A novel affine invariant feature set and its application in motion estimation

L. Chen; Z. Lu; E. K. Teoh; Z. Xue

A novel affine invariant feature set and its application in motion estimation

L. Chen, Z. Lu, E. K. Teoh, Z. Xue

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper proposed a novel semi-local feature set, which is proved to be affine invariant. The proposed feature set can be local or global based on the mask parameter selected. Small mask indicates local features, which are more precise and not sensitive to occlusion problem. Large mask indicates global features, which are more robust and less sensitive to noise. Using this feature set a correspondence based velocity estimation algorithm is developed. This motion estimation method can be used in motion detection, motion segmentation, and motion based recognition.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Volume	3
State	Published - Dec 1 2000
Event	International Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada Duration: Sep 10 2000 → Sep 13 2000

Other

Other	International Conference on Image Processing (ICIP 2000)
Country/Territory	Canada
City	Vancouver, BC
Period	9/10/00 → 9/13/00

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Hardware and Architecture
Electrical and Electronic Engineering

Cite this

@inproceedings{03bb533be37142609c46f9589a513a85,

title = "A novel affine invariant feature set and its application in motion estimation",

abstract = "This paper proposed a novel semi-local feature set, which is proved to be affine invariant. The proposed feature set can be local or global based on the mask parameter selected. Small mask indicates local features, which are more precise and not sensitive to occlusion problem. Large mask indicates global features, which are more robust and less sensitive to noise. Using this feature set a correspondence based velocity estimation algorithm is developed. This motion estimation method can be used in motion detection, motion segmentation, and motion based recognition.",

author = "L. Chen and Z. Lu and Teoh, {E. K.} and Z. Xue",

year = "2000",

month = dec,

day = "1",

language = "English",

volume = "3",

booktitle = "IEEE International Conference on Image Processing",

note = "International Conference on Image Processing (ICIP 2000) ; Conference date: 10-09-2000 Through 13-09-2000",

}

TY - GEN

T1 - A novel affine invariant feature set and its application in motion estimation

AU - Chen, L.

AU - Lu, Z.

AU - Teoh, E. K.

AU - Xue, Z.

PY - 2000/12/1

Y1 - 2000/12/1

N2 - This paper proposed a novel semi-local feature set, which is proved to be affine invariant. The proposed feature set can be local or global based on the mask parameter selected. Small mask indicates local features, which are more precise and not sensitive to occlusion problem. Large mask indicates global features, which are more robust and less sensitive to noise. Using this feature set a correspondence based velocity estimation algorithm is developed. This motion estimation method can be used in motion detection, motion segmentation, and motion based recognition.

AB - This paper proposed a novel semi-local feature set, which is proved to be affine invariant. The proposed feature set can be local or global based on the mask parameter selected. Small mask indicates local features, which are more precise and not sensitive to occlusion problem. Large mask indicates global features, which are more robust and less sensitive to noise. Using this feature set a correspondence based velocity estimation algorithm is developed. This motion estimation method can be used in motion detection, motion segmentation, and motion based recognition.

UR - http://www.scopus.com/inward/record.url?scp=0034443652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034443652&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034443652

VL - 3

BT - IEEE International Conference on Image Processing

T2 - International Conference on Image Processing (ICIP 2000)

Y2 - 10 September 2000 through 13 September 2000

ER -

A novel affine invariant feature set and its application in motion estimation

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this