Salvato in:
Dettagli Bibliografici
Autori principali: Triess, Sabrina Cynthia, Leitritz, Timo, Jauch, Christian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.19173
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911912302739456
author Triess, Sabrina Cynthia
Leitritz, Timo
Jauch, Christian
author_facet Triess, Sabrina Cynthia
Leitritz, Timo
Jauch, Christian
contents With rising technologies, the protection of privacy-sensitive information is becoming increasingly important. In industry and production facilities, image or video recordings are beneficial for documentation, tracing production errors or coordinating workflows. Individuals in images or videos need to be anonymized. However, the anonymized data should be reusable for further applications. In this work, we apply the Deep Learning-based full-body anonymization framework DeepPrivacy2, which generates artificial identities, to industrial image and video data. We compare its performance with conventional anonymization techniques. Therefore, we consider the quality of identity generation, temporal consistency, and the applicability of pose estimation and action recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19173
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation
Triess, Sabrina Cynthia
Leitritz, Timo
Jauch, Christian
Computer Vision and Pattern Recognition
With rising technologies, the protection of privacy-sensitive information is becoming increasingly important. In industry and production facilities, image or video recordings are beneficial for documentation, tracing production errors or coordinating workflows. Individuals in images or videos need to be anonymized. However, the anonymized data should be reusable for further applications. In this work, we apply the Deep Learning-based full-body anonymization framework DeepPrivacy2, which generates artificial identities, to industrial image and video data. We compare its performance with conventional anonymization techniques. Therefore, we consider the quality of identity generation, temporal consistency, and the applicability of pose estimation and action recognition.
title Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.19173