Parallax-Robust Surveillance Video Stitching
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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/1/7 |
| _version_ | 1818038338272100352 |
|---|---|
| author | Botao He Shaohua Yu |
| author_facet | Botao He Shaohua Yu |
| author_sort | Botao He |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T07:41:09Z |
| format | Article |
| id | doaj.art-3651454cb5994beba1f845b0f2e730f6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T07:41:09Z |
| publishDate | 2015-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3651454cb5994beba1f845b0f2e730f62022-12-22T01:57:18ZengMDPI AGSensors1424-82202015-12-01161710.3390/s16010007s16010007Parallax-Robust Surveillance Video StitchingBotao He0Shaohua Yu1School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan 430074, ChinaWuhan Research Institute of Posts and Telecommunications, Wuhan 430074, ChinaThis 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.http://www.mdpi.com/1424-8220/16/1/7video stitchingvideo surveillancelayered warpingparallax |
| spellingShingle | Botao He Shaohua Yu Parallax-Robust Surveillance Video Stitching Sensors video stitching video surveillance layered warping parallax |
| title | Parallax-Robust Surveillance Video Stitching |
| title_full | Parallax-Robust Surveillance Video Stitching |
| title_fullStr | Parallax-Robust Surveillance Video Stitching |
| title_full_unstemmed | Parallax-Robust Surveillance Video Stitching |
| title_short | Parallax-Robust Surveillance Video Stitching |
| title_sort | parallax robust surveillance video stitching |
| topic | video stitching video surveillance layered warping parallax |
| url | http://www.mdpi.com/1424-8220/16/1/7 |
| work_keys_str_mv | AT botaohe parallaxrobustsurveillancevideostitching AT shaohuayu parallaxrobustsurveillancevideostitching |