ML Anthology

Shape Models from Image Sequences

Xinquan Shen, David C. Hogg
ECCV 1994 pp. 225-230
doi:10.1007/3-540-57956-7_27 /eccv/1994/shen1994eccv-shape/

Abstract

This paper describes an adaptive method for the recovery of 3-D shape models from sequences of images. A 3-D surface model, initialised to be spherical, is progressively deformed under the action of simulated external forces arising from the profile of the target object in successive images, obtained using a low-level motion segmentation algorithm. Intrinsic constraints encourage the model to deform smoothly and to remain symmetrical about a vertical plane parallel to the direction of motion.

PDF ECCV Semantic Scholar

Cite

Text

Shen and Hogg. "Shape Models from Image Sequences." European Conference on Computer Vision, 1994. doi:10.1007/3-540-57956-7_27

Markdown

[Shen and Hogg. "Shape Models from Image Sequences." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/shen1994eccv-shape/) doi:10.1007/3-540-57956-7_27

BibTeX

@inproceedings{shen1994eccv-shape,
  title     = {{Shape Models from Image Sequences}},
  author    = {Shen, Xinquan and Hogg, David C.},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {225-230},
  doi       = {10.1007/3-540-57956-7_27},
  url       = {https://mlanthology.org/eccv/1994/shen1994eccv-shape/}
}