A significant portion of recent research in computer vision has focused on issues related to sensitivity and robustness of existing techniques. In this paper, we study the classical structure from motion problem and analyze how the statistics representing the quality of the input video propagates through the reconstruction algorithm and affects the quality of the output reconstruction. Specifically, we show that it is possible to derive analytical expressions of the first and second order statistics (bias and error covariance) of the solution as a function of the statistics of the input. We concentrate on the case of reconstruction from a monocular video, where the small baseline makes any algorithm very susceptible to noise in the motion estimates from the video sequence. We derive an expression relating the error covariance of the reconstruction to the error covariance of the feature tracks in the input video. This is done using the implicit function theorem of real analysis and does not require strong statistical assumptions. Next, we prove that the 3D reconstruction is statistically biased, derive an expression for it and show that it is numerically significant. Combining these two results, we also establish a new bound on the minimum error in the depth reconstruction. We present the numerical significance of these analytical results on real video data.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Statistical Error Propagation in 3D Modeling From Monocular Video


    Contributors:


    Publication date :

    2003-06-01


    Size :

    235710 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real Time Speed Estimation From Monocular Video

    Temiz, M. S. / Kulur, S. / Dogan, S. | BASE | 2012

    Free access

    Geometry-based next frame prediction from monocular video

    Mahjourian, Reza / Wicke, Martin / Angelova, Anelia | IEEE | 2017


    Monocular Video serves RADAR-based Emergency Braking

    Wedel, Andreas / Franke, Uwe | IEEE | 2007


    WarpCut - fast obstacle segmentation in monocular video

    Wedel, Andreas / Schoenemann, Thomas / Brox, Thomas et al. | Tema Archive | 2007


    Monocular Video Serves RADAR-Based Emergency Braking

    Wedel, A. / Franke, U. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2007