Dynamic Stereo with Spatial Support

Abstract: 
We present a novel method based on a Kalman filter for integrating disparity measures obtained by processing frames pairwise from a monocular video sequence. Acquired frames are processed pairwise, starting from a first reference and progressively integrating information coming from subsequent frames, taking spatial support into account in each frame. In this way, stabilization of the generated maps is obtained as well as more consistency with the real video content. Results and evidences coming from the benchmark of the system on both synthetic and natural images have also been reported, showing significant improvements with respect to other strategies.
PhD ExpO Year: 
2014
Research Area: 
Ingegneria Informatica e Multimedia