Preliminary Study of a Non-Direct Generative Image Anonymization Pipeline for Anomaly Detection

dc.contributor.authorNikolov, Ivan
dc.date.accessioned2025-07-30T08:03:31Z
dc.date.available2025-07-30T08:03:31Z
dc.date.issued2025
dc.description.abstract-translatedWith growing General Data Protection Regulation (GDPR) compliance demands for deep learning surveillance models, human anonymization is a key research area. Most studies use RGB images as input for generative models, which retain demographic features, compromising anonymization and consistency across frames. We present our initial study into a full-body anonymization pipeline for anomaly detection datasets, where the synthetic person generation never has access to the RGB pedestrian visuals. The proposed pipeline uses a combination of existing models for easier reproducibility. We use YoloV8 for object detection, ClipSeg and BiRefNet for segmentation, OpenPose for pose estimation, and an animation diffusion model. The diffusion model processes only masks and skeletal pose images, removing the problems with using sensitive data. We test on the Avenue dataset. We show that the proposed pipeline can consistently anonymize and change the demographics of detected pedestrians. We discuss the observed problems and the next steps in building a more robust second version.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/JWSCG.2025-6
dc.identifier.issn1213-6972 (print)
dc.identifier.issn1213-6964 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62200
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectdetekce anomáliícs
dc.subjectsyntetická datacs
dc.subjectgenerativní modelycs
dc.subjectotevřená pozicecs
dc.subjectanonymizacecs
dc.subjectdohledcs
dc.subject.translatedanomaly detectionen
dc.subject.translatedsynthetic dataen
dc.subject.translatedgenerative modelsen
dc.subject.translatedopen-poseen
dc.subject.translatedanonymizationen
dc.subject.translatedsurveillanceen
dc.titlePreliminary Study of a Non-Direct Generative Image Anonymization Pipeline for Anomaly Detectionen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size7105254*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
B53.pdf
Size:
6.78 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: