The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo descreve um novo método para detecção e rastreamento de objetos em movimento a partir de uma sequência de imagens de câmeras em movimento usando estimativa robusta e modelos de contorno ativos. Assumimos que o movimento aparente de fundo entre dois quadros de imagem consecutivos pode ser aproximado por transformação afim. Para registrar o fundo estático, estimamos os parâmetros de transformação afins usando o método LMedS (Least Median of Squares), que é uma espécie de estimador robusto. Modelos de contorno divididos e mesclados são empregados para rastrear vários objetos em movimento. A energia da imagem dos modelos de contorno é definida com base na imagem obtida subtraindo o quadro anterior transformado com parâmetros afins estimados do quadro atual. Implementamos o método em um sistema de processamento de imagens que consiste em placas DSP para rastreamento em tempo real de objetos em movimento a partir de uma sequência de imagens de câmeras em movimento.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Shoichi ARAKI, Takashi MATSUOKA, Naokazu YOKOYA, Haruo TAKEMURA, "Real-Time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1583-1591, July 2000, doi: .
Abstract: This paper describes a new method for detection and tracking of moving objects from a moving camera image sequence using robust estimation and active contour models. We assume that the apparent background motion between two consecutive image frames can be approximated by affine transformation. In order to register the static background, we estimate affine transformation parameters using LMedS (Least Median of Squares) method which is a kind of robust estimator. Split-and-merge contour models are employed for tracking multiple moving objects. Image energy of contour models is defined based on the image which is obtained by subtracting the previous frame transformed with estimated affine parameters from the current frame. We have implemented the method on an image processing system which consists of DSP boards for real-time tracking of moving objects from a moving camera image sequence.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1583/_p
Copiar
@ARTICLE{e83-d_7_1583,
author={Shoichi ARAKI, Takashi MATSUOKA, Naokazu YOKOYA, Haruo TAKEMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Real-Time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence},
year={2000},
volume={E83-D},
number={7},
pages={1583-1591},
abstract={This paper describes a new method for detection and tracking of moving objects from a moving camera image sequence using robust estimation and active contour models. We assume that the apparent background motion between two consecutive image frames can be approximated by affine transformation. In order to register the static background, we estimate affine transformation parameters using LMedS (Least Median of Squares) method which is a kind of robust estimator. Split-and-merge contour models are employed for tracking multiple moving objects. Image energy of contour models is defined based on the image which is obtained by subtracting the previous frame transformed with estimated affine parameters from the current frame. We have implemented the method on an image processing system which consists of DSP boards for real-time tracking of moving objects from a moving camera image sequence.},
keywords={},
doi={},
ISSN={},
month={July},}
Copiar
TY - JOUR
TI - Real-Time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence
T2 - IEICE TRANSACTIONS on Information
SP - 1583
EP - 1591
AU - Shoichi ARAKI
AU - Takashi MATSUOKA
AU - Naokazu YOKOYA
AU - Haruo TAKEMURA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - This paper describes a new method for detection and tracking of moving objects from a moving camera image sequence using robust estimation and active contour models. We assume that the apparent background motion between two consecutive image frames can be approximated by affine transformation. In order to register the static background, we estimate affine transformation parameters using LMedS (Least Median of Squares) method which is a kind of robust estimator. Split-and-merge contour models are employed for tracking multiple moving objects. Image energy of contour models is defined based on the image which is obtained by subtracting the previous frame transformed with estimated affine parameters from the current frame. We have implemented the method on an image processing system which consists of DSP boards for real-time tracking of moving objects from a moving camera image sequence.
ER -