Parallax-Robust Surveillance Video Stitching
Open Access
Abstract
This paper presents a parallax-robust video stitching technique for timely synchronized surveillance video. An efficient two-stage video stitching procedure is proposed in this paper to build wide Field-of-View (FOV) videos for surveillance applications. In the stitching model calculation stage, we develop a layered warping algorithm to align the background scenes, which is location-dependent and turned out to be more robust to parallax than the traditional global projective warping methods. On the selective seam updating stage, we propose a change-detection based optimal seam selection approach to avert ghosting and artifacts caused by moving foregrounds. Experimental results demonstrate that our procedure can efficiently stitch multi-view videos into a wide FOV video output without ghosting and noticeable seams.Keywords
This publication has 33 references indexed in Scilit:
- As-Projective-As-Possible Image Stitching with Moving DLTIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Image stitching with dynamic elementsImage and Vision Computing, 2009
- Image Alignment and Stitching: A TutorialFoundations and Trends in Computer Graphics and Vision, 2007
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Seamless Image Stitching of Scenes with Large Motions and Exposure Differences2006
- Layer-based video registrationMachine Vision and Applications, 2005
- Interactive digital photomontageACM Transactions on Graphics, 2004
- Mosaics of video sequences with moving objectsSignal Processing: Image Communication, 2004
- Graphcut texturesACM Transactions on Graphics, 2003
- Video mosaics for virtual environmentsIEEE Computer Graphics and Applications, 1996