A data-fusion approach to motion-stereo

• Unconstrained, uncalibrated extension of classical motion-stereo.
• Integrate temporal and spatial information within the same framework.
• Extensive comparison of several disparity confidence measures.
• Cast all depth proxies in a unified framework.

This paper introduces a novel method for performing motion-stereo, based on dynamic integration of depth (or its proxy) measures obtained by pairwise stereo matching of video frames. The focus is on the data fusion issue raised by the motion-stereo approach, which is solved within a Kalman filtering framework. Integration occurs along the temporal and spatial dimension, so that the final measure for a pixel results from the combination of measures of the same pixel in time and whose of its neighbors. The method has been validated on both synthetic and natural images, using the simplest stereo matching strategy and a range of different confidence measures, and has been compared to baseline and optimal strategies.