Face tracking and recognition at a distance: A coaxial and concentric ptz camera system

Unsang Park, Hyun Cheol Choi, Anil K. Jain, Seong Whan Lee

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Face recognition has been regarded as an effective method for subject identification at a distance because of its covert and remote sensing capability. However, face images have a low resolution when they are captured at a distance (say, larger than 5 meters) thereby degrading the face matching performance. To address this problem, we propose an imaging system consisting of static and pan-tilt-zoom (PTZ) cameras to acquire high resolution face images up to a distance of 12 meters. We propose a novel coaxial-concentric camera configuration between the static and PTZ cameras to achieve the distance invariance property using a simple calibration scheme. We also use a linear prediction model and camera motion control to mitigate delays in image processing and mechanical camera motion. Our imaging system was used to track 50 different subjects and their faces at distances ranging from 6 to 12 meters. The matching scenario consisted of these 50 subjects as probe and additional 10 000 subjects as gallery. Rank-1 identification accuracy of 91.5% was achieved compared to 0% rank-1 accuracy of the conventional camera system using a state-of-the-art matcher. The proposed camera system can operate at a larger distance (up to 50 meters) by replacing the static camera with a PTZ camera to detect a subject at a larger distance and control the second PTZ camera to capture the high-resolution face image.

Original languageEnglish
Article number6512016
Pages (from-to)1665-1677
Number of pages13
JournalIEEE Transactions on Information Forensics and Security
Volume8
Issue number10
DOIs
Publication statusPublished - 2013 Sep 30

Fingerprint

Cameras
Imaging systems
Motion control
Face recognition
Invariance
Remote sensing
Image processing
Calibration

Keywords

  • coaxial
  • concentric
  • Face recognition at a distance
  • PTZ camera
  • tracking

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Cite this

Face tracking and recognition at a distance : A coaxial and concentric ptz camera system. / Park, Unsang; Choi, Hyun Cheol; Jain, Anil K.; Lee, Seong Whan.

In: IEEE Transactions on Information Forensics and Security, Vol. 8, No. 10, 6512016, 30.09.2013, p. 1665-1677.

Research output: Contribution to journalArticle

@article{82fffa8800244eb981ef19699a3ec9a2,
title = "Face tracking and recognition at a distance: A coaxial and concentric ptz camera system",
abstract = "Face recognition has been regarded as an effective method for subject identification at a distance because of its covert and remote sensing capability. However, face images have a low resolution when they are captured at a distance (say, larger than 5 meters) thereby degrading the face matching performance. To address this problem, we propose an imaging system consisting of static and pan-tilt-zoom (PTZ) cameras to acquire high resolution face images up to a distance of 12 meters. We propose a novel coaxial-concentric camera configuration between the static and PTZ cameras to achieve the distance invariance property using a simple calibration scheme. We also use a linear prediction model and camera motion control to mitigate delays in image processing and mechanical camera motion. Our imaging system was used to track 50 different subjects and their faces at distances ranging from 6 to 12 meters. The matching scenario consisted of these 50 subjects as probe and additional 10 000 subjects as gallery. Rank-1 identification accuracy of 91.5{\%} was achieved compared to 0{\%} rank-1 accuracy of the conventional camera system using a state-of-the-art matcher. The proposed camera system can operate at a larger distance (up to 50 meters) by replacing the static camera with a PTZ camera to detect a subject at a larger distance and control the second PTZ camera to capture the high-resolution face image.",
keywords = "coaxial, concentric, Face recognition at a distance, PTZ camera, tracking",
author = "Unsang Park and Choi, {Hyun Cheol} and Jain, {Anil K.} and Lee, {Seong Whan}",
year = "2013",
month = "9",
day = "30",
doi = "10.1109/TIFS.2013.2261061",
language = "English",
volume = "8",
pages = "1665--1677",
journal = "IEEE Transactions on Information Forensics and Security",
issn = "1556-6013",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Face tracking and recognition at a distance

T2 - A coaxial and concentric ptz camera system

AU - Park, Unsang

AU - Choi, Hyun Cheol

AU - Jain, Anil K.

AU - Lee, Seong Whan

PY - 2013/9/30

Y1 - 2013/9/30

N2 - Face recognition has been regarded as an effective method for subject identification at a distance because of its covert and remote sensing capability. However, face images have a low resolution when they are captured at a distance (say, larger than 5 meters) thereby degrading the face matching performance. To address this problem, we propose an imaging system consisting of static and pan-tilt-zoom (PTZ) cameras to acquire high resolution face images up to a distance of 12 meters. We propose a novel coaxial-concentric camera configuration between the static and PTZ cameras to achieve the distance invariance property using a simple calibration scheme. We also use a linear prediction model and camera motion control to mitigate delays in image processing and mechanical camera motion. Our imaging system was used to track 50 different subjects and their faces at distances ranging from 6 to 12 meters. The matching scenario consisted of these 50 subjects as probe and additional 10 000 subjects as gallery. Rank-1 identification accuracy of 91.5% was achieved compared to 0% rank-1 accuracy of the conventional camera system using a state-of-the-art matcher. The proposed camera system can operate at a larger distance (up to 50 meters) by replacing the static camera with a PTZ camera to detect a subject at a larger distance and control the second PTZ camera to capture the high-resolution face image.

AB - Face recognition has been regarded as an effective method for subject identification at a distance because of its covert and remote sensing capability. However, face images have a low resolution when they are captured at a distance (say, larger than 5 meters) thereby degrading the face matching performance. To address this problem, we propose an imaging system consisting of static and pan-tilt-zoom (PTZ) cameras to acquire high resolution face images up to a distance of 12 meters. We propose a novel coaxial-concentric camera configuration between the static and PTZ cameras to achieve the distance invariance property using a simple calibration scheme. We also use a linear prediction model and camera motion control to mitigate delays in image processing and mechanical camera motion. Our imaging system was used to track 50 different subjects and their faces at distances ranging from 6 to 12 meters. The matching scenario consisted of these 50 subjects as probe and additional 10 000 subjects as gallery. Rank-1 identification accuracy of 91.5% was achieved compared to 0% rank-1 accuracy of the conventional camera system using a state-of-the-art matcher. The proposed camera system can operate at a larger distance (up to 50 meters) by replacing the static camera with a PTZ camera to detect a subject at a larger distance and control the second PTZ camera to capture the high-resolution face image.

KW - coaxial

KW - concentric

KW - Face recognition at a distance

KW - PTZ camera

KW - tracking

UR - http://www.scopus.com/inward/record.url?scp=84884548782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884548782&partnerID=8YFLogxK

U2 - 10.1109/TIFS.2013.2261061

DO - 10.1109/TIFS.2013.2261061

M3 - Article

AN - SCOPUS:84884548782

VL - 8

SP - 1665

EP - 1677

JO - IEEE Transactions on Information Forensics and Security

JF - IEEE Transactions on Information Forensics and Security

SN - 1556-6013

IS - 10

M1 - 6512016

ER -