Toward real-time extraction of pedestrian contexts with stereo camera

Kei Suzuki, Kazunori Takashio, Hideyuki Tokuda, Masaki Wada, Yusuke Matsuki, Kazunori Umeda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We extract the mood of disquiet on street corners in real-time with stereo video camera systems. Last year we proposed a novel stereo measurement algorithm to detect moving people, which was focusing on moving region in video data. In this paper, we report our prototype of probabilistic inference engine that can detect contexts of individual pedestrian and groups of pedestrians. We demonstrated that the real-time extraction of higher-level pedestrian contexts using the Bayesian Network model was effective for extracting several pedestrians' context.

Original languageEnglish
Title of host publicationProceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems
Pages115-118
Number of pages4
DOIs
Publication statusPublished - 2008
EventINSS 2008 - 5th International Conference on Networked Sensing Systems - Kanazawa, Japan
Duration: 2008 Jun 172008 Jun 19

Other

OtherINSS 2008 - 5th International Conference on Networked Sensing Systems
CountryJapan
CityKanazawa
Period08/6/1708/6/19

Fingerprint

Inference engines
Bayesian networks
Video cameras
Cameras

Keywords

  • Bayesian network model
  • Distributed camera system
  • Pedestrian context
  • Realtime context analysis
  • Stereo vision

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Suzuki, K., Takashio, K., Tokuda, H., Wada, M., Matsuki, Y., & Umeda, K. (2008). Toward real-time extraction of pedestrian contexts with stereo camera. In Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems (pp. 115-118). [4610910] https://doi.org/10.1109/INSS.2008.4610910

Toward real-time extraction of pedestrian contexts with stereo camera. / Suzuki, Kei; Takashio, Kazunori; Tokuda, Hideyuki; Wada, Masaki; Matsuki, Yusuke; Umeda, Kazunori.

Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems. 2008. p. 115-118 4610910.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Suzuki, K, Takashio, K, Tokuda, H, Wada, M, Matsuki, Y & Umeda, K 2008, Toward real-time extraction of pedestrian contexts with stereo camera. in Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems., 4610910, pp. 115-118, INSS 2008 - 5th International Conference on Networked Sensing Systems, Kanazawa, Japan, 08/6/17. https://doi.org/10.1109/INSS.2008.4610910
Suzuki K, Takashio K, Tokuda H, Wada M, Matsuki Y, Umeda K. Toward real-time extraction of pedestrian contexts with stereo camera. In Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems. 2008. p. 115-118. 4610910 https://doi.org/10.1109/INSS.2008.4610910
Suzuki, Kei ; Takashio, Kazunori ; Tokuda, Hideyuki ; Wada, Masaki ; Matsuki, Yusuke ; Umeda, Kazunori. / Toward real-time extraction of pedestrian contexts with stereo camera. Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems. 2008. pp. 115-118
@inproceedings{ec50f56616244752b8f38ad31ee8f3a6,
title = "Toward real-time extraction of pedestrian contexts with stereo camera",
abstract = "We extract the mood of disquiet on street corners in real-time with stereo video camera systems. Last year we proposed a novel stereo measurement algorithm to detect moving people, which was focusing on moving region in video data. In this paper, we report our prototype of probabilistic inference engine that can detect contexts of individual pedestrian and groups of pedestrians. We demonstrated that the real-time extraction of higher-level pedestrian contexts using the Bayesian Network model was effective for extracting several pedestrians' context.",
keywords = "Bayesian network model, Distributed camera system, Pedestrian context, Realtime context analysis, Stereo vision",
author = "Kei Suzuki and Kazunori Takashio and Hideyuki Tokuda and Masaki Wada and Yusuke Matsuki and Kazunori Umeda",
year = "2008",
doi = "10.1109/INSS.2008.4610910",
language = "English",
isbn = "9784907764319",
pages = "115--118",
booktitle = "Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems",

}

TY - GEN

T1 - Toward real-time extraction of pedestrian contexts with stereo camera

AU - Suzuki, Kei

AU - Takashio, Kazunori

AU - Tokuda, Hideyuki

AU - Wada, Masaki

AU - Matsuki, Yusuke

AU - Umeda, Kazunori

PY - 2008

Y1 - 2008

N2 - We extract the mood of disquiet on street corners in real-time with stereo video camera systems. Last year we proposed a novel stereo measurement algorithm to detect moving people, which was focusing on moving region in video data. In this paper, we report our prototype of probabilistic inference engine that can detect contexts of individual pedestrian and groups of pedestrians. We demonstrated that the real-time extraction of higher-level pedestrian contexts using the Bayesian Network model was effective for extracting several pedestrians' context.

AB - We extract the mood of disquiet on street corners in real-time with stereo video camera systems. Last year we proposed a novel stereo measurement algorithm to detect moving people, which was focusing on moving region in video data. In this paper, we report our prototype of probabilistic inference engine that can detect contexts of individual pedestrian and groups of pedestrians. We demonstrated that the real-time extraction of higher-level pedestrian contexts using the Bayesian Network model was effective for extracting several pedestrians' context.

KW - Bayesian network model

KW - Distributed camera system

KW - Pedestrian context

KW - Realtime context analysis

KW - Stereo vision

UR - http://www.scopus.com/inward/record.url?scp=53149121343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=53149121343&partnerID=8YFLogxK

U2 - 10.1109/INSS.2008.4610910

DO - 10.1109/INSS.2008.4610910

M3 - Conference contribution

SN - 9784907764319

SP - 115

EP - 118

BT - Proceedings of INSS 2008 - 5th International Conference on Networked Sensing Systems

ER -