Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences

Daphna Weinshall; Carlo Tomasi

doi:10.1109/34.391392

Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences

Daphna Weinshall, Carlo Tomasi

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Article › peer-review

40 Scopus citations

Abstract

We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.

Original language	English
Pages (from-to)	512-517
Number of pages	6
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	17
Issue number	5
DOIs	https://doi.org/10.1109/34.391392
State	Published - May 1995

Keywords

Euclidean shape
Gramian
Structure from motion
affine coordinates
affine shape
factorization method
linear reconstruction
weak perspective

Access to Document

10.1109/34.391392

Cite this

@article{262dba7c231841d590819a1be78bec72,

title = "Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences",

abstract = "We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.",

keywords = "Euclidean shape, Gramian, Structure from motion, affine coordinates, affine shape, factorization method, linear reconstruction, weak perspective",

author = "Daphna Weinshall and Carlo Tomasi",

year = "1995",

month = may,

doi = "10.1109/34.391392",

language = "אנגלית",

volume = "17",

pages = "512--517",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "5",

}

TY - JOUR

T1 - Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences

AU - Weinshall, Daphna

AU - Tomasi, Carlo

PY - 1995/5

Y1 - 1995/5

N2 - We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.

AB - We show how to automatically acquire Euclidian shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudoinverse. A nonlinear, but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improves the shape results substantially with respect to previous methods proposed for ideal images.

KW - Euclidean shape

KW - Gramian

KW - Structure from motion

KW - affine coordinates

KW - affine shape

KW - factorization method

KW - linear reconstruction

KW - weak perspective

UR - http://www.scopus.com/inward/record.url?scp=0029306613&partnerID=8YFLogxK

U2 - 10.1109/34.391392

DO - 10.1109/34.391392

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0029306613

SN - 0162-8828

VL - 17

SP - 512

EP - 517

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 5

ER -

Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this