Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods

T. Szirányi, László Czúni

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In this paper we outline a fully parallel and locally connected computation model for the spatio-temporal segmentation of motion events in video sequences. We are searching for a new algorithm, which can be easily implemented in one-pixel/one-processor cell-array VLSI architectures at high-speed. Our proposed algorithm starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, which is calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on the values of intensity, speed and the time-depth of motion history. As for checking the merging process there is a feedback implemented, by that we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation and serial processing of these components, image features are defined on the pixel-level. We use simple functions, easily realizable in VLSI, like arithmetic and logical operators, local memory transfers and convolution.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages820-823
Number of pages4
Volume15
Edition4
Publication statusPublished - 2000

Fingerprint

Pixels
Convolution
Merging
Mathematical operators
Feedback
Data storage equipment
Processing

ASJC Scopus subject areas

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

Cite this

Szirányi, T., & Czúni, L. (2000). Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods. In Proceedings - International Conference on Pattern Recognition (4 ed., Vol. 15, pp. 820-823)

Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods. / Szirányi, T.; Czúni, László.

Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. p. 820-823.

Research output: Chapter in Book/Report/Conference proceedingChapter

Szirányi, T & Czúni, L 2000, Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods. in Proceedings - International Conference on Pattern Recognition. 4 edn, vol. 15, pp. 820-823.
Szirányi T, Czúni L. Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods. In Proceedings - International Conference on Pattern Recognition. 4 ed. Vol. 15. 2000. p. 820-823
Szirányi, T. ; Czúni, László. / Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods. Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. pp. 820-823
@inbook{0ac35349735e48e5a25b92ff95f89cda,
title = "Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods",
abstract = "In this paper we outline a fully parallel and locally connected computation model for the spatio-temporal segmentation of motion events in video sequences. We are searching for a new algorithm, which can be easily implemented in one-pixel/one-processor cell-array VLSI architectures at high-speed. Our proposed algorithm starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, which is calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on the values of intensity, speed and the time-depth of motion history. As for checking the merging process there is a feedback implemented, by that we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation and serial processing of these components, image features are defined on the pixel-level. We use simple functions, easily realizable in VLSI, like arithmetic and logical operators, local memory transfers and convolution.",
author = "T. Szir{\'a}nyi and L{\'a}szl{\'o} Cz{\'u}ni",
year = "2000",
language = "English",
volume = "15",
pages = "820--823",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "4",

}

TY - CHAP

T1 - Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods

AU - Szirányi, T.

AU - Czúni, László

PY - 2000

Y1 - 2000

N2 - In this paper we outline a fully parallel and locally connected computation model for the spatio-temporal segmentation of motion events in video sequences. We are searching for a new algorithm, which can be easily implemented in one-pixel/one-processor cell-array VLSI architectures at high-speed. Our proposed algorithm starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, which is calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on the values of intensity, speed and the time-depth of motion history. As for checking the merging process there is a feedback implemented, by that we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation and serial processing of these components, image features are defined on the pixel-level. We use simple functions, easily realizable in VLSI, like arithmetic and logical operators, local memory transfers and convolution.

AB - In this paper we outline a fully parallel and locally connected computation model for the spatio-temporal segmentation of motion events in video sequences. We are searching for a new algorithm, which can be easily implemented in one-pixel/one-processor cell-array VLSI architectures at high-speed. Our proposed algorithm starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, which is calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on the values of intensity, speed and the time-depth of motion history. As for checking the merging process there is a feedback implemented, by that we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation and serial processing of these components, image features are defined on the pixel-level. We use simple functions, easily realizable in VLSI, like arithmetic and logical operators, local memory transfers and convolution.

UR - http://www.scopus.com/inward/record.url?scp=33750909814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750909814&partnerID=8YFLogxK

M3 - Chapter

VL - 15

SP - 820

EP - 823

BT - Proceedings - International Conference on Pattern Recognition

ER -