Gait identification using invisible shadows: Robustness to appearance changes

Yumi Iwashita, Ryo Kurazume, Adrian Stoica

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

5 Citations (Scopus)

Abstract

This paper presents a person identification technique that uses information from person's shadow, and is robust to appearance changes caused by variations of clothes and carried objects. The technique uses invisible lights and resulting shadows and has advantages from undetected sensing. The shadows on the ground obtained through illumination by multiple lights can be considered as silhouettes captured by multiple virtual cameras placed at light positions. Thus, a single camera, e.g. in the ceiling, is able to obtain multiple silhouettes, equivalent to a multi-camera system. If the person's appearance changes compared to the training cases in the database, e.g. by wearing different clothes or carrying a/another bag, then the identification performance gets worse. To deal with this problem, we introduce a new shadow-based identification technique robust to appearance changes. Firstly, we divide each shadow area into several parts, and estimate the discrimination capability for each part based on gait features between gallery datasets and probe dataset. Next, according to the estimated capability, we adaptively control the priorities of these parts in the person identification method. We constructed a new shadow database with a variety of clothes and bags, and carried out successful experiments to verify the effectiveness of the proposed technique.

Original languageEnglish
Title of host publicationProceedings - 2014 International Conference on Emerging Security Technologies, EST 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages34-39
Number of pages6
ISBN (Electronic)9781479970070
DOIs
Publication statusPublished - Dec 11 2014
Event5th International Conference on Emerging Security Technologies, EST 2014 - Alcala de Henares, Spain
Duration: Sep 10 2014Sep 12 2014

Publication series

NameProceedings - 2014 International Conference on Emerging Security Technologies, EST 2014

Other

Other5th International Conference on Emerging Security Technologies, EST 2014
CountrySpain
CityAlcala de Henares
Period9/10/149/12/14

Fingerprint

Cameras
Information use
Ceilings
Lighting
Experiments

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Control and Systems Engineering
  • Artificial Intelligence
  • Safety, Risk, Reliability and Quality

Cite this

Iwashita, Y., Kurazume, R., & Stoica, A. (2014). Gait identification using invisible shadows: Robustness to appearance changes. In Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014 (pp. 34-39). [6982771] (Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EST.2014.18

Gait identification using invisible shadows : Robustness to appearance changes. / Iwashita, Yumi; Kurazume, Ryo; Stoica, Adrian.

Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 34-39 6982771 (Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014).

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

Iwashita, Y, Kurazume, R & Stoica, A 2014, Gait identification using invisible shadows: Robustness to appearance changes. in Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014., 6982771, Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014, Institute of Electrical and Electronics Engineers Inc., pp. 34-39, 5th International Conference on Emerging Security Technologies, EST 2014, Alcala de Henares, Spain, 9/10/14. https://doi.org/10.1109/EST.2014.18
Iwashita Y, Kurazume R, Stoica A. Gait identification using invisible shadows: Robustness to appearance changes. In Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 34-39. 6982771. (Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014). https://doi.org/10.1109/EST.2014.18
Iwashita, Yumi ; Kurazume, Ryo ; Stoica, Adrian. / Gait identification using invisible shadows : Robustness to appearance changes. Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 34-39 (Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014).
@inproceedings{ab16cf814cb64b0e9948a819dfc0c599,
title = "Gait identification using invisible shadows: Robustness to appearance changes",
abstract = "This paper presents a person identification technique that uses information from person's shadow, and is robust to appearance changes caused by variations of clothes and carried objects. The technique uses invisible lights and resulting shadows and has advantages from undetected sensing. The shadows on the ground obtained through illumination by multiple lights can be considered as silhouettes captured by multiple virtual cameras placed at light positions. Thus, a single camera, e.g. in the ceiling, is able to obtain multiple silhouettes, equivalent to a multi-camera system. If the person's appearance changes compared to the training cases in the database, e.g. by wearing different clothes or carrying a/another bag, then the identification performance gets worse. To deal with this problem, we introduce a new shadow-based identification technique robust to appearance changes. Firstly, we divide each shadow area into several parts, and estimate the discrimination capability for each part based on gait features between gallery datasets and probe dataset. Next, according to the estimated capability, we adaptively control the priorities of these parts in the person identification method. We constructed a new shadow database with a variety of clothes and bags, and carried out successful experiments to verify the effectiveness of the proposed technique.",
author = "Yumi Iwashita and Ryo Kurazume and Adrian Stoica",
year = "2014",
month = "12",
day = "11",
doi = "10.1109/EST.2014.18",
language = "English",
series = "Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "34--39",
booktitle = "Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014",
address = "United States",

}

TY - GEN

T1 - Gait identification using invisible shadows

T2 - Robustness to appearance changes

AU - Iwashita, Yumi

AU - Kurazume, Ryo

AU - Stoica, Adrian

PY - 2014/12/11

Y1 - 2014/12/11

N2 - This paper presents a person identification technique that uses information from person's shadow, and is robust to appearance changes caused by variations of clothes and carried objects. The technique uses invisible lights and resulting shadows and has advantages from undetected sensing. The shadows on the ground obtained through illumination by multiple lights can be considered as silhouettes captured by multiple virtual cameras placed at light positions. Thus, a single camera, e.g. in the ceiling, is able to obtain multiple silhouettes, equivalent to a multi-camera system. If the person's appearance changes compared to the training cases in the database, e.g. by wearing different clothes or carrying a/another bag, then the identification performance gets worse. To deal with this problem, we introduce a new shadow-based identification technique robust to appearance changes. Firstly, we divide each shadow area into several parts, and estimate the discrimination capability for each part based on gait features between gallery datasets and probe dataset. Next, according to the estimated capability, we adaptively control the priorities of these parts in the person identification method. We constructed a new shadow database with a variety of clothes and bags, and carried out successful experiments to verify the effectiveness of the proposed technique.

AB - This paper presents a person identification technique that uses information from person's shadow, and is robust to appearance changes caused by variations of clothes and carried objects. The technique uses invisible lights and resulting shadows and has advantages from undetected sensing. The shadows on the ground obtained through illumination by multiple lights can be considered as silhouettes captured by multiple virtual cameras placed at light positions. Thus, a single camera, e.g. in the ceiling, is able to obtain multiple silhouettes, equivalent to a multi-camera system. If the person's appearance changes compared to the training cases in the database, e.g. by wearing different clothes or carrying a/another bag, then the identification performance gets worse. To deal with this problem, we introduce a new shadow-based identification technique robust to appearance changes. Firstly, we divide each shadow area into several parts, and estimate the discrimination capability for each part based on gait features between gallery datasets and probe dataset. Next, according to the estimated capability, we adaptively control the priorities of these parts in the person identification method. We constructed a new shadow database with a variety of clothes and bags, and carried out successful experiments to verify the effectiveness of the proposed technique.

UR - http://www.scopus.com/inward/record.url?scp=84921293003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921293003&partnerID=8YFLogxK

U2 - 10.1109/EST.2014.18

DO - 10.1109/EST.2014.18

M3 - Conference contribution

AN - SCOPUS:84921293003

T3 - Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014

SP - 34

EP - 39

BT - Proceedings - 2014 International Conference on Emerging Security Technologies, EST 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -