Human detection and tracking through temporal feature recognition

Fraser K. Coutts; Stephen Marshall; Paul Murray

Human detection and tracking through temporal feature recognition

Fraser K. Coutts, Stephen Marshall, Paul Murray

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

4 Citations (Scopus)

53 Downloads (Pure)

Abstract

The ability to accurately track objects of interest – particularly humans – is of great importance in the fields of security and surveillance. In such scenarios, t he application of accurate, automated human tracking offers benefits over manual supervision. In this paper, recent efforts made to investigate the improvement of automated human detection and tracking techniques through the recognition
of person-specific time-varying signatures in thermal video are detailed. A robust human detection algorithm is developed to aid the initialisation stage of a state-of-the art existing tracking algorithm. In addition, coupled with the spatial tracking methods present in this algorithm, the inclusion of temporal signature recognition in the tracking process is shown to improve human tracking results.

Original language	English
Title of host publication	2014 22nd European Signal Processing Conference (EUSIPCO)
Publisher	IEEE
Pages	2180-2184
Number of pages	5
ISBN (Print)	9780992862619
Publication status	Published - 1 Sept 2014
Event	22nd European Signal Processing Conference - Lisbon Congress Centre, Lisbon, Portugal Duration: 1 Sept 2014 → 5 Sept 2014 Conference number: 2014

Conference

Conference	22nd European Signal Processing Conference
Abbreviated title	EUSIPCO
Country/Territory	Portugal
City	Lisbon
Period	1/09/14 → 5/09/14

Keywords

automated human tracking
thermal video
temporal characteristic recognition
human detection
video signal processing
feature extraction
object detection
object tracking
spatial tracking methods
person specific time varying signatures

Access to Document

Coutts-etal-EUSPICO2014-Human-detection-and-trackingAccepted author manuscript, 2.09 MB

Cite this

@inproceedings{098699a098f14d11b8b11c35e0914df6,

title = "Human detection and tracking through temporal feature recognition",

abstract = "The ability to accurately track objects of interest – particularly humans – is of great importance in the fields of security and surveillance. In such scenarios, t he application of accurate, automated human tracking offers benefits over manual supervision. In this paper, recent efforts made to investigate the improvement of automated human detection and tracking techniques through the recognitionof person-specific time-varying signatures in thermal video are detailed. A robust human detection algorithm is developed to aid the initialisation stage of a state-of-the art existing tracking algorithm. In addition, coupled with the spatial tracking methods present in this algorithm, the inclusion of temporal signature recognition in the tracking process is shown to improve human tracking results.",

keywords = "automated human tracking, thermal video, temporal characteristic recognition, human detection, video signal processing, feature extraction, object detection, object tracking, spatial tracking methods, person specific time varying signatures",

author = "Coutts, {Fraser K.} and Stephen Marshall and Paul Murray",

note = "(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.; 22nd European Signal Processing Conference, EUSIPCO ; Conference date: 01-09-2014 Through 05-09-2014",

year = "2014",

month = sep,

day = "1",

language = "English",

isbn = "9780992862619",

pages = "2180--2184",

booktitle = "2014 22nd European Signal Processing Conference (EUSIPCO)",

publisher = "IEEE",

}

TY - GEN

T1 - Human detection and tracking through temporal feature recognition

AU - Coutts, Fraser K.

AU - Marshall, Stephen

AU - Murray, Paul

N1 - Conference code: 2014

PY - 2014/9/1

Y1 - 2014/9/1

N2 - The ability to accurately track objects of interest – particularly humans – is of great importance in the fields of security and surveillance. In such scenarios, t he application of accurate, automated human tracking offers benefits over manual supervision. In this paper, recent efforts made to investigate the improvement of automated human detection and tracking techniques through the recognitionof person-specific time-varying signatures in thermal video are detailed. A robust human detection algorithm is developed to aid the initialisation stage of a state-of-the art existing tracking algorithm. In addition, coupled with the spatial tracking methods present in this algorithm, the inclusion of temporal signature recognition in the tracking process is shown to improve human tracking results.

AB - The ability to accurately track objects of interest – particularly humans – is of great importance in the fields of security and surveillance. In such scenarios, t he application of accurate, automated human tracking offers benefits over manual supervision. In this paper, recent efforts made to investigate the improvement of automated human detection and tracking techniques through the recognitionof person-specific time-varying signatures in thermal video are detailed. A robust human detection algorithm is developed to aid the initialisation stage of a state-of-the art existing tracking algorithm. In addition, coupled with the spatial tracking methods present in this algorithm, the inclusion of temporal signature recognition in the tracking process is shown to improve human tracking results.

KW - automated human tracking

KW - thermal video

KW - temporal characteristic recognition

KW - human detection

KW - video signal processing

KW - feature extraction

KW - object detection

KW - object tracking

KW - spatial tracking methods

KW - person specific time varying signatures

UR - https://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6952796

M3 - Conference contribution book

SN - 9780992862619

SP - 2180

EP - 2184

BT - 2014 22nd European Signal Processing Conference (EUSIPCO)

PB - IEEE

T2 - 22nd European Signal Processing Conference

Y2 - 1 September 2014 through 5 September 2014

ER -

Human detection and tracking through temporal feature recognition

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this