ML Anthology

Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects

Fred Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
CVPR 2004 pp. 914-921
doi:10.1109/CVPR.2004.222 /cvpr/2004/rothganger2004cvpr-segmenting/

Abstract

This paper presents a novel representation for dynamic scenes composed of multiple rigid objects that may undergo different motions and be observed by a moving camera. Multi-view constraints associated with groups of affine-invariant scene patches and a normalized description of their appearance are used to segment a scene into its rigid parts, construct three-dimensional protective, affine, and Euclidean models of these parts, and match instances of models recovered from different image sequences. The proposed approach has been implemented, and it is applied to the detection and recognition of moving objects in video sequences and the identification of shots that depict the same scene in a video clip (shot matching).

PDF CVPR Semantic Scholar

Cite

Text

Rothganger et al. "Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.222

Markdown

[Rothganger et al. "Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/rothganger2004cvpr-segmenting/) doi:10.1109/CVPR.2004.222

BibTeX

@inproceedings{rothganger2004cvpr-segmenting,
  title     = {{Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects}},
  author    = {Rothganger, Fred and Lazebnik, Svetlana and Schmid, Cordelia and Ponce, Jean},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {914-921},
  doi       = {10.1109/CVPR.2004.222},
  url       = {https://mlanthology.org/cvpr/2004/rothganger2004cvpr-segmenting/}
}