A visual neural network for moving object recognition

Noriaki Sato, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

This paper proposes a neural network for moving object recognition based on the visual system. The proposed network has a structure focusing on the parallel hierarchy of visual information processing and can recognize moving objects. The network is composed of a movement detection module, a moving object estimation module, and a moving object recognition module. The movement detection module uses a neural network which is a model of the motion recognition aspect of vision and recognizes motion. The moving object estimation module uses a hierarchical neural network with the backpropagation (BP) algorithm, and infers moving objects based on the features of the motion. The moving object recognition module uses a multiple-structured neural network which is obtained by improvement of the inhibition mechanism and recognizes moving objects on the basis of shape features. The information is transmitted from the movement detection module to the moving object recognition module through the moving object estimation module. With this mechanism, the motion recognition and pattern recognition processes are integrated, and moving objects can be recognized. A computer simulation is performed on the recognition of a walking human, and the effectiveness of the proposed network is demonstrated.

Original languageEnglish
Pages (from-to)46-55
Number of pages10
JournalElectronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume87
Issue number9
DOIs
Publication statusPublished - 2004 Sep

Fingerprint

Object recognition
modules
Neural networks
Backpropagation algorithms
Pattern recognition
Computer simulation
walking
pattern recognition
hierarchies
computerized simulation

Keywords

  • Motion recognition
  • Moving object estimation
  • Pattern recognition
  • Visual information processing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{2b5cefe95ed248888caa68a3b061fba0,
title = "A visual neural network for moving object recognition",
abstract = "This paper proposes a neural network for moving object recognition based on the visual system. The proposed network has a structure focusing on the parallel hierarchy of visual information processing and can recognize moving objects. The network is composed of a movement detection module, a moving object estimation module, and a moving object recognition module. The movement detection module uses a neural network which is a model of the motion recognition aspect of vision and recognizes motion. The moving object estimation module uses a hierarchical neural network with the backpropagation (BP) algorithm, and infers moving objects based on the features of the motion. The moving object recognition module uses a multiple-structured neural network which is obtained by improvement of the inhibition mechanism and recognizes moving objects on the basis of shape features. The information is transmitted from the movement detection module to the moving object recognition module through the moving object estimation module. With this mechanism, the motion recognition and pattern recognition processes are integrated, and moving objects can be recognized. A computer simulation is performed on the recognition of a walking human, and the effectiveness of the proposed network is demonstrated.",
keywords = "Motion recognition, Moving object estimation, Pattern recognition, Visual information processing",
author = "Noriaki Sato and Masafumi Hagiwara",
year = "2004",
month = "9",
doi = "10.1002/ecjb.20115",
language = "English",
volume = "87",
pages = "46--55",
journal = "Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)",
issn = "8756-663X",
publisher = "Scripta Technica",
number = "9",

}

TY - JOUR

T1 - A visual neural network for moving object recognition

AU - Sato, Noriaki

AU - Hagiwara, Masafumi

PY - 2004/9

Y1 - 2004/9

N2 - This paper proposes a neural network for moving object recognition based on the visual system. The proposed network has a structure focusing on the parallel hierarchy of visual information processing and can recognize moving objects. The network is composed of a movement detection module, a moving object estimation module, and a moving object recognition module. The movement detection module uses a neural network which is a model of the motion recognition aspect of vision and recognizes motion. The moving object estimation module uses a hierarchical neural network with the backpropagation (BP) algorithm, and infers moving objects based on the features of the motion. The moving object recognition module uses a multiple-structured neural network which is obtained by improvement of the inhibition mechanism and recognizes moving objects on the basis of shape features. The information is transmitted from the movement detection module to the moving object recognition module through the moving object estimation module. With this mechanism, the motion recognition and pattern recognition processes are integrated, and moving objects can be recognized. A computer simulation is performed on the recognition of a walking human, and the effectiveness of the proposed network is demonstrated.

AB - This paper proposes a neural network for moving object recognition based on the visual system. The proposed network has a structure focusing on the parallel hierarchy of visual information processing and can recognize moving objects. The network is composed of a movement detection module, a moving object estimation module, and a moving object recognition module. The movement detection module uses a neural network which is a model of the motion recognition aspect of vision and recognizes motion. The moving object estimation module uses a hierarchical neural network with the backpropagation (BP) algorithm, and infers moving objects based on the features of the motion. The moving object recognition module uses a multiple-structured neural network which is obtained by improvement of the inhibition mechanism and recognizes moving objects on the basis of shape features. The information is transmitted from the movement detection module to the moving object recognition module through the moving object estimation module. With this mechanism, the motion recognition and pattern recognition processes are integrated, and moving objects can be recognized. A computer simulation is performed on the recognition of a walking human, and the effectiveness of the proposed network is demonstrated.

KW - Motion recognition

KW - Moving object estimation

KW - Pattern recognition

KW - Visual information processing

UR - http://www.scopus.com/inward/record.url?scp=7244262091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=7244262091&partnerID=8YFLogxK

U2 - 10.1002/ecjb.20115

DO - 10.1002/ecjb.20115

M3 - Article

AN - SCOPUS:7244262091

VL - 87

SP - 46

EP - 55

JO - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

SN - 8756-663X

IS - 9

ER -