Active surface estimation: integrating coarse-to-fine image acquisition and estimation from multiple cues

摘要

This paper is concerned with the problem of surface reconstruction from stereo images for large scenes having large depth ranges with depth discontinuities. The passive stereo paradigm is inadequate for this problem because of the need to aim cameras in different directions and to fixate at different objects. We present an active approach that involves the following steps. First, a new fixation point is selected from among the nonfixated, low-resolution scene parts of current fixation. Second, a reconfiguration of the cameras is initiated for refixation. As reconfiguration progresses, the images of the new fixation point gradually deblur and the accuracy of the position estimate of the point improves allowing the cameras to be aimed at it with increasing precision. In the third step, the improved depth estimate is used to select focus settings of the cameras, thus completing fixation. Finally, stereo images are acquired and segmented into fixated and nonfixated parts of the scene that are analyzed in parallel.