Human height estimation from highly distorted surveillance image
Authors
Tosti, Francesco
Nardinocchi, Carla
Ciampini, Claudio
Marsella, Maria
Lopes, Pierpaolo
Giuliani, Samuele
Author (Corporation)
Publication date
01.10.2021
Typ of student thesis
Course of study
Collections
Type
01A - Journal article
Editors
Editor (Corporation)
Supervisor
Parent work
Journal of Forensic Sciences
Special issue
DOI of the original publication
Link
Series
Series number
Volume
67
Issue / Number
1
Pages / Duration
332-344
Patent number
Publisher / Publishing institution
Wiley
Place of publication / Event location
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
Video surveillance camera (VSC) is an important source of information during inves-
tigations especially if used as a tool for the extraction of verified and reliable foren-
sic measurements. In this study, some aspects of human height extraction from VSC
video frames are analyzed with the aim of identifying and mitigating error sources
that can strongly affect the measurement. More specifically, those introduced by lens
distortion are present in wide-field-of-view lens such as VSCs. A weak model, which
is not able to properly describe and correct the lens distortion, could introduce sys-
tematic errors. This study focuses on the aspect of camera calibration to verify human
height extraction by Amped FIVE software, which is adopted by the Forensic science
laboratories of Carabinieri Force (RaCIS), Italy. A stable and reliable approach of cam-
era calibration is needed since investigators have to deal with different cameras while
inspecting the crime scene. The performance of the software in correcting distorted
images is compared with a technique of single view self-calibration. Both approaches
were applied to several frames acquired by a fish-eye camera and then measuring
the height of five different people. Moreover, two actual cases, both characterized
by common low-resolution and distorted images, were also analyzed. The height of
four known persons was measured and used as reference value for validation. Results
show no significant difference between the two calibration approaches working with
fish-eye camera in test field, while evidence of differences was found in the measure-
ment on the actual cases.
Keywords
Camera calibration, Height measurements, Image distortion, Photogrammetry, Space resection, Terrestrial laser scanner, Vanishing line and point
Subject (DDC)
600 - Technik, Medizin, angewandte Wissenschaften
Event
Exhibition start date
Exhibition end date
Conference start date
Conference end date
Date of the last check
ISBN
ISSN
0022-1198
1556-4029
1556-4029
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Unpublished
Review
Peer review of the complete publication
Open access category
Hybrid
Citation
TOSTI, Francesco, Carla NARDINOCCHI, Claudio CIAMPINI, Maria MARSELLA, Pierpaolo LOPES, Samuele GIULIANI und Wissam WAHBEH, 2021. Human height estimation from highly distorted surveillance image. Journal of Forensic Sciences. 1 Oktober 2021. Bd. 67, Nr. 1, S. 332–344. DOI 10.26041/fhnw-4160. Verfügbar unter: https://doi.org/10.26041/fhnw-4160