Fast medium-scale multiperson identification in aerial videos

Mei Chen Yeh, Han Kuen Chiu, Jia Shung Wang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Vision systems for unmanned aerial vehicles (UAVs) have been gaining increasing attention for surveillance and civil applications. However, aerial platforms create new challenges for several vision tasks (e.g., human tracking and identification) because UAV-mounted cameras undergo large vibration movements and capture unstable videos. Furthermore, most existing machine vision approaches use the fine details of a human figure, which are unavailable in low-quality aerial images. We propose a new blob-matching approach for human identification in aerial videos in which the identity of a human blob is estimated using an adaptive reference set of previously identified people. A target can be quickly located by matching only the target and a carefully selected candidate set. The experimental results obtained using several challenging aerial videos validated the effectiveness and computational efficiency of the proposed method.

Original languageEnglish
Pages (from-to)16117-16133
Number of pages17
JournalMultimedia Tools and Applications
Volume75
Issue number23
DOIs
Publication statusPublished - 2016 Dec 1

Fingerprint

Antennas
Unmanned aerial vehicles (UAV)
Computational efficiency
Computer vision
Cameras

Keywords

  • Aerial video
  • Human identity recognition
  • Image matching
  • Video surveillance

ASJC Scopus subject areas

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Fast medium-scale multiperson identification in aerial videos. / Yeh, Mei Chen; Chiu, Han Kuen; Wang, Jia Shung.

In: Multimedia Tools and Applications, Vol. 75, No. 23, 01.12.2016, p. 16117-16133.

Research output: Contribution to journalArticle

Yeh, Mei Chen ; Chiu, Han Kuen ; Wang, Jia Shung. / Fast medium-scale multiperson identification in aerial videos. In: Multimedia Tools and Applications. 2016 ; Vol. 75, No. 23. pp. 16117-16133.
@article{c83ab3b17bf148d2b68c725a73624bbb,
title = "Fast medium-scale multiperson identification in aerial videos",
abstract = "Vision systems for unmanned aerial vehicles (UAVs) have been gaining increasing attention for surveillance and civil applications. However, aerial platforms create new challenges for several vision tasks (e.g., human tracking and identification) because UAV-mounted cameras undergo large vibration movements and capture unstable videos. Furthermore, most existing machine vision approaches use the fine details of a human figure, which are unavailable in low-quality aerial images. We propose a new blob-matching approach for human identification in aerial videos in which the identity of a human blob is estimated using an adaptive reference set of previously identified people. A target can be quickly located by matching only the target and a carefully selected candidate set. The experimental results obtained using several challenging aerial videos validated the effectiveness and computational efficiency of the proposed method.",
keywords = "Aerial video, Human identity recognition, Image matching, Video surveillance",
author = "Yeh, {Mei Chen} and Chiu, {Han Kuen} and Wang, {Jia Shung}",
year = "2016",
month = "12",
day = "1",
doi = "10.1007/s11042-015-2921-x",
language = "English",
volume = "75",
pages = "16117--16133",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "23",

}

TY - JOUR

T1 - Fast medium-scale multiperson identification in aerial videos

AU - Yeh, Mei Chen

AU - Chiu, Han Kuen

AU - Wang, Jia Shung

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Vision systems for unmanned aerial vehicles (UAVs) have been gaining increasing attention for surveillance and civil applications. However, aerial platforms create new challenges for several vision tasks (e.g., human tracking and identification) because UAV-mounted cameras undergo large vibration movements and capture unstable videos. Furthermore, most existing machine vision approaches use the fine details of a human figure, which are unavailable in low-quality aerial images. We propose a new blob-matching approach for human identification in aerial videos in which the identity of a human blob is estimated using an adaptive reference set of previously identified people. A target can be quickly located by matching only the target and a carefully selected candidate set. The experimental results obtained using several challenging aerial videos validated the effectiveness and computational efficiency of the proposed method.

AB - Vision systems for unmanned aerial vehicles (UAVs) have been gaining increasing attention for surveillance and civil applications. However, aerial platforms create new challenges for several vision tasks (e.g., human tracking and identification) because UAV-mounted cameras undergo large vibration movements and capture unstable videos. Furthermore, most existing machine vision approaches use the fine details of a human figure, which are unavailable in low-quality aerial images. We propose a new blob-matching approach for human identification in aerial videos in which the identity of a human blob is estimated using an adaptive reference set of previously identified people. A target can be quickly located by matching only the target and a carefully selected candidate set. The experimental results obtained using several challenging aerial videos validated the effectiveness and computational efficiency of the proposed method.

KW - Aerial video

KW - Human identity recognition

KW - Image matching

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=84940876817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940876817&partnerID=8YFLogxK

U2 - 10.1007/s11042-015-2921-x

DO - 10.1007/s11042-015-2921-x

M3 - Article

AN - SCOPUS:84940876817

VL - 75

SP - 16117

EP - 16133

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 23

ER -