Detecting change in graffiti using a hybrid framework (2024)

Wild, B., Verhoeven, G. J. J., Muszyński, R., & Pfeifer, N. (2024). Detecting change in graffiti using a hybrid framework. The Photogrammetric Record, Early view, [phor.12496]. https://doi.org/10.1111/phor.12496

Wild, Benjamin ; Verhoeven, Geert Julien Joanna ; Muszyński, Rafał et al. / Detecting change in graffiti using a hybrid framework. In: The Photogrammetric Record. 2024 ; Vol. Early view.

@article{7bb58b4cbb8547f9957bc20995a563da,

title = "Detecting change in graffiti using a hybrid framework",

abstract = "Graffiti, by their very nature, are ephemeral, sometimes even vanishing before creators finish them. This transience is part of graffiti's allure yet signifies the continuous loss of this often disputed form of cultural heritage. To counteract this, graffiti documentation efforts have steadily increased over the past decade. One of the primary challenges in any documentation endeavour is identifying and recording new creations. Image-based change detection can greatly help in this process, effectuating more comprehensive documentation, less biased digital safeguarding and improved understanding of graffiti. This paper introduces a novel and largely automated image-based graffiti change detection method. The methodology uses an incremental structure-from-motion approach and synthetic cameras to generate co-registered graffiti images from different areas. These synthetic images are fed into a hybrid change detection pipeline combining a new pixel-based change detection method with a feature-based one. The approach was tested on a large and publicly available reference dataset captured along the Donaukanal (Eng. Danube Canal), one of Vienna's graffiti hotspots. With a precision of 87% and a recall of 77%, the results reveal that the proposed change detection workflow can indicate newly added graffiti in a monitored graffiti-scape, thus supporting a more comprehensive graffiti documentation.",

keywords = "3D, Austria, Change detection, Donaukanal, Feature extraction, Graffiti, IBM (Image-Based Modelling), Illumination invariant, INDIGO, MVS (Multi View Stereo), SfM (Structure from Motion), Vienna, digital imaging, cultural heritage, colour difference, 3D modelling, edge-aware smoothing, change detection, graffiti, feature matching",

author = "Benjamin Wild and Verhoeven, {Geert Julien Joanna} and Rafa{\l} Muszy{\'n}ski and Norbert Pfeifer",

year = "2024",

month = apr,

day = "24",

doi = "10.1111/phor.12496",

language = "English",

volume = "Early view",

journal = "The Photogrammetric Record",

issn = "0031-868X",

publisher = "Blackwell",

}

Wild, B, Verhoeven, GJJ, Muszyński, R & Pfeifer, N 2024, 'Detecting change in graffiti using a hybrid framework', The Photogrammetric Record, vol. Early view, phor.12496. https://doi.org/10.1111/phor.12496

Detecting change in graffiti using a hybrid framework. / Wild, Benjamin (Corresponding author); Verhoeven, Geert Julien Joanna; Muszyński, Rafał et al.

In: The Photogrammetric Record, Vol. Early view, phor.12496, 24.04.2024.

Publications: Contribution to journal › Article › Peer Reviewed

TY - JOUR

T1 - Detecting change in graffiti using a hybrid framework

AU - Wild, Benjamin

AU - Verhoeven, Geert Julien Joanna

AU - Muszyński, Rafał

AU - Pfeifer, Norbert

PY - 2024/4/24

Y1 - 2024/4/24

N2 - Graffiti, by their very nature, are ephemeral, sometimes even vanishing before creators finish them. This transience is part of graffiti's allure yet signifies the continuous loss of this often disputed form of cultural heritage. To counteract this, graffiti documentation efforts have steadily increased over the past decade. One of the primary challenges in any documentation endeavour is identifying and recording new creations. Image-based change detection can greatly help in this process, effectuating more comprehensive documentation, less biased digital safeguarding and improved understanding of graffiti. This paper introduces a novel and largely automated image-based graffiti change detection method. The methodology uses an incremental structure-from-motion approach and synthetic cameras to generate co-registered graffiti images from different areas. These synthetic images are fed into a hybrid change detection pipeline combining a new pixel-based change detection method with a feature-based one. The approach was tested on a large and publicly available reference dataset captured along the Donaukanal (Eng. Danube Canal), one of Vienna's graffiti hotspots. With a precision of 87% and a recall of 77%, the results reveal that the proposed change detection workflow can indicate newly added graffiti in a monitored graffiti-scape, thus supporting a more comprehensive graffiti documentation.

AB - Graffiti, by their very nature, are ephemeral, sometimes even vanishing before creators finish them. This transience is part of graffiti's allure yet signifies the continuous loss of this often disputed form of cultural heritage. To counteract this, graffiti documentation efforts have steadily increased over the past decade. One of the primary challenges in any documentation endeavour is identifying and recording new creations. Image-based change detection can greatly help in this process, effectuating more comprehensive documentation, less biased digital safeguarding and improved understanding of graffiti. This paper introduces a novel and largely automated image-based graffiti change detection method. The methodology uses an incremental structure-from-motion approach and synthetic cameras to generate co-registered graffiti images from different areas. These synthetic images are fed into a hybrid change detection pipeline combining a new pixel-based change detection method with a feature-based one. The approach was tested on a large and publicly available reference dataset captured along the Donaukanal (Eng. Danube Canal), one of Vienna's graffiti hotspots. With a precision of 87% and a recall of 77%, the results reveal that the proposed change detection workflow can indicate newly added graffiti in a monitored graffiti-scape, thus supporting a more comprehensive graffiti documentation.

KW - 3D

KW - Austria

KW - Change detection

KW - Donaukanal

KW - Feature extraction

KW - Graffiti

KW - IBM (Image-Based Modelling)

KW - Illumination invariant

KW - INDIGO

KW - MVS (Multi View Stereo)

KW - SfM (Structure from Motion)

KW - Vienna

KW - digital imaging

KW - cultural heritage

KW - colour difference

KW - 3D modelling

KW - edge-aware smoothing

KW - change detection

KW - graffiti

KW - feature matching

UR - http://www.scopus.com/inward/record.url?scp=85191170546&partnerID=8YFLogxK

U2 - 10.1111/phor.12496

DO - 10.1111/phor.12496

M3 - Article

VL - Early view

JO - The Photogrammetric Record

JF - The Photogrammetric Record

SN - 0031-868X

M1 - phor.12496

ER -

Wild B, Verhoeven GJJ, Muszyński R, Pfeifer N. Detecting change in graffiti using a hybrid framework. The Photogrammetric Record. 2024 Apr 24;Early view:phor.12496. Epub 2024 Apr 24. doi: 10.1111/phor.12496