Paper in ICCV 1999: “Motion Based Decompositing Video”

Motion Based Decompositing Video

  • G. J. Brostow and I. Essa (1999), “Motion Based Decompositing of Video,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 1999, pp. 8-13. [PDF] [WEBSITE] [DOI] [BLOG] [BIBTEX]
    @InProceedings{    1999-Brostow-MBDV,
      author  = {G. J. Brostow and I. Essa},
      blog    = {},
      booktitle  = {Proceedings of IEEE International Conference on
          Computer Vision (ICCV)},
      doi    = {},
      pages    = {8--13},
      pdf    = {},
      publisher  = {IEEE Computer Society},
      title    = {Motion Based Decompositing of Video},
      url    = {},
      volume  = {1},
      year    = {1999}


We present a method to decompose video sequences into layers that represent the relative depths of complex scenes. Our method combines spatial information with temporal occlusions to determine relative depths of these layers. Spatial information is obtained through edge detection and a customized contour completion algorithm. Activity in a scene is used to extract temporal occlusion events, which are in turn, used to classify objects as occluders or occludees. The path traversed by the moving objects determines the segmentation of the scene. Several examples of decompositing and compositing of video are shown. This approach can be applied in the pre-processing of sequences for compositing or tracking purposes and to determine the approximate 3D structure of a scene.

Tags: , , , , , | Categories: Aware Home, Computational Photography and Video, Gabriel Brostow, Intelligent Environments, PAMI/ICCV/CVPR/ECCV, Papers | Date: September 10th, 1999 | By: Irfan Essa |

No Comments »

You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

Leave a Reply