Human Centric Panoramic Imaging Stitching

We introduce a novel image mosaicing algorithm to generate a 360◦ landscape images while also taking into account the presence of people at the boundaries between stitched im- ages. Current image mosaicing techniques tend to fail when there is extreme parallax caused by nearby objects or mov- ing objects at the boundary between images. This parallax causes ghosting or unnatural discontinuities in the image. To address this problem, we present an image mosaicing al- gorithm that is robust to parallax and misalignment, and is also able to preserve the important human-centric con- tent, specifically faces. In particular, we find an optimal path between the boundary of two images that preserves color continuity and peoples’ faces in the scene. Prelimi- nary results show promising results of preserving close-up faces with parallax while also being able to generate a per- ceptually plausible 360◦ panoramic image.

- Tomohiro Ozawa, Kris M. Kitani, Hideki Koike: Human Centric Panoramic Imaging Stitching, Proc. on ACM Augmented Human (AH 2012), 2012.