Parallax-Robust Surveillance Video Stitching

Botao He, Shaohua Yu
2015 Sensors  
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
more » ... 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.
doi:10.3390/s16010007 pmid:26712756 pmcid:PMC4732040 fatcat:vcxww47fhfah3chdrg64jze6qy