paper
    • A Stuffed Koala

    Movie 1. Tracked feature points

    Movie 2. Feature points with the dominant 3D motion

    Movie 3. The recovered dense shape
    • A Face

    Movie 4. Tracked feature points

    Movie 5. Feature points with the dominant 3D motion

    Movie 6. The recovered dense shape
    • An Example of Online Experiments

    Movie 7. Feature points with the dominant 3D motion