From an Intensity Image to 3-D Segmented Descriptions
Abstract
We address the inference of 3-D segmented descriptions of complex objects from a single intensity image. Our approach is based on the analysis of the projective properties of a small number of generalized cylinder primitives and their relationships in the image which make up common man-made objects. Past work on this problem has either assumed perfect contours as input or used 2-dimensional shape primitives without relating them to 3-D shape. The method we present explicitly uses the 3-dimensionality of the desired descriptions and directly addresses the segmentation problem in the presence of contour breaks, markings shadows and occlusion. This work has many significant applications including recognition of complex curved objects from a single real intensity image. We demonstrate our method on real images.
Cite
Text
Zerroug and Nevatia. "From an Intensity Image to 3-D Segmented Descriptions." European Conference on Computer Vision, 1996. doi:10.1007/3-540-61750-7_21Markdown
[Zerroug and Nevatia. "From an Intensity Image to 3-D Segmented Descriptions." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/zerroug1996eccv-intensity/) doi:10.1007/3-540-61750-7_21BibTeX
@inproceedings{zerroug1996eccv-intensity,
title = {{From an Intensity Image to 3-D Segmented Descriptions}},
author = {Zerroug, Mourad and Nevatia, Ramakant},
booktitle = {European Conference on Computer Vision},
year = {1996},
pages = {11-24},
doi = {10.1007/3-540-61750-7_21},
url = {https://mlanthology.org/eccv/1996/zerroug1996eccv-intensity/}
}