Detection and recognition of moving objects using statistical motion detection and Fourier descriptors

Daniel Toth; Til Aach

doi:10.1109/ICIAP.2003.1234088

Detection and recognition of moving objects using statistical motion detection and Fourier descriptors

Daniel Toth, Til Aach

Institute of Signal Processing

Abstract

Object recognition, i.e. classification of objects into one of several known object classes, generally is a difficult task. In this paper we address the problem of detecting and classifying moving objects in image sequences from traffic scenes recorded with a static camera. In the first step, a statistical, illumination invariant motion detection algorithm is used to produce binary masks of the scene-changes. Next, Fourier descriptors of the shapes from the refined masks are computed and used as feature vectors describing the different objects in the scene. Finally, a feedforward neural net is used to distinguish between humans, vehicles, and background clutter.

Original language	English
Title of host publication	12th International Conference on Image Analysis and Processing, 2003.Proceedings.
Number of pages	6
Publisher	IEEE
Publication date	01.12.2003
Pages	430-435
Article number	1234088
ISBN (Print)	0-7695-1948-2
DOIs	https://doi.org/10.1109/ICIAP.2003.1234088
Publication status	Published - 01.12.2003
Event	12th International Conference on Image Analysis and Processing - Mantova, Italy Duration: 17.09.2003 → 19.09.2003 Conference number: 101350

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICIAP.2003.1234088

Cite this

@inproceedings{fbe797ac8dea4ad48c0527d6cd6add1f,

title = "Detection and recognition of moving objects using statistical motion detection and Fourier descriptors",

abstract = "Object recognition, i.e. classification of objects into one of several known object classes, generally is a difficult task. In this paper we address the problem of detecting and classifying moving objects in image sequences from traffic scenes recorded with a static camera. In the first step, a statistical, illumination invariant motion detection algorithm is used to produce binary masks of the scene-changes. Next, Fourier descriptors of the shapes from the refined masks are computed and used as feature vectors describing the different objects in the scene. Finally, a feedforward neural net is used to distinguish between humans, vehicles, and background clutter.",

author = "Daniel Toth and Til Aach",

year = "2003",

month = dec,

day = "1",

doi = "10.1109/ICIAP.2003.1234088",

language = "English",

isbn = "0-7695-1948-2",

series = "IEEE Proceedings",

publisher = "IEEE",

pages = "430--435",

booktitle = "12th International Conference on Image Analysis and Processing, 2003.Proceedings.",

note = "12th International Conference on Image Analysis and Processing <br/>, ICIAP 2003 ; Conference date: 17-09-2003 Through 19-09-2003",

}

Toth, D & Aach, T 2003, Detection and recognition of moving objects using statistical motion detection and Fourier descriptors. in 12th International Conference on Image Analysis and Processing, 2003.Proceedings.., 1234088, IEEE Proceedings, IEEE, pp. 430-435, 12th International Conference on Image Analysis and Processing
, Mantova, Italy, 17.09.03. https://doi.org/10.1109/ICIAP.2003.1234088

Detection and recognition of moving objects using statistical motion detection and Fourier descriptors. / Toth, Daniel; Aach, Til.
12th International Conference on Image Analysis and Processing, 2003.Proceedings.. IEEE, 2003. p. 430-435 1234088 (IEEE Proceedings).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Detection and recognition of moving objects using statistical motion detection and Fourier descriptors

AU - Toth, Daniel

AU - Aach, Til

N1 - Conference code: 101350

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Object recognition, i.e. classification of objects into one of several known object classes, generally is a difficult task. In this paper we address the problem of detecting and classifying moving objects in image sequences from traffic scenes recorded with a static camera. In the first step, a statistical, illumination invariant motion detection algorithm is used to produce binary masks of the scene-changes. Next, Fourier descriptors of the shapes from the refined masks are computed and used as feature vectors describing the different objects in the scene. Finally, a feedforward neural net is used to distinguish between humans, vehicles, and background clutter.

AB - Object recognition, i.e. classification of objects into one of several known object classes, generally is a difficult task. In this paper we address the problem of detecting and classifying moving objects in image sequences from traffic scenes recorded with a static camera. In the first step, a statistical, illumination invariant motion detection algorithm is used to produce binary masks of the scene-changes. Next, Fourier descriptors of the shapes from the refined masks are computed and used as feature vectors describing the different objects in the scene. Finally, a feedforward neural net is used to distinguish between humans, vehicles, and background clutter.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-84890517964&origin=inward&txGid=b41cfd80c0d77f66c52cad5246f8a3b8

U2 - 10.1109/ICIAP.2003.1234088

DO - 10.1109/ICIAP.2003.1234088

M3 - Conference contribution

SN - 0-7695-1948-2

T3 - IEEE Proceedings

SP - 430

EP - 435

BT - 12th International Conference on Image Analysis and Processing, 2003.Proceedings.

PB - IEEE

T2 - 12th International Conference on Image Analysis and Processing <br/>

Y2 - 17 September 2003 through 19 September 2003

ER -

Detection and recognition of moving objects using statistical motion detection and Fourier descriptors

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this