Adaptive human motion tracking using non-synchronous multiple viewpoint observations

Akira Utsumi, Howard Yang, Jun Ohya

Research output: Chapter in Book/Report/Conference proceedingChapter

7 Citations (Scopus)

Abstract

In this paper, we propose an adaptive human tracking system with non-synchronous multiple observations. Our system consists of three types of processes, discovering node for detecting newly appeared person, tracking node for tracking each target person, and observation node for processing one viewpoint (camera) images. We have multiple observation nodes and each node works fully independently. The tracking node integrates absented information based on reliability evaluation. Both observation conditions (number of cameras, relative distance between a human and cameras, extent of occlusion, etc.) and human motion states (walking, standing, sitting) are considered in the evaluation. Matching between tracking models and observed image features are performed in each observation node based on the position, size and color similarities of each 2D image. Due to the non-synchronous property, this system is highly scalable for increasing the detection area and number of observing nodes. Experimental results for some indoor scenes are also described.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages607-610
Number of pages4
Volume15
Edition4
Publication statusPublished - 2000
Externally publishedYes

Fingerprint

Cameras
Target tracking
Color
Processing

ASJC Scopus subject areas

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

Cite this

Utsumi, A., Yang, H., & Ohya, J. (2000). Adaptive human motion tracking using non-synchronous multiple viewpoint observations. In Proceedings - International Conference on Pattern Recognition (4 ed., Vol. 15, pp. 607-610)

Adaptive human motion tracking using non-synchronous multiple viewpoint observations. / Utsumi, Akira; Yang, Howard; Ohya, Jun.

Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. p. 607-610.

Research output: Chapter in Book/Report/Conference proceedingChapter

Utsumi, A, Yang, H & Ohya, J 2000, Adaptive human motion tracking using non-synchronous multiple viewpoint observations. in Proceedings - International Conference on Pattern Recognition. 4 edn, vol. 15, pp. 607-610.
Utsumi A, Yang H, Ohya J. Adaptive human motion tracking using non-synchronous multiple viewpoint observations. In Proceedings - International Conference on Pattern Recognition. 4 ed. Vol. 15. 2000. p. 607-610
Utsumi, Akira ; Yang, Howard ; Ohya, Jun. / Adaptive human motion tracking using non-synchronous multiple viewpoint observations. Proceedings - International Conference on Pattern Recognition. Vol. 15 4. ed. 2000. pp. 607-610
@inbook{97a06d509b1b4e70be7ea0dc8d707aea,
title = "Adaptive human motion tracking using non-synchronous multiple viewpoint observations",
abstract = "In this paper, we propose an adaptive human tracking system with non-synchronous multiple observations. Our system consists of three types of processes, discovering node for detecting newly appeared person, tracking node for tracking each target person, and observation node for processing one viewpoint (camera) images. We have multiple observation nodes and each node works fully independently. The tracking node integrates absented information based on reliability evaluation. Both observation conditions (number of cameras, relative distance between a human and cameras, extent of occlusion, etc.) and human motion states (walking, standing, sitting) are considered in the evaluation. Matching between tracking models and observed image features are performed in each observation node based on the position, size and color similarities of each 2D image. Due to the non-synchronous property, this system is highly scalable for increasing the detection area and number of observing nodes. Experimental results for some indoor scenes are also described.",
author = "Akira Utsumi and Howard Yang and Jun Ohya",
year = "2000",
language = "English",
volume = "15",
pages = "607--610",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "4",

}

TY - CHAP

T1 - Adaptive human motion tracking using non-synchronous multiple viewpoint observations

AU - Utsumi, Akira

AU - Yang, Howard

AU - Ohya, Jun

PY - 2000

Y1 - 2000

N2 - In this paper, we propose an adaptive human tracking system with non-synchronous multiple observations. Our system consists of three types of processes, discovering node for detecting newly appeared person, tracking node for tracking each target person, and observation node for processing one viewpoint (camera) images. We have multiple observation nodes and each node works fully independently. The tracking node integrates absented information based on reliability evaluation. Both observation conditions (number of cameras, relative distance between a human and cameras, extent of occlusion, etc.) and human motion states (walking, standing, sitting) are considered in the evaluation. Matching between tracking models and observed image features are performed in each observation node based on the position, size and color similarities of each 2D image. Due to the non-synchronous property, this system is highly scalable for increasing the detection area and number of observing nodes. Experimental results for some indoor scenes are also described.

AB - In this paper, we propose an adaptive human tracking system with non-synchronous multiple observations. Our system consists of three types of processes, discovering node for detecting newly appeared person, tracking node for tracking each target person, and observation node for processing one viewpoint (camera) images. We have multiple observation nodes and each node works fully independently. The tracking node integrates absented information based on reliability evaluation. Both observation conditions (number of cameras, relative distance between a human and cameras, extent of occlusion, etc.) and human motion states (walking, standing, sitting) are considered in the evaluation. Matching between tracking models and observed image features are performed in each observation node based on the position, size and color similarities of each 2D image. Due to the non-synchronous property, this system is highly scalable for increasing the detection area and number of observing nodes. Experimental results for some indoor scenes are also described.

UR - http://www.scopus.com/inward/record.url?scp=10244252236&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10244252236&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:10244252236

VL - 15

SP - 607

EP - 610

BT - Proceedings - International Conference on Pattern Recognition

ER -