A novel method for 2D-to-3D video conversion based on boundary information
Abstract This paper proposes a novel method for 2D-to-3D video conversion, based on boundary information to automatically generate the depth map. First, we use the Gaussian model to detect foreground objects and then separate the foreground and background. Second, we employ the superpixel algorithm...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2018-01-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13640-017-0239-5 |
| _version_ | 1819019939421356032 |
|---|---|
| author | Tsung-Han Tsai Tai-Wei Huang Rui-Zhi Wang |
| author_facet | Tsung-Han Tsai Tai-Wei Huang Rui-Zhi Wang |
| author_sort | Tsung-Han Tsai |
| collection | DOAJ |
| description | Abstract This paper proposes a novel method for 2D-to-3D video conversion, based on boundary information to automatically generate the depth map. First, we use the Gaussian model to detect foreground objects and then separate the foreground and background. Second, we employ the superpixel algorithm to find the edge information. According to the superpixels, we will assign corresponding hierarchical depth value to initial depth map. From the result of depth value assignment, we detect the edges by Sobel edge detection with two thresholds to strengthen edge information. To identify the boundary pixels, we use a thinning algorithm to modify edge detection. Following these results, we assign the depth value of foreground to refine it. We use four kinds of scanning path for the entire image to create a more accurate depth map. After that, we have the final depth map. Finally, we utilize depth image-based rendering (DIBR) to synthesize left and right view images. After combining the depth map and the original 2D video, a vivid 3D video is produced. |
| first_indexed | 2024-12-21T03:43:17Z |
| format | Article |
| id | doaj.art-cc49666964c14a1d8704b5c65dde569b |
| institution | Directory Open Access Journal |
| issn | 1687-5281 |
| language | English |
| last_indexed | 2024-12-21T03:43:17Z |
| publishDate | 2018-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-cc49666964c14a1d8704b5c65dde569b2022-12-21T19:17:10ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812018-01-012018111310.1186/s13640-017-0239-5A novel method for 2D-to-3D video conversion based on boundary informationTsung-Han Tsai0Tai-Wei Huang1Rui-Zhi Wang2Department of Electrical Engineering, National Central UniversityDepartment of Electrical Engineering, National Central UniversityDepartment of Electrical Engineering, National Central UniversityAbstract This paper proposes a novel method for 2D-to-3D video conversion, based on boundary information to automatically generate the depth map. First, we use the Gaussian model to detect foreground objects and then separate the foreground and background. Second, we employ the superpixel algorithm to find the edge information. According to the superpixels, we will assign corresponding hierarchical depth value to initial depth map. From the result of depth value assignment, we detect the edges by Sobel edge detection with two thresholds to strengthen edge information. To identify the boundary pixels, we use a thinning algorithm to modify edge detection. Following these results, we assign the depth value of foreground to refine it. We use four kinds of scanning path for the entire image to create a more accurate depth map. After that, we have the final depth map. Finally, we utilize depth image-based rendering (DIBR) to synthesize left and right view images. After combining the depth map and the original 2D video, a vivid 3D video is produced.http://link.springer.com/article/10.1186/s13640-017-0239-53D video2D to 3D conversionDepth mapForeground segmentationSuperpixelDIBR |
| spellingShingle | Tsung-Han Tsai Tai-Wei Huang Rui-Zhi Wang A novel method for 2D-to-3D video conversion based on boundary information EURASIP Journal on Image and Video Processing 3D video 2D to 3D conversion Depth map Foreground segmentation Superpixel DIBR |
| title | A novel method for 2D-to-3D video conversion based on boundary information |
| title_full | A novel method for 2D-to-3D video conversion based on boundary information |
| title_fullStr | A novel method for 2D-to-3D video conversion based on boundary information |
| title_full_unstemmed | A novel method for 2D-to-3D video conversion based on boundary information |
| title_short | A novel method for 2D-to-3D video conversion based on boundary information |
| title_sort | novel method for 2d to 3d video conversion based on boundary information |
| topic | 3D video 2D to 3D conversion Depth map Foreground segmentation Superpixel DIBR |
| url | http://link.springer.com/article/10.1186/s13640-017-0239-5 |
| work_keys_str_mv | AT tsunghantsai anovelmethodfor2dto3dvideoconversionbasedonboundaryinformation AT taiweihuang anovelmethodfor2dto3dvideoconversionbasedonboundaryinformation AT ruizhiwang anovelmethodfor2dto3dvideoconversionbasedonboundaryinformation AT tsunghantsai novelmethodfor2dto3dvideoconversionbasedonboundaryinformation AT taiweihuang novelmethodfor2dto3dvideoconversionbasedonboundaryinformation AT ruizhiwang novelmethodfor2dto3dvideoconversionbasedonboundaryinformation |