It is commonly assumed that the goal of stereovision is computing explicit 3D scene reconstructions. We show that very accurate camera calibration is needed to support this, and that such accurate calibration is difficult to achieve and maintain. We argue that for tasks like recognition, figure/ground separation is more important than 3D depth reconstruction, and demonstrate a stereo algorithm that supports figure/ground separation without 3D reconstruction.


    Access

    Download


    Export, share and cite



    Title :

    Why Stereo Vision is Not Always About 3D Reconstruction


    Contributors:

    Publication date :

    1993


    Size :

    11 pages , 393745 byte , 520870 byte


    Type of media :

    Miscellaneous


    Type of material :

    Electronic Resource


    Language :

    English




    Stereo vision parallelization for three-dimensional reconstruction

    Hernández-Beltrán, José Enrique / Lugo-Aguilar, Mack Orlando / Diaz-Ramirez, Victor H. et al. | SPIE | 2020


    Multi-baseline stereo vision for three-dimensional object reconstruction

    Gonzalez-Ruiz, Martin / Diaz-Ramirez, Victor H. / Juarez-Salazar, Rigoberto | SPIE | 2022


    Continuous Media and Machine Vision: Distributed Active Stereo Reconstruction

    Seales, W. B. / IEEE; Aerospace and Electronics Systems Society | British Library Conference Proceedings | 1996


    ACCURACY ANALYSIS OF SURFACE NORMAL RECONSTRUCTION IN STEREO VISION

    Harms, H. / Beck, J. / Ziegler, J. et al. | British Library Conference Proceedings | 2014


    Stereo vision sensor

    Yuhara,H. / Terauchi,A. / Saka,M. et al. | Automotive engineering | 2000